Faster R-CNN: Towards Real-Time Object Detection with Region Proposal\n Networks

2015/06/04 by Shaoqing Ren, Kaiming He, Ren, Shaoqing +5 · 6,279 citations
Computer Science · #Advanced Image and Video Retrieval Techniques #Advanced Neural Network Applications #Algorithm #Artificial intelligence #Bottleneck #Computation #Computer Vision and Pattern Recognition (cs.CV) #Computer network #Computer science #Computer vision #Convolutional neural network #Data mining #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Frame (networking) #Frame rate #Information retrieval #Merge (version control) #Multimodal Machine Learning Applications #Object detection #Pascal (unit) #Pattern recognition (psychology) #Pooling #cs.CV

paper · pdf · doi:10.48550/arxiv.1506.01497

published in arXiv (Cornell University) 28, 91-99 (Cornell University) · Extended tech report

openalex publication_date 2015/06/04 · arxiv created 2016/01/06 · arxiv updated 2016/01/07 · openalex created_date 2019/06/27 · openalex updated_date 2026/08/08

Abstract

State-of-the-art object detection networks depend on region proposal\nalgorithms to hypothesize object locations. Advances like SPPnet and Fast R-CNN\nhave reduced the running time of these detection networks, exposing region\nproposal computation as a bottleneck. In this work, we introduce a Region\nProposal Network (RPN) that shares full-image convolutional features with the\ndetection network, thus enabling nearly cost-free region proposals. An RPN is a\nfully convolutional network that simultaneously predicts object bounds and\nobjectness scores at each position. The RPN is trained end-to-end to generate\nhigh-quality region proposals, which are used by Fast R-CNN for detection. We\nfurther merge RPN and Fast R-CNN into a single network by sharing their\nconvolutional features---using the recently popular terminology of neural\nnetworks with 'attention' mechanisms, the RPN component tells the unified\nnetwork where to look. For the very deep VGG-16 model, our detection system has\na frame rate of 5fps (including all steps) on a GPU, while achieving\nstate-of-the-art object detection accuracy on PASCAL VOC 2007, 2012, and MS\nCOCO datasets with only 300 proposals per image. In ILSVRC and COCO 2015\ncompetitions, Faster R-CNN and RPN are the foundations of the 1st-place winning\nentries in several tracks. Code has been made publicly available.\n

Citations

• Backpropagation Applied to Handwritten Zip Code Recognition
• ImageNet classification with deep convolutional neural networks

Cited by

• FcaNet: Frequency Channel Attention Networks
• Edge-Aware and Content-Adaptive Infrared Gas Leak Detection for Industrial Safety Monitoring
• Holi-DETR: Holistic Fashion Item Detection Leveraging Contextual Information
• Exploring Syn-to-Real Domain Adaptation for Military Target Detection
• CLIP-Joint-Detect: End-to-End Joint Training of Object Detectors with Contrastive Vision-Language Supervision
• Learning Where to Focus: Density-Driven Guidance for Detecting Dense Tiny Objects
• DeFloMat: Detection with Flow Matching for Stable and Efficient Generative Object Localization
• Multimodal Semantic-Probabilistic Objectness for Open World Object Detection
• Towards High-Level Semantic Intelligence
• Neuromorphic Object Detection: An In-Depth Study and Future Directions
• Geometry Meets Semantics: Fractional Gradient Stabilization for Semantic-Driven Bounding Box Optimization in Visual Detection Tasks
• Noise-Free One-Step LoRA for Task-Driven Image Restoration with Diffusion Priors
• Advancing All-Weather Building Damage Mapping to the Instance Level: Outcomes and Insights from the 2026 Bright Challenge
• Calibration-Free 3D Multi-Camera People Tracking for Indoor Environment
• Teaching People LLM's Errors and Getting it Right
• Fast SAM2 with Text-Driven Token Pruning
• ORCA: Object Recognition and Comprehension for Archiving Marine Species
• Hierarchical Modeling Approach to Fast and Accurate Table Recognition
• Granular Ball Guided Masking: Structure-aware Data Augmentation
• Benchmarking and Enhancing VLM for Compressed Image Understanding
• TrashDet: Iterative Neural Architecture Search for Efficient Waste Detection
• Real-World Adversarial Attacks on RF-Based Drone Detectors
• Recurrent Off-Policy Deep Reinforcement Learning Doesn't Have to be Slow
• IndicDLP: A Foundational Dataset for Multi-Lingual and Multi-Domain Document Layout Parsing
• Progressive Learned Image Compression for Machine Perception
• PaveSync: A Unified and Comprehensive Dataset for Pavement Distress Analysis and Classification
• Event Extraction in Large Language Model
• PEDESTRIAN: An Egocentric Vision Dataset for Obstacle Detection on Pavements
• YolovN-CBi: A Lightweight and Efficient Architecture for Real-Time Detection of Small UAVs
• Building UI/UX Dataset for Dark Pattern Detection and YOLOv12x-based Real-Time Object Recognition Detection System
• Spectral Discrepancy and Cross-modal Semantic Consistency Learning for Object Detection in Hyperspectral Image
• A two-stream network with global-local feature fusion for bone age assessment
• StereoMV2D: A Sparse Temporal Stereo-Enhanced Framework for Robust Multi-View 3D Object Detection
• FlowDet: Unifying Object Detection and Generative Transport Flows
• SARMAE: Masked Autoencoder for SAR Representation Learning
• LAPX: Lightweight Hourglass Network with Global Context
• From Words to Wavelengths: VLMs for Few-Shot Multispectral Object Detection
• VLA-AN: An Efficient and Onboard Vision-Language-Action Framework for Aerial Navigation in Complex Environments
• A Comprehensive Safety Metric to Evaluate Perception in Autonomous Systems
• Mimicking Human Visual Development for Learning Robust Image Representations
• LFFD: A Light and Fast Face Detector for Edge Devices
• Test-Time Modification: Inverse Domain Transformation for Robust Perception
• WeDetect: Fast Open-Vocabulary Object Detection as Retrieval
• Depth-Copy-Paste: Multimodal and Depth-Aware Compositing for Robust Face Detection
• CarlaNCAP: A Framework for Quantifying the Safety of Vulnerable Road Users in Infrastructure-Assisted Collective Perception Using EuroNCAP Scenarios
• Cross-modal Context-aware Learning for Visual Prompt Guided Multimodal Image Understanding in Remote Sensing
• Reliable Detection of Minute Targets in High-Resolution Aerial Imagery across Temporal Shifts
• Emerging Standards for Machine-to-Machine Video Coding
• Feature Coding for Scalable Machine Vision
• Hands-on Evaluation of Visual Transformers for Object Recognition and Detection
• Microscopic Vehicle Trajectories from Heterogeneous and Area-Based Traffic
• A Distributed Framework for Privacy-Enhanced Vision Transformers on the Edge
• ROI-Packing: Efficient Region-Based Compression for Machine Vision
• Efficient Feature Compression for Machines with Global Statistics Preservation
• Enabling Next-Generation Consumer Experience with Feature Coding for Machines
• New VVC profiles targeting Feature Coding for Machines
• Generalization vs. Specialization: Evaluating Segment Anything Model (SAM3) Zero-Shot Segmentation Against Fine-Tuned YOLO Detectors
• DFIR-DETR: Frequency Domain Enhancement and Dynamic Feature Aggregation for Cross-Scene Small Object Detection
• Omni-Referring Image Segmentation
• JOCA: Task-Driven Joint Optimisation of Camera Hardware and Adaptive Camera Control Algorithms
• CoT4Det: A Chain-of-Thought Framework for Perception-Oriented Vision-Language Tasks
• LeAD-M3D: Leveraging Asymmetric Distillation for Real-Time Monocular 3D Detection
• Fast SceneScript: Accurate and Efficient Structured Language Model via Multi-Token Prediction
• YOLO and SGBM Integration for Autonomous Tree Branch Detection and Depth Estimation in Radiata Pine Pruning Applications
• Rethinking Decoupled Knowledge Distillation: A Predictive Distribution Perspective
• Dual-Stream Spectral Decoupling Distillation for Remote Sensing Object Detection
• "All You Need" is Not All You Need for a Paper Title: On the Origins of a Scientific Meme
• YOLOA: Real-Time Affordance Detection via LLM Adapter
• When and how to automate image analysis for wildlife monitoring? Guidelines and lessons from a worked example of seabirds in a dynamic coastal environment
• ALDI-ray: Adapting the ALDI Framework for Security X-ray Object Detection
• Artemis: Structured Visual Reasoning for Perception Policy Learning
• Chain-of-Ground: Improving GUI Grounding via Iterative Reasoning and Reference Feedback
• Bridging the Scale Gap: Balanced Tiny and General Object Detection in Remote Sensing Imagery
• BlinkBud: Detecting Hazards from Behind via Sampled Monocular 3D Detection on a Single Earbud
• FOD-S2R: A FOD Dataset for Sim2Real Transfer Learning based Object Detection
• Generalised Medical Phrase Grounding
• PAGen: Phase-guided Amplitude Generation for Domain-adaptive Object Detection
• CogEvo-Edu: Cognitive Evolution Educational Multi-Agent Collaborative System
• Analysis of Invasive Breast Cancer in Mammograms Using YOLO, Explainability, and Domain Adaptation
• Hierarchical Feature Integration for Multi-Signal Automatic Modulation Recognition
• DAONet-YOLOv8: An Occlusion-Aware Dual-Attention Network for Tea Leaf Pest and Disease Detection
• BTKD++: Beyond Teachers by Critically Distilling Knowledge from Teacher’s Bias
• UMind-VL: A Generalist Ultrasound Vision-Language Model for Unified Grounded Perception and Comprehensive Interpretation
• Uni-Hema: Unified Model for Digital Hematopathology
• CanKD: Cross-Attention-based Non-local operation for Feature-based Knowledge Distillation
• Co-Training Vision Language Models for Remote Sensing Multi-task Learning
• MedROV: Towards Real-Time Open-Vocabulary Detection Across Diverse Medical Imaging Modalities
• ScenarioCLIP: Pretrained Transferable Visual Language Models and Action-Genome Dataset for Natural Scene Analysis
• Uplifting Table Tennis: A Robust, Real-World Application for 3D Trajectory and Spin Estimation
• Exploring State-of-the-art models for Early Detection of Forest Fires
• Video Object Recognition in Mobile Edge Networks: Local Tracking or Edge Detection?
• Intelligent Image Search Algorithms Fusing Visual Large Models
• HybriDLA: Hybrid Generation for Document Layout Analysis
• Analysis of Deep-Learning Methods in an ISO/TS 15066-Compliant Human-Robot Safety Framework
• Multimodal Real-Time Anomaly Detection and Industrial Applications
• Splatonic: Architecture Support for 3D Gaussian Splatting SLAM via Sparse Processing
• Robust Physical Adversarial Patches Using Dynamically Optimized Clusters
• Can a Second-View Image Be a Language? Geometric and Semantic Cross-Modal Reasoning for X-ray Prohibited Item Detection
• SciPostLayoutTree: A Dataset for Structural Analysis of Scientific Posters
• On the development of an AI performance and behavioural measures for teaching and classroom management
• VK-Det: Visual Knowledge Guided Prototype Learning for Open-Vocabulary Aerial Object Detection
• State and Scene Enhanced Prototypes for Weakly Supervised Open-Vocabulary Object Detection
• REXO: Indoor Multi-View Radar Object Detection via 3D Bounding Box Diffusion
• Benchmarking Nighttime Traffic Sign Recognition with Illumination-Adaptive Detection and Semantic Attribute Reasoning
• Person Recognition in Aerial Surveillance: A Decade Survey
• StreetView-Waste: A Multi-Task Dataset for Urban Waste Management
• T2I-Based Physical-World Appearance Attack against Traffic Sign Recognition Systems in Autonomous Driving
• Controllable Layer Decomposition for Reversible Multi-Layer Image Generation
• Deep Learning for Accurate Vision-based Catch Composition in Tropical Tuna Purse Seiners
• Fast Post-Hoc Confidence Fusion for 3-Class Open-Set Aerial Object Detection
• What Your Features Reveal: Data-Efficient Black-Box Feature Inversion Attack for Split DNNs
• When CNNs Outperform Transformers and Mambas: Revisiting Deep Architectures for Dental Caries Segmentation
• ManipShield: A Unified Framework for Image Manipulation Detection, Localization and Explanation
• Online Data Curation for Object Detection via Marginal Contributions to Dataset-level Average Precision
• OlmoEarth: Stable Latent Image Modeling for Multimodal Earth Observation
• Skeletons Speak Louder than Text: A Motion-Aware Pretraining Paradigm for Video-Based Person Re-Identification
• MCAQ-YOLO: Morphological Complexity-Aware Quantization for Efficient Object Detection with Curriculum Learning
• Backdoor Attacks on Open Vocabulary Object Detectors via Multi-Modal Prompt Tuning
• Self-Supervised Visual Prompting for Cross-Domain Road Damage Detection
• Uncover and Unlearn Nuisances: Agnostic Fully Test-Time Adaptation
• MixAR: Mixture Autoregressive Image Generation
• YOLO-Drone: An Efficient Object Detection Approach Using the GhostHead Network for Drone Images
• LLM-YOLOMS: Large Language Model-based Semantic Interpretation and Fault Diagnosis for Wind Turbine Components
• TubeRMC: Tube-conditioned Reconstruction with Mutual Constraints for Weakly-supervised Spatio-Temporal Video Grounding
• How Can We Effectively Use LLMs for Phishing Detection?: Evaluating the Effectiveness of Large Language Model-based Phishing Detection Models
• Scale-Aware Relay and Scale-Adaptive Loss for Tiny Object Detection in Aerial Images
• Thermally Activated Dual-Modal Adversarial Clothing against AI Surveillance Systems
• RF-DETR: Neural Architecture Search for Real-Time Detection Transformers
• Machines Serve Human: A Novel Variable Human-machine Collaborative Compression Framework
• Generalizable Blood Cell Detection via Unified Dataset and Faster R-CNN
• RAPTR: Radar-based 3D Pose Estimation using Transformer
• Evaluating Gemini LLM in Food Image-Based Recipe and Nutrition Description with EfficientNet-B4 Visual Backbone
• Pixel-level Quality Assessment for Oriented Object Detection
• High-Quality Proposal Encoding and Cascade Denoising for Imaginary Supervised Object Detection
• Visual Bridge: Universal Visual Perception Representations Generating
• Cross Modal Fine-Grained Alignment via Granularity-Aware and Region-Uncertain Modeling
• SortWaste: A Densely Annotated Dataset for Object Detection in Industrial Waste Sorting
• Beyond Boundaries: Leveraging Vision Foundation Models for Source-Free Object Detection
• SFFR: Spatial-Frequency Feature Reconstruction for Multispectral Aerial Object Detection
• A Visual Perception-Based Tunable Framework and Evaluation Benchmark for H.265/HEVC ROI Encryption
• Interaction-Centric Knowledge Infusion and Transfer for Open-Vocabulary Scene Graph Generation
• Referring Expressions as a Lens into Spatial Language Grounding in Vision-Language Models
• Semantic-Guided Natural Language and Visual Fusion for Cross-Modal Interaction Based on Tiny Object Detection
• OregairuChar: A Benchmark Dataset for Character Appearance Frequency Analysis in My Teen Romantic Comedy SNAFU
• SnowyLane: Robust Lane Detection on Snow-covered Rural Roads Using Infrastructural Elements
• Automatic detection of CMEs using synthetically-trained Mask R-CNN
• Individual identification of brown bears using pose-aware metric learning
• MVAFormer: RGB-based Multi-View Spatio-Temporal Action Recognition with Transformer
• DetectiumFire: A Comprehensive Multi-modal Dataset Bridging Vision and Language for Fire Understanding
• Object Detection as an Optional Basis: A Graph Matching Network for Cross-View UAV Localization
• In-Context Adaptation of VLMs for Few-Shot Cell Detection in Optical Microscopy
• CGF-DETR: Cross-Gated Fusion DETR for Enhanced Pneumonia Detection in Chest X-rays
• A Hybrid YOLOv5-SSD IoT-Based Animal Detection System for Durian Plantation Protection
• Benchmarking individual tree segmentation using multispectral airborne laser scanning data: the FGI-EMIT dataset
• Sewer pipeline condition assessment and defect detection using computer vision
• Temporal Reasoning Graph for Activity Recognition
• An Efficient and Generalizable Transfer Learning Method for Weather Condition Detection on Ground Terminals
• Enhancing Trustworthy GUI Grounding via Self-Critiqued Reinforcement Learning
• Soft Task-Aware Routing of Experts for Equivariant Representation Learning
• SilhouetteTell: Practical Video Identification Leveraging Blurred Recordings of Video Subtitles
• Gaussian Combined Distance: A Generic Metric for Object Detection
• Improving Classification of Occluded Objects through Scene Context
• Detecting Unauthorized Vehicles using Deep Learning for Smart Cities: A Case Study on Bangladesh
• VISAT: Benchmarking Adversarial and Distribution Shift Robustness in Traffic Sign Recognition with Visual Attributes
• Bridging Vision, Language, and Mathematics: Pictographic Character Reconstruction with Bézier Curves
• Adversarial Domain Randomization
• Right for the Right Reasons: Avoiding Reasoning Shortcuts via Prototypical Neurosymbolic AI
• Learning to Refine Object Segments
• Hire-MLP: Vision MLP via Hierarchical Rearrangement
• Exemplar-Based Open-Set Panoptic Segmentation Network
• Class-specific Anchoring Proposal for 3D Object Recognition in LIDAR and RGB Images
• Hybrid Task Cascade for Instance Segmentation
• Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions
• Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training
• Bridging Knowledge Graphs to Generate Scene Graphs
• ACP: Automatic Channel Pruning via Clustering and Swarm Intelligence Optimization for CNN
• Scaling Egocentric Vision: The EPIC-KITCHENS Dataset
• Interpretable Image-Level Acne Severity Grading via EfficientNet-B0 Transfer Learning and Grad-CAM
• A Single-shot Object Detector with Feature Aggragation and Enhancement
• Scaled-YOLOv4: Scaling Cross Stage Partial Network
• DeepIris: Iris Recognition Using A Deep Learning Approach
• Exploring Multi-Branch and High-Level Semantic Networks for Improving Pedestrian Detection
• Pose-based Modular Network for Human-Object Interaction Detection
• Probabilistic and Geometric Depth: Detecting Objects in Perspective
• BERTgrid: Contextualized Embedding for 2D Document Representation and Understanding
• AdaVQA: Overcoming Language Priors with Adapted Margin Cosine Loss
• Fine-Grained Object Detection over Scientific Document Images with Region Embeddings
• Analysing object detectors from the perspective of co-occurring object categories
• Temporal Recurrent Networks for Online Action Detection
• Unsupervised Multiple Person Tracking using AutoEncoder-Based Lifted Multicuts
• Crossover Learning for Fast Online Video Instance Segmentation
• Transfer Learning-based Road Damage Detection for Multiple Countries
• Libra R-CNN: Towards Balanced Learning for Object Detection
• Vision-based Robot Manipulation Learning via Human Demonstrations
• ByteTrack: Multi-Object Tracking by Associating Every Detection Box
• Quasi-Dense Similarity Learning for Multiple Object Tracking
• Learning Channel Inter-dependencies at Multiple Scales on Dense Networks for Face Recognition
• Action Genome: Actions as Composition of Spatio-temporal Scene Graphs
• CRIC: A VQA Dataset for Compositional Reasoning on Vision and Commonsense
• QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information
• Classification based Grasp Detection using Spatial Transformer Network
• On the Importance of Visual Context for Data Augmentation in Scene\n Understanding
• Ideas Have Genomes: Benchmarking Scientific Lineage Reasoning and Lineage-Grounded Idea Generation
• Image Captioning: Transforming Objects into Words
• On the Origin of Deep Learning
• MultiPoseNet: Fast Multi-Person Pose Estimation using Pose Residual Network
• Detection as Regression: Certified Object Detection by Median Smoothing
• EfficientDet: Scalable and Efficient Object Detection
• Siamese Box Adaptive Network for Visual Tracking
• A Structure-Aware Relation Network for Thoracic Diseases Detection and Segmentation
• Fully Convolutional Networks for Panoptic Segmentation
• Are you doing what I say? On modalities alignment in ALFRED
• Improving Description-based Person Re-identification by Multi-granularity Image-text Alignments
• A Solution to Product detection in Densely Packed Scenes
• Data Extraction from Charts via Single Deep Neural Network
• Refinements in Motion and Appearance for Online Multi-Object Tracking
• End-to-End Incremental Learning
• Dynamic Adversarial Patch for Evading Object Detection Models
• Generative Partition Networks for Multi-Person Pose Estimation
• Dynamic Resolution Network
• KL-Divergence-Based Region Proposal Network for Object Detection
• Toward Intelligent Sensing: Intermediate Deep Feature Compression
• DeepACEv2: Automated Chromosome Enumeration in Metaphase Cell Images Using Deep Convolutional Neural Networks
• Feedback Attention for Cell Image Segmentation
• End-to-End Video Object Detection with Spatial-Temporal Transformers
• Decision-based Universal Adversarial Attack
• Probing Inter-modality: Visual Parsing with Self-Attention for Vision-Language Pre-training
• Semantic Foggy Scene Understanding with Synthetic Data
• Improving Object Detection from Scratch via Gated Feature Reuse
• Visual Semantic Reasoning for Image-Text Matching
• SAIA: Split Artificial Intelligence Architecture for Mobile Healthcare System
• Self-Supervised Visual Feature Learning With Deep Neural Networks: A Survey
• Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspective
• FastPose: Towards Real-time Pose Estimation and Tracking via Scale-normalized Multi-task Networks
• What Vision-Language Models `See' when they See Scenes
• SiamCAR: Siamese Fully Convolutional Classification and Regression for Visual Tracking
• Improving Network Slimming with Nonconvex Regularization
• Localization in the Crowd with Topological Constraints
• DeepFirearm: Learning Discriminative Feature Representation for Fine-grained Firearm Retrieval
• An End-to-End Network for Panoptic Segmentation
• A Self Validation Network for Object-Level Human Attention Estimation
• Progressive Coordinate Transforms for Monocular 3D Object Detection
• GhostNet: More Features From Cheap Operations
• TextNet: Irregular Text Reading from Images with an End-to-End Trainable Network
• LSKNet: A Foundation Lightweight Backbone for Remote Sensing
• The Devil is in the Boundary: Exploiting Boundary Representation for Basis-based Instance Segmentation
• HAMBox: Delving into Online High-quality Anchors Mining for Detecting Outer Faces
• SPROUT: A Scalable Diffusion Foundation Model for Agricultural Vision
• Real-world Mapping of Gaze Fixations Using Instance Segmentation for Road Construction Safety Applications
• You Only Look & Listen Once: Towards Fast and Accurate Visual Grounding
• Mask Transfiner for High-Quality Instance Segmentation
• Diagnosing Error in Temporal Action Detectors
• Unsupervised Domain Adaptation for Multispectral Pedestrian Detection
• 3DIoUMatch: Leveraging IoU Prediction for Semi-Supervised 3D Object Detection
• Enhancing Rotated Object Detection via Anisotropic Gaussian Bounding Box and Bhattacharyya Distance
• Temporal-Channel Transformer for 3D Lidar-Based Video Object Detection in Autonomous Driving
• Distilling Image Classifiers in Object Detectors
• High-throughput Verticillium wilt detection in cotton: A comparative study of faster R-CNN and YOLOv11
• Involution: Inverting the Inherence of Convolution for Visual Recognition
• AQD: Towards Accurate Fully-Quantized Object Detection
• GaTector+: A Unified Head-free Framework for Gaze Object and Gaze Following Prediction
• Membership Inference Attacks Against Object Detection Models
• Test-Time Adaptive Object Detection with Foundation Model
• Adversarially Robust Quantum Transfer Learning
• Crop yield prediction using machine learning: A systematic literature review
• Manipulating Identical Filter Redundancy for Efficient Pruning on Deep and Complicated CNN
• FruitProm: Probabilistic Maturity Estimation and Detection of Fruits and Vegetables
• Siamese Keypoint Prediction Network for Visual Object Tracking
• Corner Proposal Network for Anchor-free, Two-stage Object Detection
• TRIE: End-to-End Text Reading and Information Extraction for Document Understanding
• Feature Fusion for Online Mutual Knowledge Distillation
• Delving into the Imbalance of Positive Proposals in Two-stage Object Detection
• Delving into Cascaded Instability: A Lipschitz Continuity View on Image Restoration and Object Detection Synergy
• Multilevel Language and Vision Integration for Text-to-Clip Retrieval
• Deep GrabCut for Object Selection
• Synergistic Neural Forecasting of Air Pollution with Stochastic Sampling
• Building Damage Detection in Satellite Imagery Using Convolutional Neural Networks
• Gastroscopic Panoramic View: Application to Automatic Polyps Detection under Gastroscopy
• A Few-Shot Sequential Approach for Object Counting
• OOS-DSD: Improving Out-of-stock Detection in Retail Images using Auxiliary Tasks
• IoU-aware Single-stage Object Detector for Accurate Localization
• KongNet: A Multi-headed Deep Learning Model for Detection and Classification of Nuclei in Histopathology Images
• Track to Detect and Segment: An Online Multi-Object Tracker
• FRBNet: Revisiting Low-Light Vision through Frequency-Domain Radial Basis Network
• PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation
• Weakly Supervised Action Selection Learning in Video
• Resolving the cybersecurity Data Sharing Paradox to scale up cybersecurity via a co-production approach towards data sharing
• DQ3D: Depth-guided Query for Transformer-Based 3D Object Detection in Traffic Scenarios
• Learning Single/Multi-Attribute of Object with Symmetry and Group
• Rethinking Inference Placement for Deep Learning across Edge and Cloud Platforms: A Multi-Objective Optimization Perspective and Future Directions
• Measuring and Predicting Tag Importance for Image Retrieval
• A Critical Study on Tea Leaf Disease Detection using Deep Learning Techniques
• Doubly Smoothed Density Estimation with Application on Miners' Unsafe Act Detection
• SARVLM: A Vision Language Foundation Model for Semantic Understanding in SAR Imagery
• TensorMask: A Foundation for Dense Object Segmentation
• Syn2Real: A New Benchmark forSynthetic-to-Real Visual Domain Adaptation
• Object Recognition with and without Objects
• DiffusionLane: Diffusion Model for Lane Detection
• Attention Residual Fusion Network with Contrast for Source-free Domain Adaptation
• Group-Attention Single-Shot Detector (GA-SSD): Finding Pulmonary Nodules in Large-Scale CT Images
• On Thin Ice: Towards Explainable Conservation Monitoring via Attribution and Perturbations
• Widening and Squeezing: Towards Accurate and Efficient QNNs
• FrameShield: Adversarially Robust Video Anomaly Detection
• GRAP-MOT: Unsupervised Graph-based Position Weighted Person Multi-camera Multi-object Tracking in a Highly Congested Space
• TerraGen: A Unified Multi-Task Layout Generation Framework for Remote Sensing Data Augmentation
• FVNet: 3D Front-View Proposal Generation for Real-Time Object Detection from Point Clouds
• Joint Multimedia Event Extraction from Video and Article
• WhaleVAD-BPN: Improving Baleen Whale Call Detection with Boundary Proposal Networks and Post-processing Optimisation
• 3D-DETNet: a Single Stage Video-Based Vehicle Detector
• Stand-Alone Self-Attention in Vision Models
• Pose Augmentation: Class-agnostic Object Pose Transformation for Object Recognition
• Synthetic Data for Robust Runway Detection
• Barlow Twins: Self-Supervised Learning via Redundancy Reduction
• Deep Learning Based Domain Adaptation Methods in Remote Sensing: A Comprehensive Survey
• Physics-Guided Fusion for Robust 3D Tracking of Fast Moving Small Objects
• Real-Time Currency Detection and Voice Feedback for Visually Impaired Individuals
• General Instance Distillation for Object Detection
• A Study of Face Obfuscation in ImageNet
• Detecting Text in Natural Image with Connectionist Text Proposal Network
• Can You Trust What You See? Alpha Channel No-Box Attacks on Video Object Detection
• Towards Single-Source Domain Generalized Object Detection via Causal Visual Prompts
• Automated Morphological Analysis of Neurons in Fluorescence Microscopy Using YOLOv8
• From See to Shield: ML-Assisted Fine-Grained Access Control for Visual Data
• Vision-Based Mistake Analysis in Procedural Activities: A Review of Advances and Challenges
• A Unified Detection Pipeline for Robust Object Detection in Fisheye-Based Traffic Surveillance
• Temporal Action Localization with Variance-Aware Networks
• Kinematic Analysis and Integration of Vision Algorithms for a Mobile Manipulator Employed Inside a Self-Driving Laboratory
• Ninja Codes: Neurally Generated Fiducial Markers for Stealthy 6-DoF Tracking
• iReason: Multimodal Commonsense Reasoning using Videos and Natural Language with Interpretability
• From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Network
• Just Pick a Sign: Optimizing Deep Multitask Models with Gradient Sign Dropout
• SEAL: Semantic-Aware Hierarchical Learning for Generalized Category Discovery
• Transferable Active Grasping and Real Embodied Dataset
• Multiple Object Tracking with Mixture Density Networks for Trajectory Estimation
• Cops-Ref: A new Dataset and Task on Compositional Referring Expression Comprehension
• Comparative Analysis of Object Detection Algorithms for Surface Defect Detection
• Learning Human-Object Interaction as Groups
• Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network
• Unbiased Object Detection Beyond Frequency with Visually Prompted Image Synthesis
• Modeling and Analysis of Energy Harvesting and Smart Grid-Powered Wireless Communication Networks: A Contemporary Survey
• Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised Learning
• Integrating Trustworthy Artificial Intelligence with Energy-Efficient Robotic Arms for Waste Sorting
• A Single Set of Adversarial Clothes Breaks Multiple Defense Methods in the Physical World
• MSSDF: Modality-Shared Self-supervised Distillation for High-Resolution Multi-modal Remote Sensing Image Learning
• Enrich and Detect: Video Temporal Grounding with Multimodal LLMs
• Vision Pair Learning: An Efficient Training Framework for Image Classification
• Open-set 3D Object Detection
• Moment-Based Domain Adaptation: Learning Bounds and Algorithms
• ReCon: Region-Controllable Data Augmentation with Rectification and Alignment for Object Detection
• MOBIUS: Big-to-Mobile Universal Instance Segmentation via Multi-modal Bottleneck Fusion and Calibrated Decoder Pruning
• CaptionFormer: Unified Segmentation, Tracking, and Captioning for Spatio-Temporal Objects
• MotionNet: Joint Perception and Motion Prediction for Autonomous Driving Based on Bird's Eye View Maps
• Cross-Layer Feature Self-Attention Module for Multi-Scale Object Detection
• Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Driving
• Accelerating Minibatch Stochastic Gradient Descent using Typicality Sampling
• BoardVision: Deployment-ready and Robust Motherboard Defect Detection with YOLO+Faster-RCNN Ensemble
• Spatial Preference Rewarding for MLLMs Spatial Understanding
• A Modular Object Detection System for Humanoid Robots Using YOLO
• Fusion Meets Diverse Conditions: A High-diversity Benchmark and Baseline for UAV-based Multimodal Object Detection with Condition Cues
• Universally Slimmable Networks and Improved Training Techniques
• Deep learning-based prediction of response to HER2-targeted neoadjuvant chemotherapy from pre-treatment dynamic breast MRI: A multi-institutional validation study
• Unbiased Scene Graph Generation from Biased Training
• Progressive Cluster Purification for Unsupervised Feature Learning
• OS-HGAdapter: Open Semantic Hypergraph Adapter for Large Language Models Assisted Entropy-Enhanced Image-Text Alignment
• Learning Independent Instance Maps for Crowd Localization
• DocVQA: A Dataset for VQA on Document Images
• Detect Anything via Next Point Prediction
• Heterogeneous Memory Enhanced Multimodal Attention Model for Video Question Answering
• Quantifying the presence of graffiti in urban environments
• A Review of Longitudinal Radiology Report Generation: Dataset Composition, Methods, and Performance Evaluation
• The Impact of Synthetic Data on Object Detection Model Performance: A Comparative Analysis with Real-World Data
• Controllable Collision Scenario Generation via Collision Pattern Prediction
• DRL: Discriminative Representation Learning with Parallel Adapters for Class Incremental Learning
• Post-surgical Endometriosis Segmentation in Laparoscopic Videos
• Visual Question Answering Using Semantic Information from Image Descriptions
• NV3D: Leveraging Spatial Shape Through Normal Vector-based 3D Object Detection
• Reliable Cross-modal Alignment via Prototype Iterative Construction
• Cascade RetinaNet: Maintaining Consistency for Single-Stage Object Detection
• Source-Free Object Detection with Detection Transformer
• Implicit Feature Pyramid Network for Object Detection
• Weeping and Gnashing of Teeth: Teaching Deep Learning in Image and Video Processing Classes
• Image-to-Video Transfer Learning based on Image-Language Foundation Models: A Comprehensive Survey
• Layout-Independent License Plate Recognition via Integrated Vision and Language Models
• Taming a Retrieval Framework to Read Images in Humanlike Manner for Augmenting Generation of MLLMs
• Ordinal Scale Traffic Congestion Classification with Multi-Modal Vision-Language and Motion Analysis
• The Importance and the Limitations of Sim2Real for Robotic Manipulation in Precision Agriculture
• MRI Brain Tumor Detection with Computer Vision
• PSRR-MaxpoolNMS: Pyramid Shifted MaxpoolNMS with Relationship Recovery
• Learning to Reweight with Deep Interactions
• Towards General Purpose Vision Systems
• Patch-as-Decodable-Token: Towards Unified Multi-Modal Vision Tasks in MLLMs
• Data-efficient Alignment of Multimodal Sequences by Aligning Gradient Updates and Internal Feature Distributions
• Leveraging Prior Knowledge of Diffusion Model for Person Search
• CDSA: Cross-Dimensional Self-Attention for Multivariate, Geo-tagged Time Series Imputation
• SimpleDet: A Simple and Versatile Distributed Framework for Object Detection and Instance Recognition
• Pose Neural Fabrics Search
• Re-ID Driven Localization Refinement for Person Search
• Drill the Cork of Information Bottleneck by Inputting the Most Important Data
• Regional Homogeneity: Towards Learning Transferable Universal Adversarial Perturbations Against Defenses
• Learning Transferable Adversarial Examples via Ghost Networks
• TARO: Toward Semantically Rich Open-World Object Detection
• Robustness of Object Recognition under Extreme Occlusion in Humans and Computational Models
• Denoised Diffusion for Object-Focused Image Augmentation
• Synthetic Object Compositions for Scalable and Accurate Learning in Detection, Segmentation, and Grounding
• A Novel Automation-Assisted Cervical Cancer Reading Method Based on Convolutional Neural Network
• Towards Adversarially Robust Object Detection
• Structured Knowledge Distillation for Dense Prediction
• Exploring Data Aggregation and Transformations to Generalize across Visual Domains
• Learning to Generate Content-Aware Dynamic Detectors
• Deep Learning based Multi-Modal Sensing for Tracking and State Extraction of Small Quadcopters
• OPANAS: One-Shot Path Aggregation Network Architecture Search for Object Detection
• Fast-Tracker 2.0: Improving Autonomy of Aerial Tracking with Active Vision and Human Location Regression
• Robust 2D/3D Vehicle Parsing in CVIS
• Curriculum Learning with Diversity for Supervised Computer Vision Tasks
• Spatial-Temporal Block and LSTM Network for Pedestrian Trajectories Prediction
• Curriculum Learning with Synthetic Data for Enhanced Pulmonary Nodule Detection in Chest Radiographs
• Multiple interaction learning with question-type prior knowledge for constraining answer search space in visual question answering
• MimicDet: Bridging the Gap Between One-Stage and Two-Stage Object Detection
• X-LXMERT: Paint, Caption and Answer Questions with Multi-Modal Transformers
• Spatio-Temporal Action Detection with Multi-Object Interaction
• Region Proposal Network with Graph Prior and IoU-Balance Loss for Landmark Detection in 3D Ultrasound
• EOLO: Embedded Object Segmentation only Look Once
• More Grounded Image Captioning by Distilling Image-Text Matching Model
• Tracking by Instance Detection: A Meta-Learning Approach
• G-TAD: Sub-Graph Localization for Temporal Action Detection
• A Unified Object Motion and Affinity Model for Online Multi-Object Tracking
• Two-Stream AMTnet for Action Detection
• Explaining raw data complexity to improve satellite onboard processing
• Less is More: ClipBERT for Video-and-Language Learning via Sparse Sampling
• The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models
• Efficient Discriminative Joint Encoders for Large Scale Vision-Language Reranking
• Getting the Numbers Right\unicodex2014Modelling Multi-Class Object Counting in Dense and Varied Scenes
• VIOLIN: A Large-Scale Dataset for Video-and-Language Inference
• Ultralytics YOLO Evolution: An Overview of YOLO26, YOLO11, YOLOv8 and YOLOv5 Object Detectors for Computer Vision and Pattern Recognition
• Neuroplastic Modular Framework: Cross-Domain Image Classification of Garbage and Industrial Surfaces
• Diverse Sample Generation: Pushing the Limit of Generative Data-free Quantization
• Comparative Analysis of YOLOv5, Faster R-CNN, SSD, and RetinaNet for Motorbike Detection in Kigali Autonomous Driving Context
• Improving Transferability of Adversarial Examples with Input Diversity
• 3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans
• WebVision Database: Visual Learning and Understanding from Web Data
• Multi-Scale Aligned Distillation for Low-Resolution Detection
• Attention Branch Network: Learning of Attention Mechanism for Visual Explanation
• Reformulating HOI Detection as Adaptive Set Prediction
• Cross-View Open-Vocabulary Object Detection in Aerial Imagery
• Quantum-soft QUBO Suppression for Accurate Object Detection
• PPR-FCN: Weakly Supervised Visual Relation Detection via Parallel Pairwise R-FCN
• Detecting Noteheads in Handwritten Scores with ConvNets and Bounding Box Regression
• Video Instance Segmentation
• Referring Expression Comprehension for Small Objects
• A Hybrid Co-Finetuning Approach for Visual Bug Detection in Video Games
• Conditional Pseudo-Supervised Contrast for Data-Free Knowledge Distillation
• Bayesian Test-time Adaptation for Object Recognition and Detection with Vision-language Models
• Align Your Query: Representation Alignment for Multimodality Medical Object Detection
• IMAGEdit: Let Any Subject Transform
• Fast Object Detection in Compressed Video
• Group-based Distinctive Image Captioning with Memory Attention
• Improving localization-based approaches for breast cancer screening exam classification
• Semantic Visual Simultaneous Localization and Mapping: A Survey on State of the Art, Challenges, and Future Directions
• Momentum Contrast for Unsupervised Visual Representation Learning
• TAP: Text-Aware Pre-training for Text-VQA and Text-Caption
• Advances in Medical Image Segmentation: A Comprehensive Survey with a Focus on Lumbar Spine Applications
• VisualBERT: A Simple and Performant Baseline for Vision and Language
• Learning Multi-level Deep Representations for Image Emotion Classification
• Iterative Answer Prediction with Pointer-Augmented Multimodal Transformers for TextVQA
• Dynamic Anchor Learning for Arbitrary-Oriented Object Detection
• Looking Beyond the Known: Towards a Data Discovery Guided Open-World Object Detection
• Multi-View Camera System for Variant-Aware Autonomous Vehicle Inspection and Defect Detection
• Self-Supervised Anatomical Consistency Learning for Vision-Grounded Medical Report Generation
• Hybrid Dual-Batch and Cyclic Progressive Learning for Efficient Distributed Training
• VLM-FO1: Bridging the Gap Between High-Level Reasoning and Fine-Grained Perception in VLMs
• FishNet++: Analyzing the capabilities of Multimodal Large Language Models in marine biology
• YOLO26: Key Architectural Enhancements and Performance Benchmarking for Real-Time Object Detection
• TP-MVCC: Tri-plane Multi-view Fusion Model for Silkie Chicken Counting
• A Fast Knowledge Distillation Framework for Visual Recognition
• Dense Contrastive Learning for Self-Supervised Visual Pre-Training
• S3VAE: Self-Supervised Sequential VAE for Representation Disentanglement and Data Generation
• SPLAT: Semantic Pixel-Level Adaptation Transforms for Detection
• 2nd Place Solution to ECCV 2020 VIPriors Object Detection Challenge
• Semantically-Aware Strategies for Stereo-Visual Robotic Obstacle Avoidance
• Understanding the Effects of Pre-Training for Object Detectors via Eigenspectrum
• A Multi-Camera Vision-Based Approach for Fine-Grained Assembly Quality Control
• Diff-3DCap: Shape Captioning with Diffusion Models
• Focusing on What Matters: Object-Agent-centric Tokenization for Vision Language Action models
• Voxel-FPN: multi-scale voxel feature aggregation in 3D object detection from point clouds
• Representing Videos as Discriminative Sub-graphs for Action Recognition
• FracDetNet: Advanced Fracture Detection via Dual-Focus Attention and Multi-scale Calibration in Medical X-ray Imaging
• Enhanced Fracture Diagnosis Based on Critical Regional and Scale Aware in YOLO
• Answer-checking in Context: A Multi-modal FullyAttention Network for Visual Question Answering
• Soft Sampling for Robust Object Detection
• Learning Modulated Loss for Rotated Object Detection
• Tracking Objects as Points
• Exploiting long-term temporal dynamics for video captioning
• One-Shot Object Detection without Fine-Tuning
• TSDM: Tracking by SiamRPN++ with a Depth-refiner and a Mask-generator
• Cross-Modality Relevance for Reasoning on Language and Vision
• Visual Relationship Detection using Scene Graphs: A Survey
• Scope Head for Accurate Localization in Object Detection
• COCAS: A Large-Scale Clothes Changing Person Dataset for Re-identification
• End-to-End Pseudo-LiDAR for Image-Based 3D Object Detection
• γ-Quant: Towards Learnable Quantization for Low-bit Pattern Recognition
• HierLight-YOLO: A Hierarchical and Lightweight Object Detection Network for UAV Photography
• Multilingual Vision-Language Models, A Survey
• Spatial Reasoning in Foundation Models: Benchmarking Object-Centric Spatial Understanding
• Enhancing Vehicle Detection under Adverse Weather Conditions with Contrastive Learning
• Incorporating Scene Context and Semantic Labels for Enhanced Group-level Emotion Recognition
• MS-YOLO: Infrared Object Detection for Edge Deployment via MobileNetV4 and SlideLoss
• Deep Watershed Detector for Music Object Recognition
• Learning Student Networks via Feature Embedding
• AI-Enabled Crater-Based Navigation for Lunar Mapping
• FCPose: Fully Convolutional Multi-Person Pose Estimation with Dynamic Instance-Aware Convolutions
• DeFacto: Counterfactual Thinking with Images for Enforcing Evidence-Grounded and Faithful Reasoning
• FSMODNet: A Closer Look at Few-Shot Detection in Multispectral Data
• Resolving Class Imbalance in Object Detection with Weighted Cross Entropy Losses
• Visually Grounded Continual Learning of Compositional Phrases
• CompressAI-Vision: Open-source software to evaluate compression methods for computer vision tasks
• Self-Critical Reasoning for Robust Visual Question Answering
• LXMERT: Learning Cross-Modality Encoder Representations from Transformers
• Discrete Diffusion for Reflective Vision-Language-Action Models in Autonomous Driving
• Unleashing the Potential of the Semantic Latent Space in Diffusion Models for Image Dehazing
• SDE-DET: A Precision Network for Shatian Pomelo Detection in Complex Orchard Environments
• GridMask Data Augmentation
• DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution
• BiTAA: A Bi-Task Adversarial Attack for Object Detection and Depth Estimation via 3D Gaussian Splatting
• Monitoring spatial sustainable development: Semi-automated analysis of satellite and aerial images for energy transition and sustainability indicators
• MM-FSOD: Meta and metric integrated few-shot object detection
• The 1st Tiny Object Detection Challenge:Methods and Results
• Not Only Look But Observe: Variational Observation Model of Scene-Level 3D Multi-Object Understanding for Probabilistic SLAM
• Structure-Aware Face Clustering on a Large-Scale Graph with \bf10⁷ Nodes
• One Patch Is Enough: Reinforcement-Optimized Visual Token Grounding for MLLM-Based Scene Text Spotting
• Conditional Convolutions for Instance Segmentation
• MSG-Transformer: Exchanging Local Spatial Information by Manipulating Messenger Tokens
• Beyond Classification: Pathology Foundation Models as Detection Encoders for Mitotic Figures
• Improving Object Detection with Selective Self-supervised Self-training
• Whole-Body Human Pose Estimation in the Wild
• Deep learning for brake squeal: vibration detection, characterization and prediction
• Commonality-Parsing Network across Shape and Appearance for Partially Supervised Instance Segmentation
• Towards a Generic Diver-Following Algorithm: Balancing Robustness and Efficiency in Deep Visual Detection
• Hard Negative Mixing for Contrastive Learning
• Image Captioning based on Deep Learning Methods: A Survey
• Towards Autonomous Aircraft Surveillance from Nanosatellites through On-Board Inference and Generative Data Augmentation
• Recurrence along Depth: Deep Convolutional Neural Networks with Recurrent Layer Aggregation
• A scalar per patch from pre-trained ViTs enables fast moving navigation in the real world
• A Multi-Stage Attentive Transfer Learning Framework for Improving COVID-19 Diagnosis
• Exploring the Capacity of an Orderless Box Discretization Network for Multi-orientation Scene Text Detection
• Compare and Reweight: Distinctive Image Captioning Using Similar Images Sets
• Semantic Understanding of Scenes Through the ADE20K Dataset
• A CNN Approach to Simultaneously Count Plants and Detect Plantation-Rows from UAV Imagery
• CLIP-Adapter: Better Vision-Language Models with Feature Adapters
• Multi-view Tracking, Re-ID, and Social Network Analysis of a Flock of Visually Similar Birds in an Outdoor Aviary
• FADE: A Task-Agnostic Upsampling Operator for Encoder–Decoder Architectures
• RevealNet: Seeing Behind Objects in RGB-D Scans
• Semi-Autoregressive Transformer for Image Captioning
• Fast Video Shot Transition Localization with Deep Structured Models
• RiO-DETR: DETR for Real-time Oriented Object Detection
• Gesture Recognition for Initiating Human-to-Robot Handovers
• Forest R-CNN: Large-Vocabulary Long-Tailed Object Detection and Instance Segmentation
• Representation Sharing for Fast Object Detector Search and Beyond
• Where are the Blobs: Counting by Localization with Point Supervision
• Fashion Captioning: Towards Generating Accurate Descriptions with Semantic Rewards
• Gotta Adapt 'Em All: Joint Pixel and Feature-Level Domain Adaptation for Recognition in the Wild
• TuningIQA: Fine-Grained Blind Image Quality Assessment for Livestreaming Camera Tuning
• Adaptive Offline Quintuplet Loss for Image-Text Matching
• A Performance Comparison of Loss Functions for Deep Face Recognition
• Joint Face Detection and Facial Motion Retargeting for Multiple Faces
• IoU Attack: Towards Temporally Coherent Black-Box Adversarial Attack for Visual Object Tracking
• Human-centric Spatio-Temporal Video Grounding With Visual Transformers
• Weakly-Supervised Spatio-Temporally Grounding Natural Sentence in Video
• Deep Affinity Net: Instance Segmentation via Affinity
• ReLaText: Exploiting Visual Relationships for Arbitrary-Shaped Scene Text Detection with Graph Convolutional Networks
• Bringing in the outliers: A sparse subspace clustering approach to learn a dictionary of mouse ultrasonic vocalizations
• RobustTAD: Robust Time Series Anomaly Detection via Decomposition and Convolutional Neural Networks
• Globally-Aware Multiple Instance Classifier for Breast Cancer Screening
• Learning semantic Image attributes using Image recognition and knowledge graph embeddings
• Object Detection in the Context of Mobile Augmented Reality
• Learning to Discriminate Information for Online Action Detection
• Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation
• SOLO: A Simple Framework for Instance Segmentation
• Stuck on Suggestions: Automation Bias, the Anchoring Effect, and the Factors That Shape Them in Computational Pathology
• Self-supervised 6D Object Pose Estimation for Robot Manipulation
• Exploiting Playbacks in Unsupervised Domain Adaptation for 3D Object Detection
• SuperOCR: A Conversion from Optical Character Recognition to Image Captioning
• Object DGCNN: 3D Object Detection using Dynamic Graphs
• Unsupervised Part Discovery via Feature Alignment
• Multimodal Learning for Hateful Memes Detection
• Automatic Detection of Cardiac Chambers Using an Attention-based YOLOv4 Framework from Four-chamber View of Fetal Echocardiography
• Positional Encoding as Spatial Inductive Bias in GANs
• ParaNet: Deep Regular Representation for 3D Point Clouds
• Box-Level Class-Balanced Sampling for Active Object Detection
• Robust Segmentation of Optic Disc and Cup from Fundus Images Using Deep Neural Networks
• Self-supervised pre-training and contrastive representation learning for multiple-choice video QA
• From Unstable to Playable: Stabilizing Angry Birds Levels via Object Segmentation
• DRG: Dual Relation Graph for Human-Object Interaction Detection
• Region Refinement Network for Salient Object Detection
• Advancing Metallic Surface Defect Detection via Anomaly-Guided Pretraining on a Large Industrial Dataset
• Physical Adversarial Attack on Vehicle Detector in the Carla Simulator
• Latent Danger Zone: Distilling Unified Attention for Cross-Architecture Black-box Attacks
• A Deep Ordinal Distortion Estimation Approach for Distortion Rectification
• Language-in-the-Loop Culvert Inspection on the Erie Canal
• Multi-needle Localization for Pelvic Seed Implant Brachytherapy based on Tip-handle Detection and Matching
• Searching for Accurate Binary Neural Architectures
• Improving RetinaNet for CT Lesion Detection with Dense Masks from Weak RECIST Labels
• Two-Stream Region Convolutional 3D Network for Temporal Activity Detection
• Visual Instruction Pretraining for Domain-Specific Foundation Models
• DepTR-MOT: Unveiling the Potential of Depth-Informed Trajectory Refinement for Multi-Object Tracking
• Fourier Contour Embedding for Arbitrary-Shaped Text Detection
• Domain Adaptive Object Detection for Space Applications with Real-Time Constraints
• Democratizing Production-Scale Distributed Deep Learning
• FPGA-based Accelerators of Deep Learning Networks for Learning and Classification: A Review
• An Analysis of Kalman Filter based Object Tracking Methods for Fast-Moving Tiny Objects
• Automated Facility Enumeration for Building Compliance Checking using Door Detection and Large Language Models
• SFN-YOLO: Towards Free-Range Poultry Detection via Scale-aware Fusion Networks
• Deep Clustering for Unsupervised Learning of Visual Features
• LLM-Assisted Semantic Guidance for Sparsely Annotated Remote Sensing Object Detection
• Prototypical Contrastive Learning of Unsupervised Representations
• Enhanced Detection of Tiny Objects in Aerial Images
• From Data to Diagnosis: A Large, Comprehensive Bone Marrow Dataset and AI Methods for Childhood Leukemia Prediction
• UNIV: Unified Foundation Model for Infrared and Visible Modalities
• Towards Size-invariant Salient Object Detection: A Generic Evaluation and Optimization Approach
• Robust Object Detection for Autonomous Driving via Curriculum-Guided Group Relative Policy Optimization
• Saccadic Vision for Fine-Grained Visual Classification
• Region-Aware Deformable Convolutions
• Maize Seedling Detection Dataset (MSDD): A Curated High-Resolution RGB Dataset for Seedling Maize Detection and Benchmarking with YOLOv9, YOLO11, YOLOv12 and Faster-RCNN
• Rethinking "Batch" in BatchNorm
• PRISM: Product Retrieval In Shopping Carts using Hybrid Matching
• Crafting GBD-Net for Object Detection
• Emotion-Aware Speech Generation with Character-Specific Voices for Comics
• Improving Weakly Supervised Visual Grounding by Contrastive Knowledge Distillation
• Exploring Self-attention for Image Recognition
• Cross-view Relation Networks for Mammogram Mass Detection
• Multi-Sensor 3D Object Box Refinement for Autonomous Driving
• NoduleNet: Decoupled False Positive Reductionfor Pulmonary Nodule Detection and Segmentation
• Sequential Voting with Relational Box Fields for Active Object Detection
• Unsupervised Object-Level Representation Learning from Scene Images
• Towards Overcoming False Positives in Visual Relationship Detection
• A Framework for Generating Artificial Datasets to Validate Absolute and Relative Position Concepts
• AntiDote: Attention-based Dynamic Optimization for Neural Network Runtime Efficiency
• Modification method for single-stage object detectors that allows to exploit the temporal behaviour of a scene to improve detection accuracy
• An Exploratory Study on Abstract Images and Visual Representations Learned from Them
• Data Leakage in Visual Datasets
• CETUS: Causal Event-Driven Temporal Modeling With Unified Variable-Rate Scheduling
• Improving Generalized Visual Grounding with Instance-aware Joint Learning
• Multimodal Transformer with Multi-View Visual Representation for Image Captioning
• Structure Aware SLAM using Quadrics and Planes
• MINGLE: VLMs for Semantically Complex Region Detection in Urban Scenes
• Simultaneously Localize, Segment and Rank the Camouflaged Objects
• A Novel Compression Framework for YOLOv8: Achieving Real-Time Aerial Object Detection on Edge Devices via Structured Pruning and Channel-Wise Distillation
• Maps for Autonomous Driving: Full-process Survey and Frontiers
• Cumulative Consensus Score: Label-Free and Model-Agnostic Evaluation of Object Detectors in Deployment
• BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation
• Learning in an Uncertain World: Representing Ambiguity Through Multiple Hypotheses
• TANet: Robust 3D Object Detection from Point Clouds with Triple Attention
• Robust Object Detection under Occlusion with Context-Aware CompositionalNets
• PPDM: Parallel Point Detection and Matching for Real-time Human-Object Interaction Detection
• Toward Filament Segmentation Using Deep Neural Networks
• Re-labeling ImageNet: from Single to Multi-Labels, from Global to Localized Labels
• Learning Deep Image Priors for Blind Image Denoising
• Learning Deep ResNet Blocks Sequentially using Boosting Theory
• Text-Based Person Search with Limited Data
• SceneGen: Generative Contextual Scene Augmentation using Scene Graph Priors
• GLiT: Neural Architecture Search for Global and Local Image Transformer
• Addressing Failure Prediction by Learning Model Confidence
• Bootstrap your own latent: A new approach to self-supervised Learning
• Autonomous Driving with Deep Learning: A Survey of State-of-Art Technologies
• MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers
• Few-Shot Object Detection via Knowledge Transfer
• Sitatapatra: Blocking the Transfer of Adversarial Samples
• Deep Multi-camera People Detection
• FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection
• VSR: A Unified Framework for Document Layout Analysis combining Vision, Semantics and Relations
• A Multiplexed Network for End-to-End, Multilingual OCR
• A Fully Open and Generalizable Foundation Model for Ultrasound Clinical Applications
• Customizing Student Networks From Heterogeneous Teachers via Adaptive Knowledge Amalgamation
• Unpaired Image-to-Speech Synthesis with Multimodal Information Bottleneck
• Optical deep learning nano-profilometry
• Hierarchical LSTMs with Adaptive Attention for Visual Captioning
• Motion Estimation for Multi-Object Tracking using KalmanNet with Semantic-Independent Encoding
• InterBERT: Vision-and-Language Interaction for Multi-modal Pretraining
• Beyond Instance Consistency: Investigating View Diversity in Self-supervised Learning
• 3D Feature Pyramid Attention Module for Robust Visual Speech Recognition
• Policy-Driven Transfer Learning in Resource-Limited Animal Monitoring
• Review: deep learning on 3D point clouds
• Group Evidence Matters: Tiling-based Semantic Gating for Dense Object Detection
• Pose-adaptive Hierarchical Attention Network for Facial Expression Recognition
• Implicit Label Augmentation on Partially Annotated Clips via Temporally-Adaptive Features Learning
• Deep Learning for Generic Object Detection: A Survey
• Rethinking Channel Dimensions for Efficient Model Design
• Keep it Simple: Image Statistics Matching for Domain Adaptation
• Online 3D Multi-Camera Perception through Robust 2D Tracking and Depth-based Late Aggregation
• Effect of Visual Extensions on Natural Language Understanding in Vision-and-Language Models
• Towards Understanding Visual Grounding in Visual Language Models
• Relation-Aware Graph Attention Network for Visual Question Answering
• Locate, Size and Count: Accurately Resolving People in Dense Crowds via Detection
• Dense RepPoints: Representing Visual Objects with Dense Point Sets
• A Co-Training Semi-Supervised Framework Using Faster R-CNN and YOLO Networks for Object Detection in Densely Packed Retail Images
• Model-Agnostic Open-Set Air-to-Air Visual Object Detection for Reliable UAV Perception
• Person Re-identification: Past, Present and Future
• Graph Density-Aware Losses for Novel Compositions in Scene Graph Generation
• RT-DETR++ for UAV Object Detection
• Uncertainty-Aware Unsupervised Domain Adaptation in Object Detection
• Research on Fast Text Recognition Method for Financial Ticket Image
• WAVE-DETR Multi-Modal Visible and Acoustic Real-Life Drone Detector
• GeneVA: A Dataset of Human Annotations for Generative Text to Video Artifacts
• Renovating Parsing R-CNN for Accurate Multiple Human Parsing
• Separating Skills and Concepts for Novel Visual Question Answering
• Deep Learning for LiDAR Point Clouds in Autonomous Driving: A Review
• Symmetry and Group in Attribute-Object Compositions
• CCL: Cross-modal Correlation Learning with Multi-grained Fusion by Hierarchical Network
• CEM-FBGTinyDet: Context-Enhanced Foreground Balance with Gradient Tuning for tiny Objects
• Single-Shot Multi-Person 3D Pose Estimation From Monocular RGB
• A2J: Anchor-to-Joint Regression Network for 3D Articulated Pose Estimation from a Single Depth Image
• Actor-Centric Relation Network
• Exploring Simple Siamese Representation Learning
• HRank: Filter Pruning using High-Rank Feature Map
• Boosted Training of Lightweight Early Exits for Optimizing CNN Image Classification Inference
• Dual-Thresholding Heatmaps to Cluster Proposals for Weakly Supervised Object Detection
• CrowdQuery: Density-Guided Query Module for Enhanced 2D and 3D Detection in Crowded Scenes
• Impression Space from Deep Template Network
• Improving Multispectral Pedestrian Detection by Addressing Modality Imbalance Problems
• PBRnet: Pyramidal Bounding Box Refinement to Improve Object Localization Accuracy
• Two-Stage Swarm Intelligence Ensemble Deep Transfer Learning (SI-EDTL) for Vehicle Detection Using Unmanned Aerial Vehicles
• Feature Pyramid Transformer
• Rethinking the Artificial Neural Networks: A Mesh of Subnets with a Central Mechanism for Storing and Predicting the Data
• Deep Image Retrieval: Learning global representations for image search
• DeepSEED: 3D Squeeze-and-Excitation Encoder-Decoder Convolutional Neural Networks for Pulmonary Nodule Detection
• Towards Generalization and Data Efficient Learning of Deep Robotic Grasping
• ResizeMix: Mixing Data with Preserved Object Information and True Labels
• Towards Robust LiDAR-based Perception in Autonomous Driving: General Black-box Adversarial Sensor Attack and Countermeasures
• FCOS: Fully Convolutional One-Stage Object Detection
• End-to-end Deep Learning Methods for Automated Damage Detection in Extreme Events at Various Scales
• Comprehensive Image Captioning via Scene Graph Decomposition
• Detection of trade in products derived from threatened species using machine learning and a smartphone
• Tiny-DSOD: Lightweight Object Detection for Resource-Restricted Usages
• An Analysis of Scale Invariance in Object Detection - SNIP
• Multi-Modal Camera-Based Detection of Vulnerable Road Users
• When Language Model Guides Vision: Grounding DINO for Cattle Muzzle Detection
• Comparison Network for One-Shot Conditional Object Detection
• Two-Stage Framework for Efficient UAV-Based Wildfire Video Analysis with Adaptive Compression and Fire Source Detection
• Pothole Detection and Recognition based on Transfer Learning
• A Recurrent Vision-and-Language BERT for Navigation
• Image Enhanced Rotation Prediction for Self-Supervised Learning
• Semantic Segmentation for Compound figures
• A New Hybrid Model of Generative Adversarial Network and You Only Look Once Algorithm for Automatic License-Plate Recognition
• TinyDef-DETR: A Transformer-Based Framework for Defect Detection in Transmission Lines from UAV Imagery
• Iterative Shrinking for Referring Expression Grounding Using Deep Reinforcement Learning
• Detection of E-scooter Riders in Naturalistic Scenes
• PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things
• Closer to Reality: Practical Semi-Supervised Federated Learning for Foundation Model Adaptation
• Edited Media Understanding Frames: Reasoning About the Intent and Implications of Visual Misinformation
• Language-guided Recursive Spatiotemporal Graph Modeling for Video Summarization
• ShapeCaptioner: Generative Caption Network for 3D Shapes by Learning a Mapping from Parts Detected in Multiple Views to Sentences
• High Utilization Energy-Aware Real-Time Inference Deep Convolutional Neural Network Accelerator
• FCOS: A simple and strong anchor-free object detector
• Comp-X: On Defining an Interactive Learned Image Compression Paradigm With Expert-driven LLM Agent
• PropVG: End-to-End Proposal-Driven Visual Grounding with Multi-Granularity Discrimination
• Learning Spatio-Temporal Representation with Local and Global Diffusion
• Quaternion Approximation Networks for Enhanced Image Classification and Oriented Object Detection
• Bayesian Loss for Crowd Count Estimation with Point Supervision
• Towards Open World Detection: A Survey
• CPT: Colorful Prompt Tuning for Pre-trained Vision-Language Models
• Differential Morphological Profile Neural Networks for Semantic Segmentation
• YOLO Ensemble for UAV-based Multispectral Defect Detection in Wind Turbine Components
• TriLiteNet: Lightweight Model for Multi-Task Visual Perception
• Integrating Objects into Monocular SLAM: Line Based Category Specific Models
• Quantifying and Alleviating the Language Prior Problem in Visual Question Answering
• Object Detection in Specific Traffic Scenes using YOLOv2
• SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation
• Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression
• Revisiting the Loss Weight Adjustment in Object Detection
• Dari Barisan ke Pakatan: berubahnya dinamiks Pilihan Raya UmumKuala Lumpur 1955-2013
• Defective Convolutional Networks
• DisPatch: Disarming Adversarial Patches in Object Detection with Diffusion Models
• Semantic Segmentation from Limited Training Data
• Center-based 3D Object Detection and Tracking
• YOLOv4: Optimal Speed and Accuracy of Object Detection
• SAMFusion: Sensor-Adaptive Multimodal Fusion for 3D Object Detection in Adverse Weather
• Human De-occlusion: Invisible Perception and Recovery for Humans
• SOPSeg: Prompt-based Small Object Instance Segmentation in Remote Sensing Imagery
• Heatmap Guided Query Transformers for Robust Astrocyte Detection across Immunostains and Resolutions
• The EPIC-KITCHENS Dataset: Collection, Challenges and Baselines
• Vision-based deep execution monitoring
• P² Net: Augmented Parallel-Pyramid Net for Attention Guided Pose Estimation
• Targeted Physical Evasion Attacks in the Near-Infrared Domain
• Look, Read and Feel: Benchmarking Ads Understanding with Multimodal Multitask Learning
• Efficient Pipelines for Vision-Based Context Sensing
• Structure-aware Contrastive Learning for Diagram Understanding of Multimodal Models
• Multimodal Contrastive Training for Visual Representation Learning
• Lightweight Pyramid Networks for Image Deraining
• Automated data extraction of bar chart raster images
• Global Context Aware RCNN for Object Detection
• Delving into Robust Object Detection from Unmanned Aerial Vehicles: A Deep Nuisance Disentanglement Approach
• Synesthesia of Machines (SoM)-Based Task-Driven MIMO System for Image Transmission
• When Healthcare Meets Off-the-Shelf WiFi: A Non-Wearable and Low-Costs Approach for In-Home Monitoring
• The Role of Context Selection in Object Detection
• Practical Detection of Trojan Neural Networks: Data-Limited and Data-Free Cases
• Improving Long-Tailed Object Detection with Balanced Group Softmax and Metric Learning
• FEDEXCHANGE: Bridging the Domain Gap in Federated Object Detection for Free
• Hierarchical Vision-Language Reasoning for Multimodal Multiple-Choice Question Answering
• High-Precision Mixed Feature Fusion Network Using Hypergraph Computation for Cervical Abnormal Cell Detection
• Uirapuru: Timely Video Analytics for High-Resolution Steerable Cameras on Edge Devices
• Image Quality Enhancement and Detection of Small and Dense Objects in Industrial Recycling Processes
• SAR-NAS: Lightweight SAR Object Detection with Neural Architecture Search
• MVTrajecter: Multi-View Pedestrian Tracking with Trajectory Motion Cost and Trajectory Appearance Cost
• FICGen: Frequency-Inspired Contextual Disentanglement for Layout-driven Degraded Image Generation
• Unifying Training and Inference for Panoptic Segmentation
• Class-Incremental Few-Shot Object Detection
• GridTracer: Automatic Mapping of Power Grids using Deep Learning and Overhead Imagery
• Towards Deep Learning Assisted Autonomous UAVs for Manipulation Tasks in GPS-Denied Environments
• Trait specialization facilitates autonomous selfing ability in a mixed‐mating plant
• Perceptual Generative Adversarial Networks for Small Object Detection
• Learning from Multiple Datasets with Heterogeneous and Partial Labels for Universal Lesion Detection in CT
• RfD-Net: Point Scene Understanding by Semantic Instance Reconstruction
• COVID-19 personal protective equipment detection using real-time deep learning methods
• RT-VLM: Re-Thinking Vision Language Model with 4-Clues for Real-World Object Recognition Robustness
• Detailed 2D-3D Joint Representation for Human-Object Interaction
• C-DiffDet+: Fusing Global Scene Context with Generative Denoising for High-Fidelity Car Damage Detection
• SurgLLM: A Versatile Large Multimodal Model with Spatial Focus and Temporal Awareness for Surgical Video Understanding
• Target-Oriented Single Domain Generalization
• CO2: Consistent Contrast for Unsupervised Visual Representation Learning
• Waste-Bench: A Comprehensive Benchmark for Evaluating VLLMs in Cluttered Environments
• FLORA: Efficient Synthetic Data Generation for Object Detection in Low-Data Regimes via finetuning Flux LoRA
• Solutions for Mitotic Figure Detection and Atypical Classification in MIDOG 2025
• Understanding the Behaviour of Contrastive Loss
• Learning with Rethinking: Recurrently Improving Convolutional Neural Networks through Feedback
• Probabilistic two-stage detection
• Identifying Surgical Instruments in Laparoscopy Using Deep Learning Instance Segmentation
• Panoptic Segmentation of Environmental UAV Images : Litter Beach
• Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning
• QuadricSLAM: Dual Quadrics from Object Detections as Landmarks in\n Object-oriented SLAM
• CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark
• An Empirical Study of DNNs Robustification Inefficacy in Protecting Visual Recommenders
• KeepAugment: A Simple Information-Preserving Data Augmentation Approach
• Accurate RGB-D Salient Object Detection via Collaborative Learning
• Improving Deep Lesion Detection Using 3D Contextual and Spatial Attention
• IG-TRACK: IOU Guided Siamese Networks for visual object tracking
• Semantic-Aware Ship Detection with Vision-Language Integration
• Off-Policy Self-Critical Training for Transformer in Visual Paragraph Generation
• YOLOX: Exceeding YOLO Series in 2021
• ViP-DeepLab: Learning Visual Perception with Depth-aware Video Panoptic Segmentation
• Simple Online and Realtime Tracking with a Deep Association Metric
• Learning a Disentangled Embedding for Monocular 3D Shape Retrieval and Pose Estimation
• Temporal Action Localization using Long Short-Term Dependency
• To New Beginnings: A Survey of Unified Perception in Autonomous Vehicle Software
• Adapting Foundation Model for Dental Caries Detection with Dual-View Co-Training
• Contrastive Learning through Auxiliary Branch for Video Object Detection
• CaddieSet: A Golf Swing Dataset with Human Joint Features and Ball Information
• Finding the Evidence: Localization-aware Answer Prediction for Text Visual Question Answering
• 3D Context Enhanced Region-based Convolutional Neural Network for End-to-End Lesion Detection
• End-to-end trainable network for degraded license plate detection via vehicle-plate relation mining
• Iterative Low-Rank Approximation for CNN Compression
• What makes instance discrimination good for transfer learning?
• Exploring Randomly Wired Neural Networks for Image Recognition
• HiddenObject: Modality-Agnostic Fusion for Multimodal Hidden Object Detection
• The Role of Teacher Calibration in Knowledge Distillation
• Spatiotemporal Contrastive Video Representation Learning
• Accurate Anchor Free Tracking
• Improving Calibration for Long-Tailed Recognition
• Kernel Transformer Networks for Compact Spherical Convolution
• Objects in Semantic Topology
• Image Quality Assessment for Machines: Paradigm, Large-scale Database, and Models
• RATopo: Improving Lane Topology Reasoning via Redundancy Assignment
• Decoupling the Role of Data, Attention, and Losses in Multimodal Transformers
• Scalable Object Detection in the Car Interior With Vision Foundation Models
• SODA10M: A Large-Scale 2D Self/Semi-Supervised Object Detection Dataset for Autonomous Driving
• FlowDet: Overcoming Perspective and Scale Challenges in Real-Time End-to-End Traffic Detection
• Exploring Categorical Regularization for Domain Adaptive Object Detection
• ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network
• ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spotting
• Learning to Generate Synthetic Data via Compositing
• Co-Separating Sounds of Visual Objects
• LDC-Net: A Unified Framework for Localization, Detection and Counting in Dense Crowds
• Robust and Label-Efficient Deep Waste Detection
• Are All Marine Species Created Equal? Performance Disparities in Underwater Object Detection
• Clustering-based Feature Representation Learning for Oracle Bone Inscriptions Detection
• Object Detection for Comics using Manga109 Annotations
• Why Do We Click: Visual Impression-aware News Recommendation
• Adaptive Visual Navigation Assistant in 3D RPGs
• Object Detection with Multimodal Large Vision-Language Models: An In-depth Review
• A Deep Journey into Super-resolution: A survey
• Deep Learning Inference in Facebook Data Centers: Characterization, Performance Optimizations and Hardware Implications
• AQ-PCDSys: An Adaptive Quantized Planetary Crater Detection System for Autonomous Space Exploration
• Elucidating image-to-set prediction: An analysis of models, losses and datasets
• Revisiting the Sibling Head in Object Detector
• Multi-perspective monitoring of wildlife and human activities from camera traps and drones with deep learning models
• Learning Object Relation Graph and Tentative Policy for Visual Navigation
• SM-NAS: Structural-to-Modular Neural Architecture Search for Object Detection
• Learning to Fuse Things and Stuff
• YOLObile: Real-Time Object Detection on Mobile Devices via Compression-Compilation Co-Design
• Decentralized Vision-Based Autonomous Aerial Wildlife Monitoring
• Understanding top-down attention using task-oriented ablation design
• CLOCs: Camera-LiDAR Object Candidates Fusion for 3D Object Detection
• Incremental Object Detection with Prompt-based Methods
• Toward unsupervised, multi-object discovery in large-scale image collections
• Towards Precise End-to-end Weakly Supervised Object Detection Network
• CAD-PU: A Curvature-Adaptive Deep Learning Solution for Point Set Upsampling
• Normalized Cut Loss for Weakly-supervised CNN Segmentation
• AffordanceNet: An End-to-End Deep Learning Approach for Object Affordance Detection
• A Survey on Video Anomaly Detection via Deep Learning: Human, Vehicle, and Environment
• Revisiting Knowledge Distillation for Object Detection
• CCA: Exploring the Possibility of Contextual Camouflage Attack on Object Detection
• OmViD: Omni-supervised active learning for video action detection
• Large Scale Visual Food Recognition
• Self-Aware Adaptive Alignment: Enabling Accurate Perception for Intelligent Transportation Systems
• Bidirectional Regression for Arbitrary-Shaped Text Detection
• FaPN: Feature-aligned Pyramid Network for Dense Image Prediction
• MF-LPR²: Multi-Frame License Plate Image Restoration and Recognition using Optical Flow
• ICNet for Real-Time Semantic Segmentation on High-Resolution Images
• Gaussian Temporal Awareness Networks for Action Localization
• RICO: Two Realistic Benchmarks and an In-Depth Analysis for Incremental Learning in Object Detection
• Domain Adaptation and Image Classification via Deep Conditional Adaptation Network
• Hybrid Attention for Automatic Segmentation of Whole Fetal Head in Prenatal Ultrasound Volumes
• Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networks
• G2L-Net: Global to Local Network for Real-time 6D Pose Estimation with Embedding Vector Features
• supervised adptive threshold network for instance segmentation
• vireoJD-MM at Activity Detection in Extended Videos
• Bounding Box Regression with Uncertainty for Accurate Object Detection
• Multi-Person Pose Estimation with Local Joint-to-Person Associations
• Design and Validation of a Responsible Artificial Intelligence-based System for the Referral of Diabetic Retinopathy Patients
• A system of vision sensor based deep neural networks for complex driving scene analysis in support of crash risk assessment and prevention
• Long Short-Term Relation Networks for Video Action Detection
• Deep Contextual Attention for Human-Object Interaction Detection
• Learning Transferable 3D Adversarial Cloaks for Deep Trained Detectors
• A Gap-Based Framework for Chinese Word Segmentation via Very Deep Convolutional Networks
• Data Shift of Object Detection in Autonomous Driving
• Loss re-scaling VQA: Revisiting the LanguagePrior Problem from a Class-imbalance View
• Automated Model Evaluation for Object Detection via Prediction Consistency and Reliability
• PEdger++: Practical Edge Detection via Assembling Cross Information
• TACR-YOLO: A Real-time Detection Framework for Abnormal Human Behaviors Enhanced with Coordinate and Task-Aware Representations
• MOS: A Low Latency and Lightweight Framework for Face Detection, Landmark Localization, and Head Pose Estimation
• Spatial-Temporal Relation Networks for Multi-Object Tracking
• A Real-time Concrete Crack Detection and Segmentation Model Based on YOLOv11
• Learning Layout and Style Reconfigurable GANs for Controllable Image Synthesis
• HOID-R1: Reinforcement Learning for Open-World Human-Object Interaction Detection Reasoning with Multimodal Large Language Model
• Index-Aligned Query Distillation for Transformer-based Incremental Object Detection
• Generalized Decoupled Learning for Enhancing Open-Vocabulary Dense Perception
• Two-Level Residual Distillation based Triple Network for Incremental Object Detection
• Adma: A Flexible Loss Function for Neural Networks
• Generic Tubelet Proposals for Action Localization
• A Coarse-to-Fine Human Pose Estimation Method based on Two-stage Distillation and Progressive Graph Neural Network
• VFM-Guided Semi-Supervised Detection Transformer under Source-Free Constraints for Remote Sensing Object Detection
• Are Large Pre-trained Vision Language Models Effective Construction Safety Inspectors?
• Graph-Based Social Relation Reasoning
• Axis-level Symmetry Detection with Group-Equivariant Representation
• EventNet: Asynchronous Recursive Event Processing
• LGA-RCNN: Loss-Guided Attention for Object Detection
• A Segmentation-driven Editing Method for Bolt Defect Augmentation and Detection
• CSNR and JMIM Based Spectral Band Selection for Reducing Metamerism in Urban Driving
• Processing and acquisition traces in visual encoders: What does CLIP know about your camera?
• Towards Powerful and Practical Patch Attacks for 2D Object Detection in Autonomous Driving
• SkeySpot: Automating Service Key Detection for Digital Electrical Layout Plans in the Construction Industry
• CTAP: Complementary Temporal Action Proposal Generation
• Improving OCR for Historical Texts of Multiple Languages
• Glo-UMF: A Unified Multi-model Framework for Automated Morphometry of Glomerular Ultrastructural Characterization
• From Surface to Semantics: Semantic Structure Parsing for Table-Centric Document Analysis
• Image Captioning with Visual Object Representations Grounded in the Textual Modality
• BERT-VQA: Visual Question Answering on Plots
• A Structured Model For Action Detection
• Deep Learning Acceleration Techniques for Real Time Mobile Vision Applications
• iFAN: Image-Instance Full Alignment Networks for Adaptive Object Detection
• Shift Equivariance in Object Detection
• Progressive Sparse Local Attention for Video object detection
• SynSpill: Improved Industrial Spill Detection With Synthetic Data
• Sparse Coding Driven Deep Decision Tree Ensembles for Nuclear Segmentation in Digital Pathology Images
• TOTNet: Occlusion-Aware Temporal Tracking for Robust Ball Detection in Sports Videos
• MixSearch: Searching for Domain Generalized Medical Image Segmentation Architectures
• SemVLP: Vision-Language Pre-training by Aligning Semantics at Multiple Levels
• How benign is benign overfitting?
• ConFoc: Content-Focus Protection Against Trojan Attacks on Neural Networks
• What-Meets-Where: Unified Learning of Action and Contact Localization in a New Dataset
• Joint-DetNAS: Upgrade Your Detector with NAS, Pruning and Dynamic Distillation
• EXSCLAIM! -- An automated pipeline for the construction of labeled materials imaging datasets from literature
• DenoDet V2: Phase-Amplitude Cross Denoising for SAR Object Detection
• Person Identification with Visual Summary for a Safe Access to a Smart Home
• CFTrack: Center-based Radar and Camera Fusion for 3D Multi-Object Tracking
• Dual-stream Network for Visual Recognition
• Geometry-Aware Global Feature Aggregation for Real-Time Indirect Illumination
• Beyond the Camera: Neural Networks in World Coordinates
• Hierarchical Visual Prompt Learning for Continual Video Instance Segmentation
• QueryCraft: Transformer-Guided Query Initialization for Enhanced Human-Object Interaction Detection
• Video-based Person Re-identification without Bells and Whistles
• Unsupervised Domain Alignment to Mitigate Low Level Dataset Biases
• SIXray : A Large-scale Security Inspection X-ray Benchmark for Prohibited Item Discovery in Overlapping Images
• One-Shot Instance Segmentation
• Designing Object Detection Models for TinyML: Foundations, Comparative Analysis, Challenges, and Emerging Solutions
• Instance-Level Task Parameters: A Robust Multi-task Weighting Framework
• Speaker Diarization with Region Proposal Network
• ZSTAD: Zero-Shot Temporal Activity Detection
• Discovering Visual Patterns in Art Collections with Spatially-consistent Feature Learning
• Self-Supervised Representation Learning for Visual Anomaly Detection
• MambaTrans: Multimodal Fusion Image Translation via Large Language Model Priors for Downstream Visual Tasks
• DoorDet: Semi-Automated Multi-Class Door Detection Dataset via Object Detection and Large Language Models
• Object-Aware Multi-Branch Relation Networks for Spatio-Temporal Video Grounding
• AURA: A Fine-Grained Benchmark and Decomposed Metric for Audio-Visual Reasoning
• Visual Dialogue State Tracking for Question Generation
• Deformable Kernels: Adapting Effective Receptive Fields for Object Deformation
• LungSurg: A Generative AI System for Segmentation and Phase Classification in Thoracoscopic Lobectomy
• LU-Net: a multi-task network to improve the robustness of segmentation of left ventriclular structures by deep learning in 2D echocardiography
• WQT and DG-YOLO: towards domain generalization in underwater object detection
• Training few-shot classification via the perspective of minibatch and pretraining
• Data Priming Network for Automatic Check-Out
• CornerNet: Detecting Objects as Paired Keypoints
• Introducing Pose Consistency and Warp-Alignment for Self-Supervised 6D Object Pose Estimation in Color Images
• Neural Mesh Refiner for 6-DoF Pose Estimation
• WDR FACE: The First Database for Studying Face Detection in Wide Dynamic Range
• Understanding Egocentric Hand-Object Interactions from Hand Pose Estimation
• Synthetic Data-Driven Multi-Architecture Framework for Automated Polyp Segmentation Through Integrated Detection and Mask Generation
• CountQA: How Well Do MLLMs Count in the Wild?
• Integrating Vision Foundation Models with Reinforcement Learning for Enhanced Object Interaction
• Head Anchor Enhanced Detection and Association for Crowded Pedestrian Tracking
• Physical Adversarial Camouflage through Gradient Calibration and Regularization
• mKG-RAG: Multimodal Knowledge Graph-Enhanced RAG for Visual Question Answering
• Segmenting the Complex and Irregular in Two-Phase Flows: A Real-World Empirical Study with SAM2
• Contextual Object Detection with Multimodal Large Language Models
• Parts4Feature: Learning 3D Global Features from Generally Semantic Parts in Multiple Views
• Self-Error Adjustment: Theory and Practice of Balancing Individual Performance and Diversity in Ensemble Learning
• Disentangled Deep Autoencoding Regularization for Robust Image Classification
• Benchmarking pig detection and tracking under diverse and challenging conditions
• TopKD: Top-scaled Knowledge Distillation
• A Smartphone-based System for Real-time Early Childhood Caries Diagnosis
• What Holds Back Open-Vocabulary Segmentation?
• UniFGVC: Universal Training-Free Few-Shot Fine-Grained Vision Classification via Attribute-Aware Multimodal Retrieval
• Learning Using Privileged Information for Litter Detection
• CLIPVehicle: A Unified Framework for Vision-based Vehicle Search
• Scaling-Translation-Equivariant Networks with Decomposed Convolutional Filters
• Retrieve, Read, Rerank: Towards End-to-End Multi-Document Reading Comprehension
• Deep learning framework for crater detection and identification on the Moon and Mars
• Training Deep Neural Networks via Branch-and-Bound
• GPNAS: A Neural Network Architecture Search Framework Based on Graphical Predictor
• DyCAF-Net: Dynamic Class-Aware Fusion Network
• Relationship-Embedded Representation Learning for Grounding Referring Expressions
• AVPDN: Learning Motion-Robust and Scale-Adaptive Representations for Video-Based Polyp Detection
• Where are the Masks: Instance Segmentation with Image-level Supervision
• The Research of the Real-time Detection and Recognition of Targets in Streetscape Videos
• Temporally Identity-Aware SSD with Attentional LSTM
• Open-Vocabulary HOI Detection with Interaction-aware Prompt and Concept Calibration
• Where and How to Enhance: Discovering Bit-Width Contribution for Mixed Precision Quantization
• TrackNet: A Deep Learning Network for Tracking High-speed and Tiny Objects in Sports Applications
• Adversarial Attention Perturbations for Large Object Detection Transformers
• Online Active Proposal Set Generation for Weakly Supervised Object Detection
• Architectural Insights into Knowledge Distillation for Object Detection: A Comprehensive Review
• Feature Selective Small Object Detection via Knowledge-based Recurrent Attentive Neural Network
• CoFF: Cooperative Spatial Feature Fusion for 3D Object Detection on Autonomous Vehicles
• Few-shot Object Detection with Self-adaptive Attention Network for Remote Sensing Images
• Evaluation and Analysis of Deep Neural Transformers and Convolutional Neural Networks on Modern Remote Sensing Datasets
• BiFNet: Bidirectional Fusion Network for Road Segmentation
• Towards Compact and Robust Deep Neural Networks
• Unified Category-Level Object Detection and Pose Estimation from RGB Images using 3D Prototypes
• Self-Supervised YOLO: Leveraging Contrastive Learning for Label-Efficient Object Detection
• Fast Neural Network Adaptation via Parameter Remapping and Architecture Search
• YOLOv1 to YOLOv11: A Comprehensive Survey of Real-Time Object Detection Innovations and Challenges
• Robust Real-time Pedestrian Detection in Aerial Imagery on Jetson TX2
• Benchmarking Deep Learning-Based Object Detection Models on Feature Deficient Astrophotography Imagery Dataset
• Regula Sub-rosa: Latent Backdoor Attacks on Deep Neural Networks
• InspectVLM: Unified in Theory, Unreliable in Practice
• IAUNet: Instance-Aware U-Net
• TAN: Temporal Affine Network for Real-Time Left Ventricle Anatomical Structure Analysis Based on 2D Ultrasound Videos
• Stack-VS: Stacked Visual-Semantic Attention for Image Caption Generation
• Spatial-Frequency Aware for Object Detection in RAW Image
• A Full-Stage Refined Proposal Algorithm for Suppressing False Positives in Two-Stage CNN-Based Detection Methods
• Geometry-Aware Video Object Detection for Static Cameras
• Multi-Scale Time-Frequency Attention for Acoustic Event Detection
• Screencast-Based Analysis of User-Perceived GUI Responsiveness
• SBP-YOLO:A Lightweight Real-Time Model for Detecting Speed Bumps and Potholes toward Intelligent Vehicle Suspension Systems
• Tobler's First Law in GeoAI: A Spatially Explicit Deep Learning Model for Terrain Feature Detection Under Weak Supervision
• AI-Driven Collaborative Satellite Object Detection for Space Sustainability
• Revisiting Adversarial Patch Defenses on Object Detectors: Unified Evaluation, Large-Scale Dataset, and New Insights
• Disrupting Semantic and Abstract Features for Better Adversarial Transferability
• Residual-CNDS for Grand Challenge Scene Dataset
• Weakly Supervised Virus Capsid Detection with Image-Level Annotations in Electron Microscopy Images
• CoST: Efficient Collaborative Perception From Unified Spatiotemporal Perspective
• Backdoor Attacks on Deep Learning Face Detection
• Relation Networks for Object Detection
• DICOM De-Identification via Hybrid AI and Rule-Based Framework for Scalable, Uncertainty-Aware Redaction
• Fruit Quantity and Quality Estimation using a Robotic Vision System
• Dynamic Temporal Pyramid Network: A Closer Look at Multi-Scale Modeling for Activity Detection
• Human Motion Capture Using a Drone
• AugFPN: Improving Multi-scale Feature Learning for Object Detection
• Saliency-Guided Attention Network for Image-Sentence Matching
• Local Dense Logit Relations for Enhanced Knowledge Distillation
• SemiNLL: A Framework of Noisy-Label Learning by Semi-Supervised Learning
• Tricks and Plug-ins for Gradient Boosting in Image Classification
• The Garden of Forking Paths: Towards Multi-Future Trajectory Prediction
• Scalable Change Retrieval Using Deep 3D Neural Codes
• Segment Anything for Video: A Comprehensive Review of Video Object Segmentation and Tracking from Past to Future
• DDD20 End-to-End Event Camera Driving Dataset: Fusing Frames and Events with Deep Learning for Improved Steering Prediction
• Exploiting Diffusion Prior for Task-driven Image Restoration
• Training a Binary Weight Object Detector by Knowledge Transfer for Autonomous Driving
• StarNet: Targeted Computation for Object Detection in Point Clouds
• FDNAS: Improving Data Privacy and Model Diversity in AutoML
• Object Recognition Datasets and Challenges: A Review
• A Survey on Deep Multi-Task Learning in Connected Autonomous Vehicles
• AI in Agriculture: A Survey of Deep Learning Techniques for Crops, Fisheries and Livestock
• Staining and locking computer vision models without retraining
• SARD: A YOLOv8-Based System for Solar Active Region Detection with SDO/HMI Magnetograms
• Transferring Domain-Agnostic Knowledge in Video Question Answering
• Control Copy-Paste: Controllable Diffusion-Based Augmentation Method for Remote Sensing Few-Shot Object Detection
• Entropy-Enhanced Multimodal Attention Model for Scene-Aware Dialogue Generation
• RRTO: A High-Performance Transparent Offloading System for Model Inference in Mobile Edge Computing
• Detection Transformers Under the Knife: A Neuroscience-Inspired Approach to Ablations
• Transferable Adversarial Examples for Anchor Free Object Detection
• Automated Detection of Antarctic Benthic Organisms in High-Resolution In Situ Imagery to Aid Biodiversity Monitoring
• Efficient Neural Architecture Transformation Searchin Channel-Level for Object Detection
• Tracking Moose using Aerial Object Detection
• Dual Guidance Semi-Supervised Action Detection
• On Explaining Visual Captioning with Hybrid Markov Logic Networks
• A Frank-Wolfe Framework for Efficient and Effective Adversarial Attacks
• Real-time Visual Object Tracking with Natural Language Description
• Context-Aware Single-Shot Detector
• Adapting Vehicle Detectors for Aerial Imagery to Unseen Domains with Weak Supervision
• Ensemble Foreground Management for Unsupervised Object Discovery
• Regularizing Subspace Redundancy of Low-Rank Adaptation
• Instance Segmentation with Point Supervision
• Object 6D Pose Estimation with Non-local Attention
• Self-Supervised Continuous Colormap Recovery from a 2D Scalar Field Visualization without a Legend
• Loss Function Discovery for Object Detection via Convergence-Simulation Driven Search
• Rethinking Re-Sampling in Imbalanced Semi-Supervised Learning
• An Improved YOLOv8 Approach for Small Target Detection of Rice Spikelet Flowering in Field Environments
• Sparse 3D Perception for Rose Harvesting Robots: A Two-Stage Approach Bridging Simulation and Real-World Applications
• TDAPNet: Prototype Network with Recurrent Top-Down Attention for Robust Object Classification under Partial Occlusion
• MiLeNAS: Efficient Neural Architecture Search via Mixed-Level Reformulation
• Few-Shot Object Detection via Spatial-Channel State Space Model
• One-Shot Domain Adaptation For Face Generation
• AnimalClue: Recognizing Animals by their Traces
• Layerwise Optimization by Gradient Decomposition for Continual Learning
• Towards Universal Modal Tracking with Online Dense Temporal Token Learning
• Region-based Cluster Discrimination for Visual Representation Learning
• Seesaw Loss for Long-Tailed Instance Segmentation
• Spatial Language Likelihood Grounding Network for Bayesian Fusion of Human-Robot Observations
• Rethinking on Multi-Stage Networks for Human Pose Estimation
• Defect-GAN: High-Fidelity Defect Synthesis for Automated Defect Inspection
• Visual Tracking via Dynamic Memory Networks
• A Large Scale Urban Surveillance Video Dataset for Multiple-Object Tracking and Behavior Analysis
• Adaptive Label Smoothing
• Beef Cattle Instance Segmentation Using Fully Convolutional Neural Network
• RADDet: Range-Azimuth-Doppler based Radar Object Detection for Dynamic Road Users
• A²-FPN: Attention Aggregation based Feature Pyramid Network for Instance Segmentation
• Modeling Spatio-Temporal Human Track Structure for Action Localization
• Incremental Learning for Robot Perception through HRI
• MITOS-RCNN: A Novel Approach to Mitotic Figure Detection in Breast Cancer Histopathology Images using Region Based Convolutional Neural Networks
• RILOD: Near Real-Time Incremental Learning for Object Detection at the Edge
• Two-phase weakly supervised object detection with pseudo ground truth mining
• CentripetalText: An Efficient Text Instance Representation for Scene Text Detection
• Towards Holistic Surgical Scene Graph
• AlteregoNets: a way to human augmentation
• Progressive Stage-wise Learning for Unsupervised Feature Representation Enhancement
• 6-DoF Object Pose from Semantic Keypoints
• Interpretable Open-Vocabulary Referring Object Detection with Reverse Contrast Attention
• ATCTrack: Aligning Target-Context Cues with Dynamic Target States for Robust Vision-Language Tracking
• OW-CLIP: Data-Efficient Visual Supervision for Open-World Object Detection via Human-AI Collaboration
• X-Linear Attention Networks for Image Captioning
• DS-Det: Single-Query Paradigm and Attention Disentangled Learning for Flexible Object Detection
• JDATT: A Joint Distillation Framework for Atmospheric Turbulence Mitigation and Target Detection
• Large Language Model Agent for Structural Drawing Generation Using ReAct Prompt Engineering and Retrieval Augmented Generation
• GLSD: The Global Large-Scale Ship Database and Baseline Evaluations
• Exemplar Med-DETR: Toward Generalized and Robust Lesion Detection in Mammogram Images and beyond
• PhysVarMix: Physics-Informed Variational Mixture Model for Multi-Modal Trajectory Prediction
• Towards a Robust Deep Neural Network in Texts: A Survey
• ABCD: Automatic Blood Cell Detection via Attention-Guided Improved YOLOX
• Hit-Detector: Hierarchical Trinity Architecture Search for Object Detection
• Where Does It Exist: Spatio-Temporal Video Grounding for Multi-Form Sentences
• Enhancing Diabetic Retinopathy Classification Accuracy through Dual Attention Mechanism in Deep Learning
• Towards Cross-Modal Forgery Detection and Localization on Live Surveillance Videos
• Revisiting DETR for Small Object Detection via Noise-Resilient Query Optimization
• YOLO for Knowledge Extraction from Vehicle Images: A Baseline Study
• PerioDet: Large-Scale Panoramic Radiograph Benchmark for Clinical-Oriented Apical Periodontitis Detection
• WiSE-OD: Benchmarking Robustness in Infrared Object Detection
• Target Driven Instance Detection
• Plot and Rework: Modeling Storylines for Visual Storytelling
• Unsupervised Hard Example Mining from Videos for Improved Object Detection
• LMM-Det: Make Large Multimodal Models Excel in Object Detection
• VideoNavQA: Bridging the Gap between Visual and Embodied Question Answering
• Multi-adversarial Faster-RCNN for Unrestricted Object Detection
• A COCO-Formatted Instance-Level Dataset for Plasmodium Falciparum Detection in Giemsa-Stained Blood Smears
• TCM-Tongue: A Standardized Tongue Image Dataset with Pathological Annotations for AI-Assisted TCM Diagnosis
• Few-shot Learning with Global Relatedness Decoupled-Distillation
• Real Time Incremental Foveal Texture Mapping for Autonomous Vehicles
• Cross-modal Scene Graph Matching for Relationship-aware Image-Text Retrieval
• Weakly-Supervised Spatio-Temporal Anomaly Detection in Surveillance Video
• Towards Generalized and Incremental Few-Shot Object Detection
• Fast query-by-example speech search using separable model
• Learning Context-Aware Embedding for Person Search
• BleedOrigin: Dynamic Bleeding Source Localization in Endoscopic Submucosal Dissection via Dual-Stage Detection and Tracking
• Location-Aware Box Reasoning for Anchor-Based Single-Shot Object Detection
• Reverse-engineering Bar Charts Using Neural Networks
• Diffusion-FS: Multimodal Free-Space Prediction via Diffusion for Autonomous Driving
• Towards Large Scale Geostatistical Methane Monitoring with Part-based Object Detection
• Language-Conditioned Imitation Learning for Robot Manipulation Tasks
• Detecting Semantic Parts on Partially Occluded Objects
• 3D Object Proposals using Stereo Imagery for Accurate Object Class Detection
• Object-Centric Unsupervised Image Captioning
• DeNet: Scalable Real-time Object Detection with Directed Sparse Sampling
• Domain2Vec: Domain Embedding for Unsupervised Domain Adaptation
• Eliminating the Blind Spot: Adapting 3D Object Detection and Monocular Depth Estimation to 360° Panoramic Imagery
• An End-to-End Foreground-Aware Network for Person Re-Identification
• C2FNAS: Coarse-to-Fine Neural Architecture Search for 3D Medical Image Segmentation
• InsightX Agent: An LMM-based Agentic Framework with Integrated Tools for Reliable X-ray NDT Analysis
• Distilling Object Detectors with Feature Richness
• SOLO: Segmenting Objects by Locations
• Baidu-UTS Submission to the EPIC-Kitchens Action Recognition Challenge 2019
• Localization-aware Channel Pruning for Object Detection
• Focal and Global Knowledge Distillation for Detectors
• Multi-Scale 2D Temporal Adjacent Networks for Moment Localization with Natural Language
• PDPGD: Primal-Dual Proximal Gradient Descent Adversarial Attack
• ShuffleDet: Real-Time Vehicle Detection Network in On-board Embedded UAV Imagery
• Spatio-temporal Video Re-localization by Warp LSTM
• A Robotic Approach towards Quantifying Epipelagic Bound Plastic Using Deep Visual Models
• LeAdQA: LLM-Driven Context-Aware Temporal Grounding for Video Question Answering
• Developing a Compressed Object Detection Model based on YOLOv4 for Deployment on Embedded GPU Platform of Autonomous System
• Physics-based Scene-level Reasoning for Object Pose Estimation in Clutter
• RarePlanes: Synthetic Data Takes Flight
• Pathology-Aware Generative Adversarial Networks for Medical Image Augmentation
• Large Scale Font Independent Urdu Text Recognition System
• Low-light Image Enhancement Algorithm Based on Retinex and Generative Adversarial Network
• Selecting Relevant Features from a Multi-domain Representation for Few-shot Classification
• SwAMP: Swapped Assignment of Multi-Modal Pairs for Cross-Modal Retrieval
• Image De-raining Using a Conditional Generative Adversarial Network
• Weakly Supervised Complementary Parts Models for Fine-Grained Image Classification from the Bottom Up
• Detecting Small, Densely Distributed Objects with Filter-Amplifier Networks and Loss Boosting
• Lightweight Real-time Makeup Try-on in Mobile Browsers with Tiny CNN Models for Facial Tracking
• Context-Aware Zero-Shot Recognition
• Domain Adaptor Networks for Hyperspectral Image Recognition
• Merging Tasks for Video Panoptic Segmentation
• Improving Contrastive Learning by Visualizing Feature Transformation
• Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training
• Rethinking Drone-Based Search and Rescue with Aerial Person Detection
• Exploring Semantic Relationships for Unpaired Image Captioning
• TL-SDD: A Transfer Learning-Based Method for Surface Defect Detection with Few Samples
• Saliency deep embedding for aurora image search
• When We First Met: Visual-Inertial Person Localization for Co-Robot Rendezvous
• Alpha-Refine: Boosting Tracking Performance by Precise Bounding Box Estimation
• Machine Vision for Improved Human-Robot Cooperation in Adverse Underwater Conditions
• Decoupled PROB: Decoupled Query Initialization Tasks and Objectness-Class Learning for Open World Object Detection
• Channel-wise Motion Features for Efficient Motion Segmentation
• SECS: Efficient Deep Stream Processing via Class Skew Dichotomy
• Pneumothorax Segmentation: Deep Learning Image Segmentation to predict Pneumothorax
• f-Cal: Calibrated aleatoric uncertainty estimation from neural networks for robot perception
• Self-EMD: Self-Supervised Object Detection without ImageNet
• 3D Multi-Object Tracking: A Baseline and New Evaluation Metrics
• Weakly Aligned Cross-Modal Learning for Multispectral Pedestrian Detection
• Point in, Box out: Beyond Counting Persons in Crowds
• Labeled Data Generation with Inexact Supervision
• PAN++: Towards Efficient and Accurate End-to-End Spotting of Arbitrarily-Shaped Text
• Multilayer Collaborative Low-Rank Coding Network for Robust Deep Subspace Discovery
• ElixirNet: Relation-aware Network Architecture Adaptation for Medical Lesion Detection
• S2DNAS:Transforming Static CNN Model for Dynamic Inference via Neural Architecture Search
• Open-World Entity Segmentation
• Negative Margin Matters: Understanding Margin in Few-shot Classification
• Image Augmentations for GAN Training
• Multispectral State-Space Feature Fusion: Bridging Shared and Cross-Parametric Interactions for Object Detection
• Aligning Visual Regions and Textual Concepts for Semantic-Grounded Image Representations
• An End-to-End Framework for Unsupervised Pose Estimation of Occluded Pedestrians
• MosaicOS: A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detection
• Faceness-Net: Face Detection through Deep Facial Part Responses
• Context and Attribute Grounded Dense Captioning
• Issues in Object Detection in Videos using Common Single-Image CNNs
• Unpaired Pose Guided Human Image Generation
• Motion-Excited Sampler: Video Adversarial Attack with Sparked Prior
• BoundarySqueeze: Image Segmentation as Boundary Squeezing
• Open Domain Generalization with Domain-Augmented Meta-Learning
• PP-YOLOv2: A Practical Object Detector
• Spiking-YOLO: Spiking Neural Network for Energy-Efficient Object Detection
• Reformulating Level Sets as Deep Recurrent Neural Network Approach to Semantic Segmentation
• LIT: Light-field Inference of Transparency for Refractive Object Localization
• RDSNet: A New Deep Architecture for Reciprocal Object Detection and Instance Segmentation
• Grasping Detection Network with Uncertainty Estimation for Confidence-Driven Semi-Supervised Domain Adaptation
• Semi-convolutional Operators for Instance Segmentation
• CornerNet-Lite: Efficient Keypoint Based Object Detection
• Residual Attention based Network for Hand Bone Age Assessment
• PubLayNet: largest dataset ever for document layout analysis
• HiFT: Hierarchical Feature Transformer for Aerial Tracking
• T-EMDE: Sketching-based global similarity for cross-modal retrieval
• SkySense V2: A Unified Foundation Model for Multi-modal Remote Sensing
• Empirical Upper Bound in Object Detection and More
• Human Following for Wheeled Robot with Monocular Pan-tilt Camera
• Rethinking Natural Adversarial Examples for Classification Models
• Driver Action Prediction Using Deep (Bidirectional) Recurrent Neural Network
• Detecting, Localising and Classifying Polyps from Colonoscopy Videos using Deep Learning
• Natural Language Video Localization with Learnable Moment Proposals
• Visual Concepts and Compositional Voting
• Reusing Attention for One-stage Lane Topology Understanding
• Dynamic Scoring with Enhanced Semantics for Training-Free Human-Object Interaction Detection
• Dynamic-DINO: Fine-Grained Mixture of Experts Tuning for Real-time Open-Vocabulary Object Detection
• A Picture May Be Worth a Hundred Words for Visual Question Answering
• RoadBench: A Vision-Language Foundation Model and Benchmark for Road Damage Understanding
• Phase Space Reconstruction Network for Lane Intrusion Action Recognition
• Analysis of Plant Nutrient Deficiencies Using Multi-Spectral Imaging and Optimized Segmentation Model
• Joint 2D-3D Breast Cancer Classification
• CPARR: Category-based Proposal Analysis for Referring Relationships
• FishDet-M: A Unified Benchmark for Underwater Fish Detection with CLIP-Guided Model Selection
• Shape Robust Text Detection with Progressive Scale Expansion Network
• Epipolar-Guided Deep Object Matching for Scene Change Detection
• Few-Shot Learning in Video and 3D Object Detection: A Survey
• Can 3D Adversarial Logos Cloak Humans?
• X-volution: On the unification of convolution and self-attention
• Mask TextSpotter v3: Segmentation Proposal Network for Robust Scene Text Spotting
• TracKlinic: Diagnosis of Challenge Factors in Visual Tracking
• A Hypergradient Approach to Robust Regression without Correspondence
• Using UAV images and deep learning to enhance the mapping of deadwood in boreal forests
• FishNet: A Camera Localizer using Deep Recurrent Networks
• AngleRoCL: Angle-Robust Concept Learning for Physically View-Invariant T2I Adversarial Patches
• LAViTeR: Learning Aligned Visual and Textual Representations Assisted by Image and Caption Generation
• Temporal RoI Align for Video Object Recognition
• Interact as You Intend: Intention-Driven Human-Object Interaction Detection
• Semantic-guided Fine-tuning of Foundation Model for Long-tailed Visual Recognition
• Light-Weight RetinaNet for Object Detection
• EXTD: Extremely Tiny Face Detector via Iterative Filter Reuse
• RS-TinyNet: Stage-wise Feature Fusion Network for Detecting Tiny Objects in Remote Sensing Images
• DeepFashion2: A Versatile Benchmark for Detection, Pose Estimation, Segmentation and Re-Identification of Clothing Images
• CFENet: An Accurate and Efficient Single-Shot Object Detector for Autonomous Driving
• Learning Context Graph for Person Search
• SOD-YOLO: Enhancing YOLO-Based Detection of Small Objects in UAV Imagery
• Few-shot Object Detection with Feature Attention Highlight Module in Remote Sensing Images
• Funnel-HOI: Top-Down Perception for Zero-Shot HOI Detection
• Improve bone age assessment by learning from anatomical local regions
• Universal Physical Camouflage Attacks on Object Detectors
• Frequency-Dynamic Attention Modulation for Dense Prediction
• Search Spaces for Neural Model Training
• 3DGeoDet: General-purpose Geometry-aware Image-based 3D Object Detection
• Bilinear Graph Networks for Visual Question Answering
• Rethinking of Radar's Role: A Camera-Radar Dataset and Systematic Annotator via Coordinate Alignment
• InterpIoU: Rethinking Bounding Box Regression with Interpolation-Based IoU Optimization
• Deep Blur Mapping: Exploiting High-Level Semantics by Deep Neural Networks
• An Attention Module for Convolutional Neural Networks
• Video Foundation Models for Animal Behavior Analysis
• Attention to Lesion: Lesion-Aware Convolutional Neural Network for Retinal Optical Coherence Tomography Image Classification
• HR-RCNN: Hierarchical Relational Reasoning for Object Detection
• COVR: A test-bed for Visually Grounded Compositional Generalization with real images
• UniMoCo: Unsupervised, Semi-Supervised and Full-Supervised Visual Representation Learning
• Pretraining Techniques for Sequence-to-Sequence Voice Conversion
• Location-Aware Feature Selection Text Detection Network
• Prediction-Tracking-Segmentation
• ObjectNet Dataset: Reanalysis and Correction
• Multi-person Articulated Tracking with Spatial and Temporal Embeddings
• ClipCap: CLIP Prefix for Image Captioning
• Exploiting Contextual Information with Deep Neural Networks
• Sperm Detection and Tracking in Phase-Contrast Microscopy Image Sequences using Deep Learning and Modified CSR-DCF
• SynthRef: Generation of Synthetic Referring Expressions for Object Segmentation
• OVANet: One-vs-All Network for Universal Domain Adaptation
• Enhancing Object Detection in Adverse Conditions using Thermal Imaging
• MovieNet: A Holistic Dataset for Movie Understanding
• DIODE: Dilatable Incremental Object Detection
• TOG: Targeted Adversarial Objectness Gradient Attacks on Real-time Object Detection Systems
• CenterMask: single shot instance segmentation with point representation
• Learning Orientation-Estimation Convolutional Neural Network for Building Detection in Optical Remote Sensing Image
• Towards End-to-End Text Spotting in Natural Scenes
• Pointly-Supervised Instance Segmentation
• Face Anti-Spoofing by Learning Polarization Cues in a Real-World Scenario
• Adaptive Object Detection Using Adjacency and Zoom Prediction
• A survey of Object Classification and Detection based on 2D/3D data
• Weakly Supervised Dataset Collection for Robust Person Detection
• Convolutional Neural Networks for User Identificationbased on Motion Sensors Represented as Image
• Cascade R-CNN: High Quality Object Detection and Instance Segmentation
• A Multimodal Sentiment Dataset for Video Recommendation
• Adaptive Multi-scale Detection of Acoustic Events
• PSC-Net: Learning Part Spatial Co-occurrence for Occluded Pedestrian Detection
• Data-Efficient Challenges in Visual Inductive Priors: A Retrospective
• SIFT Meets CNN: A Decade Survey of Instance Retrieval
• DR Loss: Improving Object Detection by Distributional Ranking
• Face Parsing with RoI Tanh-Warping
• Analysis and a Solution of Momentarily Missed Detection for Anchor-based Object Detectors
• IAN: The Individual Aggregation Network for Person Search
• Sequential End-to-end Network for Efficient Person Search
• Hiding Faces in Plain Sight: Disrupting AI Face Synthesis with Adversarial Perturbations
• Universal Adversarial Perturbations: A Survey
• Stabilized Medical Image Attacks
• Multi-Scale Attention Network for Crowd Counting
• Learning 3D-aware Egocentric Spatial-Temporal Interaction via Graph Convolutional Networks
• NADS-Net: A Nimble Architecture for Driver and Seat Belt Detection via Convolutional Neural Networks
• A Training-free, One-shot Detection Framework For Geospatial Objects In Remote Sensing Images
• Self-Supervised Learning for Semi-Supervised Temporal Action Proposal
• EAdam Optimizer: How ε Impact Adam
• Harvesting, Detecting, and Characterizing Liver Lesions from Large-scale Multi-phase CT Data via Deep Dynamic Texture Learning
• Semantic Image Manipulation Using Scene Graphs
• Relevance Attack on Detectors
• FrostNet: Towards Quantization-Aware Network Architecture Search
• Deep neural networks can be improved using human-derived contextual expectations
• Exploring Low-light Object Detection Techniques
• Boosting ship detection in SAR images with complementary pretraining techniques
• A Video Analysis Method on Wanfang Dataset via Deep Neural Network
• Back to Simplicity: How to Train Accurate BNNs from Scratch?
• Object-aware Feature Aggregation for Video Object Detection
• Making History Matter: History-Advantage Sequence Training for Visual Dialog
• Gaining Extra Supervision via Multi-task learning for Multi-Modal Video Question Answering
• Universal Adder Neural Networks
• Panoptic Feature Pyramid Networks
• Multi-Person Pose Estimation with Enhanced Feature Aggregation and Selection
• Scene-Graph Augmented Data-Driven Risk Assessment of Autonomous Vehicle Decisions
• Regularizing Neural Networks via Stochastic Branch Layers
• DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
• LyAm: Robust Non-Convex Optimization for Stable Learning in Noisy Environments
• Learning non-maximum suppression
• Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey
• CASIA-Face-Africa: A Large-scale African Face Image Database
• Learning a metacognition for object perception
• On the Evaluation of Prohibited Item Classification and Detection in Volumetric 3D Computed Tomography Baggage Security Screening Imagery
• PanoNet3D: Combining Semantic and Geometric Understanding for LiDARPoint Cloud Detection
• A Holistically-Guided Decoder for Deep Representation Learning with Applications to Semantic Segmentation and Object Detection
• Dense Multiscale Feature Fusion Pyramid Networks for Object Detection in UAV-Captured Images
• Deformable Tube Network for Action Detection in Videos
• Sewer-ML: A Multi-Label Sewer Defect Classification Dataset and Benchmark
• Discovering Spatio-Temporal Action Tubes
• GKNet: Graph-based Keypoints Network for Monocular Pose Estimation of Non-cooperative Spacecraft
• A Comprehensive Survey for Real-World Industrial Defect Detection: Challenges, Approaches, and Prospects
• Combining Transformers and CNNs for Efficient Object Detection in High-Resolution Satellite Imagery
• Conceptualizing Multi-scale Wavelet Attention and Ray-based Encoding for Human-Object Interaction Detection
• Object-Centric Mobile Manipulation through SAM2-Guided Perception and Imitation Learning
• OOWL500: Overcoming Dataset Collection Bias in the Wild
• Layer-wise Customized Weak Segmentation Block and AIoU Loss for Accurate Object Detection
• CNN-based Density Estimation and Crowd Counting: A Survey
• Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Net
• 1st Place Solution for the UVO Challenge on Image-based Open-World Segmentation 2021
• Deep Co-Training for Semi-Supervised Image Recognition
• Hierarchical Neural Collapse Detection Transformer for Class Incremental Object Detection
• Real-Time Text Detection and Recognition
• Fine-Grained Zero-Shot Object Detection
• Aggregated Residual Transformations for Deep Neural Networks
• ContourRend: A Segmentation Method for Improving Contours by Rendering
• Perception Improvement for Free: Exploring Imperceptible Black-box Adversarial Attacks on Image Classification
• Neighbourhood Distillation: On the benefits of non end-to-end distillation
• SlumpGuard: An AI-Powered Real-Time System for Automated Concrete Slump Prediction via Video Analysis
• Glance-MCMT: A General MCMT Framework with Glance Initialization and Progressive Association
• 3DGAA: Realistic and Robust 3D Gaussian-based Adversarial Attack for Autonomous Driving
• ADAM: Autonomous Discovery and Annotation Model using LLMs for Context-Aware Annotations
• Measuring the Impact of Rotation Equivariance on Aerial Object Detection
• Tackling the Unannotated: Scene Graph Generation with Bias-Reduced Models
• Two is a crowd: tracking relations in videos
• Product-oriented Machine Translation with Cross-modal Cross-lingual Pre-training
• LLM-Guided Agentic Object Detection for Open-World Understanding
• WebVision Challenge: Visual Learning and Understanding With Web Data
• Say As You Wish: Fine-grained Control of Image Caption Generation with Abstract Scene Graphs
• Split and Connect: A Universal Tracklet Booster for Multi-Object Tracking
• Channel-wise Alignment for Adaptive Object Detection
• SimVLM: Simple Visual Language Model Pretraining with Weak Supervision
• Ambiguity-Aware and High-Order Relation Learning for Multi-Grained Image-Text Matching
• TapLab: A Fast Framework for Semantic Video Segmentation Tapping into Compressed-Domain Knowledge
• Butter: Frequency Consistency and Hierarchical Fusion for Autonomous Driving Object Detection
• RoHOI: Robustness Benchmark for Human-Object Interaction Detection
• Progressive Cross-Stream Cooperation in Spatial and Temporal Domain for Action Localization
• Chained-Tracker: Chaining Paired Attentive Regression Results for End-to-End Joint Multiple-Object Detection and Tracking
• Move to See Better: Self-Improving Embodied Object Detection
• Knowledge-Enriched Visual Storytelling
• Certainty Driven Consistency Loss on Multi-Teacher Networks for Semi-Supervised Learning
• Visual Semantic Description Generation with MLLMs for Image-Text Matching
• Unified People Tracking with Graph Neural Networks
• Smelly, dense, and spreaded: The Object Detection for Olfactory References (ODOR) dataset
• Cross-Resolution SAR Target Detection Using Structural Hierarchy Adaptation and Reliable Adjacency Alignment
• Weight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gap
• Language and Visual Entity Relationship Graph for Agent Navigation
• Neighbor-view Enhanced Model for Vision and Language Navigation
• Oriented Objects as pairs of Middle Lines
• Towards Detection of Sheep Onboard a UAV
• Car Object Counting and Position Estimation via Extension of the CLIP-EBC Framework
• Lightweight Object Detection Using Quantized YOLOv4-Tiny for Emergency Response in Aerial Imagery
• Doodle Your Keypoints: Sketch-Based Few-Shot Keypoint Detection
• 3D-ADAM: A Dataset for 3D Anomaly Detection in Additive Manufacturing
• Rainbow Artifacts from Electromagnetic Signal Injection Attacks on Image Sensors
• A Hybrid Multilayer Extreme Learning Machine for Image Classification with an Application to Quadcopters
• 6-PACK: Category-level 6D Pose Tracker with Anchor-Based Keypoints
• Bi-Classifier Determinacy Maximization for Unsupervised Domain Adaptation
• Spatial ModernBERT: Spatial-Aware Transformer for Table and Key-Value Extraction in Financial Documents at Scale
• A model-agnostic active learning approach for animal detection from camera traps
• Unsupervised Multimodal Neural Machine Translation with Pseudo Visual Pivoting
• Deep Learning Techniques for Future Intelligent Cross-Media Retrieval
• Mask6D: Masked Pose Priors For 6D Object Pose Estimation
• Multi-Class 3D Object Detection Within Volumetric 3D Computed Tomography Baggage Security Screening Imagery
• LOVON: Legged Open-Vocabulary Object Navigator
• What Demands Attention in Urban Street Scenes? From Scene Understanding towards Road Safety: A Survey of Vision-driven Datasets and Studies
• VisioPath: Vision-Language Enhanced Model Predictive Control for Safe Autonomous Navigation in Mixed Traffic
• SULAND v2: A Refined RGB Dataset and Deep Learning Object Detection Benchmark for UAV/UGV-Based SUrface LANDmine Detection Under Domain Shift
• Humble Teachers Teach Better Students for Semi-Supervised Object Detection
• Contrastive and Transfer Learning for Effective Audio Fingerprinting through a Real-World Evaluation Protocol
• SPADE: Spatial-Aware Denoising Network for Open-vocabulary Panoptic Scene Graph Generation with Long- and Local-range Context Reasoning
• Vision Based Picking System for Automatic Express Package Dispatching
• DREAM: Document Reconstruction via End-to-end Autoregressive Model
• Learning to Reconstruct and Segment 3D Objects
• SIENet: Spatial Information Enhancement Network for 3D Object Detection from Point Cloud
• DeepApple: Deep Learning-based Apple Detection using a Suppression Mask R-CNN
• Self-Knowledge Distillation with Progressive Refinement of Targets
• Batch Normalization with Enhanced Linear Transformation
• Learning Human-Object Interactions by Graph Parsing Neural Networks
• Spatio-temporal Person Retrieval via Natural Language Queries
• Actions as Moving Points
• R-VLM: Region-Aware Vision Language Model for Precise GUI Grounding
• A Selective Survey on Versatile Knowledge Distillation Paradigm for Neural Network Models
• TigAug: Data Augmentation for Testing Traffic Light Detection in Autonomous Driving Systems
• YOLO-APD: Enhancing YOLOv8 for Robust Pedestrian Detection on Complex Road Geometries
• Using Cross-Model EgoSupervision to Learn Cooperative Basketball Intention
• ReFormer: The Relational Transformer for Image Captioning
• Self-Supervised Real-Time Tracking of Military Vehicles in Low-FPS UAV Footage
• Monocular 3D Object Detection and Box Fitting Trained End-to-End Using Intersection-over-Union Loss
• HGNet: High-Order Spatial Awareness Hypergraph and Multi-Scale Context Attention Network for Colorectal Polyp Detection
• Visual Identification of Individual Holstein-Friesian Cattle via Deep Metric Learning
• Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression
• LabelEnc: A New Intermediate Supervision Method for Object Detection
• Few-Shot Transformation of Common Actions into Time and Space
• DevMuT: Testing Deep Learning Framework via Developer Expertise-Based Mutation
• Automated Object Behavioral Feature Extraction for Potential Risk Analysis based on Video Sensor
• DMAT: An End-to-End Framework for Joint Atmospheric Turbulence Mitigation and Object Detection
• Early Convolutions Help Transformers See Better
• ASFormer: Transformer for Action Segmentation
• Just Add Geometry: Gradient-Free Open-Vocabulary 3D Detection Without Human-in-the-Loop
• Overcoming Statistical Shortcuts for Open-ended Visual Counting
• Self-supervised Object Tracking with Cycle-consistent Siamese Networks
• On Class Imbalance and Background Filtering in Visual Relationship Detection
• CUAB: Convolutional Uncertainty Attention Block Enhanced the Chest X-ray Image Analysis
• T-SYNTH: A Knowledge-Based Dataset of Synthetic Breast Images
• Unsupervised data augmentation for object detection
• An Empirical Study of Spatial Attention Mechanisms in Deep Networks
• Universal Bounding Box Regression and Its Applications
• Answer Them All! Toward Universal Visual Question Answering Models
• MRC-DETR: An Adaptive Multi-Residual Coupled Transformer for Bare Board PCB Defect Detection
• R-TOD: Real-Time Object Detector with Minimized End-to-End Delay for Autonomous Driving
• C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection
• Text Perceptron: Towards End-to-End Arbitrary-Shaped Text Spotting
• SOLQ: Segmenting Objects by Learning Queries
• Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Transformers
• Unsupervised Deep Representation Learning for Real-Time Tracking
• Open-Vocabulary Object Detection in UAV Imagery: A Review and Future Perspectives
• i-Mix: A Domain-Agnostic Strategy for Contrastive Representation Learning
• Segmenting Unknown 3D Objects from Real Depth Images using Mask R-CNN Trained on Synthetic Data
• Learning Spatio-Appearance Memory Network for High-Performance Visual Tracking
• Local Metrics for Multi-Object Tracking
• Malignancy Prediction and Lesion Identification from Clinical Dermatological Images
• CircleNet: Anchor-free Detection with Circle Representation
• Automatic Labelling for Low-Light Pedestrian Detection
• FNA++: Fast Network Adaptation via Parameter Remapping and Architecture Search
• MedFormer: Hierarchical Medical Vision Transformer with Content-Aware Dual Sparse Selection Attention
• CrowdTrack: A Benchmark for Difficult Multiple Pedestrian Tracking in Real Scenarios
• A Novel Tuning Method for Real-time Multiple-Object Tracking Utilizing Thermal Sensor with Complexity Motion Pattern
• The Problem of Fragmented Occlusion in Object Detection
• DORi: Discovering Object Relationship for Moment Localization of a Natural-Language Query in Video
• Tomato plant disease detection using transfer learning with C-GAN synthetic images
• Robust Real-Time Pedestrian Detection on Embedded Devices
• PolyTransform: Deep Polygon Transformer for Instance Segmentation
• Detecting tiny objects in aerial images: A normalized Wasserstein distance and a new benchmark
• TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarios
• Dynamic Refinement Network for Oriented and Densely Packed Object Detection
• Towards Compact CNNs via Collaborative Compression
• Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence
• Domain Adaptation without Source Data
• DeRIS: Decoupling Perception and Cognition for Enhanced Referring Image Segmentation through Loopback Synergy
• I3Net: Implicit Instance-Invariant Network for Adapting One-Stage Object Detectors
• Integrating Traditional and Deep Learning Methods to Detect Tree Crowns in Satellite Images
• Affordance Transfer Learning for Human-Object Interaction Detection
• Contextual Multi-Scale Region Convolutional 3D Network for Activity Detection
• 3D Gaussian Splatting Driven Multi-View Robust Physical Adversarial Camouflage Generation
• SSA-CNN: Semantic Self-Attention CNN for Pedestrian Detection
• Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models
• NOCTIS: Novel Object Cyclic Threshold based Instance Segmentation
• Active Measurement: Efficient Estimation at Scale
• Robust Component Detection for Flexible Manufacturing: A Deep Learning Approach to Tray-Free Object Recognition under Variable Lighting
• High-Frequency Semantics and Geometric Priors for End-to-End Detection Transformers in Challenging UAV Imagery
• UPRE: Zero-Shot Domain Adaptation for Object Detection via Unified Prompt and Representation Enhancement
• De-Simplifying Pseudo Labels to Enhancing Domain Adaptive Object Detection
• Disentangling Label Distribution for Long-tailed Visual Recognition
• m-RevNet: Deep Reversible Neural Networks with Momentum
• Customizable ROI-Based Deep Image Compression
• Mind the Detail: Uncovering Clinically Relevant Image Details in Accelerated MRI with Semantically Diverse Reconstructions
• Amodal Instance Segmentation
• AFAN: Augmented Feature Alignment Network for Cross-Domain Object Detection
• X-LineNet: Detecting Aircraft in Remote Sensing Images by a pair of Intersecting Line Segments
• A Revised Generative Evaluation of Visual Dialogue
• DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
• Attention-Driven Dynamic Graph Convolutional Network for Multi-Label Image Recognition
• SelvaBox: A high-resolution dataset for tropical tree crown detection
• Restoring Spatially-Heterogeneous Distortions using Mixture of Experts Network
• Data Augmentation For Small Object using Fast AutoAugment
• Can We Challenge Open-Vocabulary Object Detectors with Generated Content in Street Scenes?
• PBCAT: Patch-based composite adversarial training against physically realizable attacks on object detection
• Event-based Tiny Object Detection: A Benchmark Dataset and Baseline
• Improve Underwater Object Detection through YOLOv12 Architecture and Physics-informed Augmentation
• Synergizing between Self-Training and Adversarial Learning for Domain Adaptive Object Detection
• Semi-Supervised Surface Anomaly Detection of Composite Wind Turbine Blades From Drone Imagery
• TOOD: Task-aligned One-stage Object Detection
• Data Augmentation Revisited: Rethinking the Distribution Gap between Clean and Augmented Data
• Achieving Human Parity on Visual Question Answering
• Spurious-Aware Prototype Refinement for Reliable Out-of-Distribution Detection
• DirectPose: Direct End-to-End Multi-Person Pose Estimation
• Linear Context Transform Block
• MiniVLM: A Smaller and Faster Vision-Language Model
• OGNet: Salient Object Detection with Output-guided Attention Module
• Congestion Analysis of Convolutional Neural Network-Based Pedestrian Counting Methods on Helicopter Footage
• Person-in-WiFi: Fine-grained Person Perception using WiFi
• CAMERAS: Enhanced Resolution And Sanity preserving Class Activation Mapping for image saliency
• DGE-YOLO: Dual-Branch Gathering and Attention for Accurate UAV Object Detection
• Transformer-Based Person Search with High-Frequency Augmentation and Multi-Wave Mixing
• Dont Even Look Once: Synthesizing Features for Zero-Shot Detection
• Attention to the Burstiness in Visual Prompt Tuning!
• Region-Aware CAM: High-Resolution Weakly-Supervised Defect Segmentation via Salient Region Perception
• A Survey of Human-in-the-loop for Machine Learning
• VoteSplat: Hough Voting Gaussian Splatting for 3D Scene Understanding
• Dual-Level Collaborative Transformer for Image Captioning
• Label-PEnet: Sequential Label Propagation and Enhancement Networks for Weakly Supervised Instance Segmentation
• A New Window Loss Function for Bone Fracture Detection and Localization in X-ray Images with Point-based Annotation
• Improving Token-based Object Detection with Video
• Attention-disentangled Uniform Orthogonal Feature Space Optimization for Few-shot Object Detection
• Contextual Heterogeneous Graph Network for Human-Object Interaction Detection
• Learning Human-Object Interaction Detection using Interaction Points
• Social Adaptive Module for Weakly-supervised Group Activity Recognition
• Detecting Text in the Wild with Deep Character Embedding Network
• Disaster mapping from satellites: damage detection with crowdsourced point labels
• Visual Content Detection in Educational Videos with Transfer Learning and Dataset Enrichment
• Object Tracking Using Spatio-Temporal Future Prediction
• Pixels-to-Graph: Real-time Integration of Building Information Models and Scene Graphs for Semantic-Geometric Human-Robot Understanding
• CARAFE++: Unified Content-Aware ReAssembly of FEatures
• Energy Drain of the Object Detection Processing Pipeline for Mobile Devices: Analysis and Implications
• TITAN: Query-Token based Domain Adaptive Adversarial Learning
• VideoMix: Rethinking Data Augmentation for Video Classification
• YOLO-FDA: Integrating Hierarchical Attention and Detail Enhancement for Surface Defect Detection
• EgoAdapt: Adaptive Multisensory Distillation and Policy Learning for Efficient Egocentric Perception
• Boosting Generative Adversarial Transferability with Self-supervised Vision Transformer Features
• Boosting Domain Generalized and Adaptive Detection with Diffusion Models: Fitness, Generalization, and Transferability
• Finding Task-Relevant Features for Few-Shot Learning by Category Traversal
• Style-Aligned Image Composition for Robust Detection of Abnormal Cells in Cytopathology
• 3D for Free: Crossmodal Transfer Learning using HD Maps
• THAT: Two Head Adversarial Training for Improving Robustness at Scale
• REGRAD: A Large-Scale Relational Grasp Dataset for Safe and Object-Specific Robotic Grasping in Clutter
• LogoDet-3K: A Large-Scale Image Dataset for Logo Detection
• Class-Agnostic Region-of-Interest Matching in Document Images
• Towards Reliable Detection of Empty Space: Conditional Marked Point Processes for Object Detection
• LiDAR point-cloud processing based on projection methods: a comparison
• Implicit Saliency in Deep Neural Networks
• Maximal Matching Matters: Preventing Representation Collapse for Robust Cross-Modal Retrieval
• Dense Video Captioning using Graph-based Sentence Summarization
• Lightweight Multi-Frame Integration for Robust YOLO Object Detection in Videos
• AeroLite-MDNet: Lightweight Multi-task Deviation Detection Network for UAV Landing
• Feature Hallucination for Self-supervised Action Recognition
• From Codicology to Code: A Comparative Study of Transformer and YOLO-based Detectors for Layout Analysis in Historical Documents
• Multi-Scale Positive Sample Refinement for Few-Shot Object Detection
• Cascaded Regression Tracking: Towards Online Hard Distractor Discrimination
• Scalable Dynamic Origin-Destination Demand Estimation Enhanced by High-Resolution Satellite Imagery Data
• Investigating Attention Mechanism in 3D Point Cloud Object Detection
• CBAM-STN-TPS-YOLO: Enhancing Agricultural Object Detection through Spatially Adaptive Attention Mechanisms
• Geometry Normalization Networks for Accurate Scene Text Detection
• AdaDeDup: Adaptive Hybrid Data Pruning for Efficient Large-Scale Object Detection Training
• Memory Enhanced Global-Local Aggregation for Video Object Detection
• Sparse DETR: Efficient End-to-End Object Detection with Learnable Sparsity
• USIS16K: High-Quality Dataset for Underwater Salient Instance Segmentation
• Cooling-Shrinking Attack: Blinding the Tracker with Imperceptible Noises
• Progressive Modality Cooperation for Multi-Modality Domain Adaptation
• Deep Reasoning with Knowledge Graph for Social Relationship Understanding
• Disentangled Motif-aware Graph Learning for Phrase Grounding
• Joint Deep Learning of Facial Expression Synthesis and Recognition
• InfoFocus: 3D Object Detection for Autonomous Driving with Dynamic Information Modeling
• USVTrack: USV-Based 4D Radar-Camera Tracking Dataset for Autonomous Driving in Inland Waterways
• Mask-GD Segmentation Based Robotic Grasp Detection
• Dual-Forward Path Teacher Knowledge Distillation: Bridging the Capacity Gap Between Teacher and Student
• Domain Randomization for Object Detection in Manufacturing Applications using Synthetic Data: A Comprehensive Study
• Spatial-temporal Fusion Convolutional Neural Network for Simulated Driving Behavior Recognition
• Disp R-CNN: Stereo 3D Object Detection via Shape Prior Guided Instance Disparity Estimation
• HAL: Improved Text-Image Matching by Mitigating Visual Semantic Hubs
• Pattern-Based Phase-Separation of Tracer and Dispersed Phase Particles in Two-Phase Defocusing Particle Tracking Velocimetry
• On the Robustness of Human-Object Interaction Detection against Distribution Shift
• Feedback Driven Multi Stereo Vision System for Real-Time Event Analysis
• Segmentation Mask Guided End-to-End Person Search
• A Multi-task Contextual Atrous Residual Network for Brain Tumor Detection & Segmentation
• YOLOv13: Real-Time Object Detection with Hypergraph-Enhanced Adaptive Visual Perception
• CSDN: A Context-Gated Self-Adaptive Detection Network for Real-Time Object Detection
• DRAMA-X: A Fine-grained Intent Prediction and Risk Reasoning Benchmark For Driving
• HARRISON: A Benchmark on HAshtag Recommendation for Real-world Images in Social Networks
• GUIPilot: A Consistency-based Mobile GUI Testing Approach for Detecting Application-specific Bugs
• RoIMix: Proposal-Fusion among Multiple Images for Underwater Object Detection
• On Feature Normalization and Data Augmentation
• Diversify and Match: A Domain Adaptive Representation Learning Paradigm for Object Detection
• Unsupervised Pre-training for Person Re-identification
• CDeC-Net: Composite Deformable Cascade Network for Table Detection in Document Images
• Class Agnostic Instance-level Descriptor for Visual Instance Search
• Cross-modal Offset-guided Dynamic Alignment and Fusion for Weakly Aligned UAV Object Detection
• Convolutional Character Networks
• RealDriveSim: A Realistic Multi-Modal Multi-Task Synthetic Dataset for Autonomous Driving
• End-to-End Video Instance Segmentation with Transformers
• iShape: A First Step Towards Irregular Shape Instance Segmentation
• You Cannot Easily Catch Me: A Low-Detectable Adversarial Patch for Object Detectors
• Hierarchical Scene Parsing by Weakly Supervised Learning with Image Descriptions
• Turning old models fashion again: Recycling classical CNN networks using the Lattice Transformation
• Real-Time Seamless Single Shot 6D Object Pose Prediction
• Opening up Open-World Tracking
• Translate-to-Recognize Networks for RGB-D Scene Recognition
• PointINS: Point-based Instance Segmentation
• 3D Object Detection on Point Clouds using Local Ground-aware and Adaptive Representation of scenes' surface
• AI-driven visual monitoring of industrial assembly tasks
• Image Captioning Based on a Hierarchical Attention Mechanism and Policy Gradient Optimization
• RetinaFace: Single-stage Dense Face Localisation in the Wild
• SAFCAR: Structured Attention Fusion for Compositional Action Recognition
• Open-World Object Counting in Videos
• Vehicle Detection in Deep Learning
• Improving Visual Question Answering by Referring to Generated Paragraph Captions
• Towards Automatic Construction of Diverse, High-quality Image Dataset
• BinaryRelax: A Relaxation Approach For Training Deep Neural Networks With Quantized Weights
• Rethinking Pseudo-LiDAR Representation
• Learning to Navigate for Fine-grained Classification
• Image Segmentation with Large Language Models: A Survey with Perspectives for Intelligent Transportation Systems
• GoG: Relation-aware Graph-over-Graph Network for Visual Dialog
• Malaria Detection and Classificaiton
• Multiple Instance Segmentation in Brachial Plexus Ultrasound Image Using BPMSegNet
• Egocentric Human-Object Interaction Detection: A New Benchmark and Method
• YOLOv11-RGBT: Towards a Comprehensive Single-Stage Multispectral Object Detection Framework
• Removing the Background by Adding the Background: Towards Background Robust Self-supervised Video Representation Learning
• Hallucination Improves Few-Shot Object Detection
• Robustness Enhancement of Object Detection in Advanced Driver Assistance Systems (ADAS)
• Evaluating Explainability: A Framework for Systematic Assessment and Reporting of Explainable AI Features
• An Unsupervised Sampling Approach for Image-Sentence Matching Using Document-Level Structural Information
• ESRPCB: an Edge guided Super-Resolution model and Ensemble learning for tiny Printed Circuit Board Defect detection
• Deep Learning-Based Multi-Object Tracking: A Comprehensive Survey from Foundations to State-of-the-Art
• Curriculum By Smoothing
• All One Needs to Know about Metaverse: A Complete Survey on Technological Singularity, Virtual Ecosystem, and Research Agenda
• ADAM-Dehaze: Adaptive Density-Aware Multi-Stage Dehazing for Improved Object Detection in Foggy Conditions
• Continual Learning for Generative AI: From LLMs to MLLMs and Beyond
• MeliusNet: Can Binary Neural Networks Achieve MobileNet-level Accuracy?
• Benchmarking Single Image Dehazing and Beyond
• FOAM: A General Frequency-Optimized Anti-Overlapping Framework for Overlapping Object Perception
• Bring Your Own Codegen to Deep Learning Compiler
• Probabilistic Ranking-Aware Ensembles for Enhanced Object Detections
• Human Object Interaction Detection using Two-Direction Spatial Enhancement and Exclusive Object Prior
• A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets
• Universal Lesion Detection by Learning from Multiple Heterogeneously Labeled Datasets
• Stereo Vision Based Single-Shot 6D Object Pose Estimation for Bin-Picking by a Robot Manipulator
• Attention Based Glaucoma Detection: A Large-scale Database and CNN Model
• Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
• Improving 3D Object Detection for Pedestrians with Virtual Multi-View Synthesis Orientation Estimation
• Fingerspelling recognition in the wild with iterative visual attention
• Towards Unified INT8 Training for Convolutional Neural Network
• Generalization Bounds for Convolutional Neural Networks
• DSFD: Dual Shot Face Detector
• DMV: Visual Object Tracking via Part-level Dense Memory and Voting-based Retrieval
• Context Encoding Chest X-rays
• Affinity Graph Supervision for Visual Recognition
• Learned Image Compression for Machine Perception
• Team JL Solution to Google Landmark Recognition 2019
• Image-based localization using LSTMs for structured feature correlation
• Scene-aware SAR ship detection guided by unsupervised sea-land segmentation
• Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts
• Domain Generalization for Person Re-identification: A Survey Towards Domain-Agnostic Person Matching
• MatchPlant: An Open-Source Pipeline for UAV-Based Single-Plant Detection and Data Extraction
• Dynamic Relevance Learning for Few-Shot Object Detection
• Towards End-to-end Text Spotting with Convolutional Recurrent Neural Networks
• Distilling Object Detectors with Task Adaptive Regularization
• Vision-based Lifting of 2D Object Detections for Automated Driving
• Teleoperated Driving: a New Challenge for 3D Object Detection in Compressed Point Clouds
• Efficient Object Embedding for Spliced Image Retrieval
• Sequence Level Semantics Aggregation for Video Object Detection
• High-order Tensor Pooling with Attention for Action Recognition
• Graph-Structured Referring Expression Reasoning in The Wild
• Manager: Aggregating Insights from Unimodal Experts in Two-Tower VLMs and MLLMs
• Representation Decomposition for Learning Similarity and Contrastness Across Modalities for Affective Computing
• OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields
• An Empirical Study on Leveraging Scene Graphs for Visual Question Answering
• Joint Layout Analysis, Character Detection and Recognition for Historical Document Digitization
• LGPMA: Complicated Table Structure Recognition with Local and Global Pyramid Mask Alignment
• Appearance-Preserving 3D Convolution for Video-based Person Re-identification
• Fashionpedia: Ontology, Segmentation, and an Attribute Localization Dataset
• UG²⁺ Track 2: A Collective Benchmark Effort for Evaluating and Advancing Image Understanding in Poor Visibility Environments
• The Multi-Modal Video Reasoning and Analyzing Competition
• A Neural Rejection System Against Universal Adversarial Perturbations in Radio Signal Classification
• EdgeSpotter: Multi-Scale Dense Text Spotting for Industrial Panel Monitoring
• ViLLa: A Neuro-Symbolic approach for Animal Monitoring
• Semantic-decoupled Spatial Partition Guided Point-supervised Oriented Object Detection
• GRIP: Generative Robust Inference and Perception for Semantic Robot Manipulation in Adversarial Environments
• Teaching in adverse scenes: a statistically feedback-driven threshold and mask adjustment teacher-student framework for object detection in UAV images under adverse scenes
• Semi-Autoregressive Image Captioning
• Deep Volumetric Universal Lesion Detection using Light-Weight Pseudo 3D Convolution and Surface Point Regression
• J-DDL: Surface Damage Detection and Localization System for Fighter Aircraft
• SLICK: Selective Localization and Instance Calibration for Knowledge-Enhanced Car Damage Segmentation in Automotive Insurance
• K-Net: Towards Unified Image Segmentation
• ALBERT: Advanced Localization and Bidirectional Encoder Representations from Transformers for Automotive Damage Evaluation
• Co-mining: Self-Supervised Learning for Sparsely Annotated Object Detection
• Synthesizing Unrestricted False Positive Adversarial Objects Using Generative Models
• Searching for TrioNet: Combining Convolution with Local and Global Self-Attention
• The Four Color Theorem for Cell Instance Segmentation
• GLD-Road:A global-local decoding road network extraction model for remote sensing images
• Exploiting the Inherent Limitation of L0 Adversarial Examples
• Learning to Collocate Neural Modules for Image Captioning
• Simple online and real-time tracking with occlusion handling
• Exposing Semantic Segmentation Failures via Maximum Discrepancy Competition
• Dual Normalization Multitasking for Audio-Visual Sounding Object Localization
• Bridging Perspectives: A Survey on Cross-view Collaborative Intelligence with Egocentric-Exocentric Vision
• Dynamic Filtering with Large Sampling Field for ConvNets
• Semi-Online Knowledge Distillation
• Domain Adaptation for Big Data in Agricultural Image Analysis: A Comprehensive Review
• Adaptive Contextual Embedding for Robust Far-View Borehole Detection
• Regularizing Attention Networks for Anomaly Detection in Visual Question Answering
• VIVO: Visual Vocabulary Pre-Training for Novel Object Captioning
• AdaPruner: Adaptive Channel Pruning and Effective Weights Inheritance
• Locality-Aware Rotated Ship Detection in High-Resolution Remote Sensing Imagery Based on Multi-Scale Convolutional Network
• Learning from Lexical Perturbations for Consistent Visual Question Answering
• Mask R-CNN with Pyramid Attention Network for Scene Text Detection
• Real-Time Privacy Preservation for Robot Visual Perception
• Context-Aware Unsupervised Clustering for Person Search
• Advancement and Field Evaluation of a Dual-arm Apple Harvesting Robot
• Online Multi-Object Tracking with Dual Matching Attention Networks
• Integer Binary-Range Alignment Neuron for Spiking Neural Networks
• Joint Visual Grounding with Language Scene Graphs
• Extract and Merge: Merging extracted humans from different images utilizing Mask R-CNN
• Towards Mixed-Precision Quantization of Neural Networks via Constrained Optimization
• HOI Analysis: Integrating and Decomposing Human-Object Interaction
• Spatio-Temporal Action Detection with Cascade Proposal and Location Anticipation
• Mitosis Detection for Breast Cancer Pathology Images Using UV-Net
• FRED: The Florence RGB-Event Drone Dataset
• Bridging Annotation Gaps: Transferring Labels to Align Object Detection Datasets
• On Applying Machine Learning/Object Detection Models for Analysing Digitally Captured Physical Prototypes from Engineering Design Projects
• A Survey on Vietnamese Document Analysis and Recognition: Challenges and Future Directions
• VoxDet: Rethinking 3D Semantic Occupancy Prediction as Dense Object Detection
• Cheaper Pre-training Lunch: An Efficient Paradigm for Object Detection
• ConvTransformer: A Convolutional Transformer Network for Video Frame Synthesis
• Multiple Object Tracking with Motion and Appearance Cues
• An Automatic System for Unconstrained Video-Based Face Recognition
• Learning to decompose for object detection and instance segmentation
• Co-Grounding Networks with Semantic Attention for Referring Expression Comprehension in Videos
• Image-based table recognition: data, model, and evaluation
• Multi-Branch Fully Convolutional Network for Face Detection
• Accurate Monocular Object Detection via Color-Embedded 3D Reconstruction for Autonomous Driving
• Act Like a Radiologist: Towards Reliable Multi-view Correspondence Reasoning for Mammogram Mass Detection
• Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generation
• iSAID: A Large-scale Dataset for Instance Segmentation in Aerial Images
• Object Detection in Video with Spatial-temporal Context Aggregation
• Key Points Estimation and Point Instance Segmentation Approach for Lane Detection
• Closing the Generalization Gap of Adaptive Gradient Methods in Training Deep Neural Networks
• SS3D: Single Shot 3D Object Detector
• Style Normalization and Restitution for Domain Generalization and Adaptation
• Domain Contrast for Domain Adaptive Object Detection
• Exploring the Hierarchy in Relation Labels for Scene Graph Generation
• The Next Big Thing(s) in Unsupervised Machine Learning: Five Lessons from Infant Learning
• Better Understanding Hierarchical Visual Relationship for Image Caption
• Copyspace: Where to Write on Images?
• Fine-Grained Image Analysis with Deep Learning: A Survey
• Reduced Focal Loss: 1st Place Solution to xView object detection in Satellite Imagery
• Detecting Human-Object Interactions with Action Co-occurrence Priors
• Transformation Driven Visual Reasoning
• Learning Efficient Detector with Semi-supervised Adaptive Distillation
• MS-YOLO: A Multi-Scale Model for Accurate and Efficient Blood Cell Detection
• Diversifying Sample Generation for Accurate Data-Free Quantization
• Compositional Scalable Object SLAM
• Graph-based Knowledge Distillation by Multi-head Attention Network
• Person Recognition at Altitude and Range: Fusion of Face, Body Shape and Gait
• MSNet: A Multilevel Instance Segmentation Network for Natural Disaster Damage Assessment in Aerial Videos
• 360-Indoor: Towards Learning Real-World Objects in 360° Indoor Equirectangular Images
• Recent Advances in Deep Learning for Object Detection
• IC Networks: Remodeling the Basic Unit for Convolutional Neural Networks
• Phrase Localization Without Paired Training Examples
• DOSED: a deep learning approach to detect multiple sleep micro-events in EEG signal
• Long-Term Feature Banks for Detailed Video Understanding
• GPS-Net: Graph Property Sensing Network for Scene Graph Generation
• Shape2Motion: Joint Analysis of Motion Parts and Attributes from 3D Shapes
• MixTConv: Mixed Temporal Convolutional Kernels for Efficient Action Recogntion
• Multi-layer Feature Aggregation for Deep Scene Parsing Models
• Weakly Supervised Cell Instance Segmentation by Propagating from Detection Response
• Meta-DETR: Image-Level Few-Shot Object Detection with Inter-Class Correlation Exploitation
• Double Anchor R-CNN for Human Detection in a Crowd
• Unleashing the Power of Chain-of-Prediction for Monocular 3D Object Detection
• MaskFace: multi-task face and landmark detector
• EmbedMask: Embedding Coupling for One-stage Instance Segmentation
• Tensor Programs II: Neural Tangent Kernel for Any Architecture
• Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentation
• Fusion of Head and Full-Body Detectors for Multi-Object Tracking
• One-Shot Unsupervised Cross-Domain Detection
• RAPiD: Rotation-Aware People Detection in Overhead Fisheye Images
• Relation Transformer Network
• Spatial Priming for Detecting Human-Object Interactions
• Audiovisual SlowFast Networks for Video Recognition
• Down to the Last Detail: Virtual Try-on with Detail Carving
• Sequential Context Encoding for Duplicate Removal
• Cross Chest Graph for Disease Diagnosis with Structural Relational Reasoning
• Towards Practical Multi-Object Manipulation using Relational Reinforcement Learning
• Augmented Parallel-Pyramid Net for Attention Guided Pose-Estimation
• DEPARA: Deep Attribution Graph for Deep Knowledge Transferability
• ASK: Adaptively Selecting Key Local Features for RGB-D Scene Recognition
• Towards Accurate One-Stage Object Detection with AP-Loss
• Farm land weed detection with region-based deep convolutional neural networks
• Meta Module Network for Compositional Visual Reasoning
• Scale-Aware Trident Networks for Object Detection
• Multi-Attribute Enhancement Network for Person Search
• Adversarial Examples in Modern Machine Learning: A Review
• Pseudo-IoU: Improving Label Assignment in Anchor-Free Object Detection
• Goal-oriented Object Importance Estimation in On-road Driving Videos
• DeCLIP: Decoupled Learning for Open-Vocabulary Dense Perception
• Beyond the Deep Metric Learning: Enhance the Cross-Modal Matching with Adversarial Discriminative Domain Regularization
• Towards Robust Pattern Recognition: A Review
• Transformer-Based Source-Free Domain Adaptation
• MobilePose: Real-Time Pose Estimation for Unseen Objects with Weak Shape Supervision
• Towards Better Object Detection in Scale Variation with Adaptive Feature Selection
• Signet Ring Cell Detection With a Semi-supervised Learning Framework
• Grounding Physical Concepts of Objects and Events Through Dynamic Visual Reasoning
• DeeperLab: Single-Shot Image Parser
• Learning Joint Representations of Videos and Sentences with Web Image Search
• DiagNet: Detecting Objects using Diagonal Constraints on Adjacency Matrix of Graph Neural Network
• Adaptive Object Detection with Dual Multi-Label Prediction
• A Deep Neuro-Fuzzy Network for Image Classification
• You Only Train Once
• Towards Unsupervised Crowd Counting via Regression-Detection Bi-knowledge Transfer
• Variational Saccading: Efficient Inference for Large Resolution Images
• FAN: Focused Attention Networks
• Video-Text Pre-training with Learned Regions
• A Free Lunch for Unsupervised Domain Adaptive Object Detection without Source Data
• Deeply Activated Salient Region for Instance Search
• FSHNet: Fully Sparse Hybrid Network for 3D Object Detection
• PDSE: A Multiple Lesion Detector for CT Images using PANet and Deformable Squeeze-and-Excitation Block
• Ice Hockey Puck Localization Using Contextual Cues
• InstaBoost: Boosting Instance Segmentation via Probability Map Guided Copy-Pasting
• Point-Set Anchors for Object Detection, Instance Segmentation and Pose Estimation
• VIPriors 1: Visual Inductive Priors for Data-Efficient Deep Learning Challenges
• PC2WF: 3D Wireframe Reconstruction from Raw Point Clouds
• High Performance Space Debris Tracking in Complex Skylight Backgrounds with a Large-Scale Dataset
• Normalized and Geometry-Aware Self-Attention Network for Image Captioning
• Reflective Decoding Network for Image Captioning
• From Multi-View to Hollow-3D: Hallucinated Hollow-3D R-CNN for 3D Object Detection
• A Parameterized Approach to Personalized Variable Length Summarization of Soccer Matches
• Rethinking Image-Scaling Attacks: The Interplay Between Vulnerabilities in Machine Learning Systems
• Weak Novel Categories without Tears: A Survey on Weak-Shot Learning
• SportMamba: Adaptive Non-Linear Multi-Object Tracking with State Space Models for Team Sports
• Geometric Visual Fusion Graph Neural Networks for Multi-Person Human-Object Interaction Recognition in Videos
• Auto-Labeling Data for Object Detection
• Organ At Risk Segmentation with Multiple Modality
• Stacked Deconvolutional Network for Semantic Segmentation
• The More You Know: Using Knowledge Graphs for Image Classification
• Real-time Human-Robot Collaborative Manipulations of Cylindrical and Cubic Objects via Geometric Primitives and Depth Information
• Improving Image Captioning by Leveraging Intra- and Inter-layer Global Representation in Transformer Network
• Hierarchy Parsing for Image Captioning
• Towards Unconstrained End-to-End Text Spotting
• unMORE: Unsupervised Multi-Object Segmentation via Center-Boundary Reasoning
• FDSG: Forecasting Dynamic Scene Graphs
• VRD-IU: Lessons from Visually Rich Document Intelligence and Understanding
• A 2-Stage Model for Vehicle Class and Orientation Detection with Photo-Realistic Image Generation
• PixelLink: Detecting Scene Text via Instance Segmentation
• WeightAlign: Normalizing Activations by Weight Alignment
• VoxelPose: Towards Multi-Camera 3D Human Pose Estimation in Wild Environment
• ZS-SLR: Zero-Shot Sign Language Recognition from RGB-D Videos
• DocSpiral: A Platform for Integrated Assistive Document Annotation through Human-in-the-Spiral
• OD3: Optimization-free Dataset Distillation for Object Detection
• SpatialFlow: Bridging All Tasks for Panoptic Segmentation
• Localizing Visual Sounds the Hard Way
• Optical Music Recognition: State of the Art and Major Challenges
• NODIS: Neural Ordinary Differential Scene Understanding
• SegVoxelNet: Exploring Semantic Context and Depth-aware Features for 3D Vehicle Detection from Point Cloud
• ProstaTD: Bridging Surgical Triplet from Classification to Fully Supervised Detection
• Advancing from Automated to Autonomous Beamline by Leveraging Computer Vision
• Toward Transformer-Based Object Detection
• Visual Agreement Regularized Training for Multi-Modal Machine Translation
• Visual Diagnosis of Dermatological Disorders: Human and Machine Performance
• Investigations of the Influences of a CNN's Receptive Field on Segmentation of Subnuclei of Bilateral Amygdalae
• Towards Predicting Any Human Trajectory In Context
• Pseudo-Labeling Driven Refinement of Benchmark Object Detection Datasets via Analysis of Learning Patterns
• Geometric Neural Phrase Pooling: Modeling the Spatial Co-occurrence of Neurons
• Probabilistic Oriented Object Detection in Automotive Radar
• Feature-Driven Super-Resolution for Object Detection
• Uncertainty-Aware Prototype Semantic Decoupling for Text-Based Person Search in Full Images
• iDPA: Instance Decoupled Prompt Attention for Incremental Medical Object Detection
• Learning to Assemble Neural Module Tree Networks for Visual Grounding
• Object Detection Networks on Convolutional Feature Maps
• Learning Instance-wise Sparsity for Accelerating Deep Models
• Target-Tailored Source-Transformation for Scene Graph Generation
• Multi-Task Incremental Learning for Object Detection
• GTNet:Guided Transformer Network for Detecting Human-Object Interactions
• Fast Local Attack: Generating Local Adversarial Examples for Object Detectors
• Jigsaw Clustering for Unsupervised Visual Representation Learning
• SSAP: Single-Shot Instance Segmentation With Affinity Pyramid
• Point Cloud Instance Segmentation using Probabilistic Embeddings
• Deformable Attention Mechanisms Applied to Object Detection, case of Remote Sensing
• Discriminative Semantic Feature Pyramid Network with Guided Anchoring for Logo Detection
• MFPN: A Novel Mixture Feature Pyramid Network of Multiple Architectures for Object Detection
• Error-Corrected Margin-Based Deep Cross-Modal Hashing for Facial Image Retrieval
• Discriminative Triad Matching and Reconstruction for Weakly Referring Expression Grounding
• Spectro-Temporal RF Identification using Deep Learning
• Multi-Precision Quantized Neural Networks via Encoding Decomposition of -1 and +1
• Learning to Filter: Siamese Relation Network for Robust Tracking
• Characters Detection on Namecard with faster RCNN
• Efficient Pig Counting in Crowds with Keypoints Tracking and Spatial-aware Temporal Response Filtering
• TPDNet: Triple phenotype deepen networks for monocular 3D object detection of melons and fruits in fields
• Conformal Object Detection by Sequential Risk Control
• Semi Supervised Deep Quick Instance Detection and Segmentation
• Shape Back-Projection In 3D Scenes
• PaStaNet: Toward Human Activity Knowledge Engine
• ReenactGAN: Learning to Reenact Faces via Boundary Transfer
• Image Captioning with Integrated Bottom-Up and Multi-level Residual Top-Down Attention for Game Scene Understanding
• A Reverse Causal Framework to Mitigate Spurious Correlations for Debiasing Scene Graph Generation
• Towards Fully Automated Manga Translation
• Point or Line? Using Line-based Representation for Panoptic Symbol Spotting in CAD Drawings
• Disrupting Vision-Language Model-Driven Navigation Services via Adversarial Object Fusion
• Advancing Image Super-resolution Techniques in Remote Sensing: A Comprehensive Survey
• WTEFNet: Real-Time Low-Light Object Detection for Advanced Driver Assistance Systems
• Deep Learning at 15PF: Supervised and Semi-Supervised Classification for Scientific Data
• Question Type Guided Attention in Visual Question Answering
• Multi-Sourced Compositional Generalization in Visual Question Answering
• SafeNet: An Assistive Solution to Assess Incoming Threats for Premises
• End-to-end Compression Towards Machine Vision: Network Architecture Design and Optimization
• AACP: Model Compression by Accurate and Automatic Channel Pruning
• Discovering Multi-Label Actor-Action Association in a Weakly Supervised\n Setting
• Simple Unsupervised Multi-Object Tracking
• FMG-Det: Foundation Model Guided Robust Object Detection
• Towards Multi-class Object Detection in Unconstrained Remote Sensing Imagery
• TinaFace: Strong but Simple Baseline for Face Detection
• Bosch Deep Learning Hardware Benchmark
• E²BoWs: An End-to-End Bag-of-Words Model via Deep Convolutional Neural Network
• Joint Monocular 3D Vehicle Detection and Tracking
• DeepIM: Deep Iterative Matching for 6D Pose Estimation
• PIDray: A Large-Scale X-ray Benchmark for Real-World Prohibited Item Detection
• A Survey on Long-Tailed Visual Recognition
• RefineMask: Towards High-Quality Instance Segmentation with Fine-Grained Features
• Face Detection with End-to-End Integration of a ConvNet and a 3D Model
• Structure Information is the Key: Self-Attention RoI Feature Extractor in 3D Object Detection
• RGBX-DiffusionDet: A Framework for Multi-Modal RGB-X Object Detection Using DiffusionDet
• Multi-Modal Pedestrian Detection with Large Misalignment Based on Modal-Wise Regression and Multi-Modal IoU
• Low-Light Maritime Image Enhancement with Regularized Illumination Optimization and Deep Noise Suppression
• Cross-DINO: Cross the Deep MLP and Transformer for Small Object Detection
• Noisy Annotation Refinement for Object Detection
• Patch2Pix: Epipolar-Guided Pixel-Level Correspondences
• Soft Anchor-Point Object Detection
• Streaming Object Detection for 3-D Point Clouds
• Multi-View Multi-Person 3D Pose Estimation with Plane Sweep Stereo
• Domain-Specific Suppression for Adaptive Object Detection
• MSFNet-CPD: Multi-Scale Cross-Modal Fusion Network for Crop Pest Detection
• Large Product Key Memory for Pretrained Language Models
• Learning Natural Language Generation from Scratch
• Looking Beyond Two Frames: End-to-End Multi-Object Tracking Using Spatial and Temporal Transformers
• DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision
• Semantic Feature Matching for Robust Mapping in Agriculture
• LSTC: Boosting Atomic Action Detection with Long-Short-Term Context
• Music's Multimodal Complexity in AVQA: Why We Need More than General Multimodal LLMs
• Understand, Think, and Answer: Advancing Visual Reasoning with Large Multimodal Models
• Abstractive Text Classification Using Sequence-to-convolution Neural Networks
• SAM-RCNN: Scale-Aware Multi-Resolution Multi-Channel Pedestrian Detection
• AmphibianDetector: adaptive computation for moving objects detection
• Identifying and Exploiting Structures for Reliable Deep Learning
• Detect-to-Retrieve: Efficient Regional Aggregation for Image Search
• Open-Det: An Efficient Learning Framework for Open-Ended Detection
• Assured Autonomy with Neuro-Symbolic Perception
• YOLO-SPCI: Enhancing Remote Sensing Object Detection via Selective-Perspective-Class Integration
• Visual Product Graph: Bridging Visual Products And Composite Images For End-to-End Style Recommendations
• VisAlgae 2023: A Dataset and Challenge for Algae Detection in Microscopy Images
• Spatio-Temporal Attention Models for Grounded Video Captioning
• Joint 3D Proposal Generation and Object Detection from View Aggregation
• Using Artificial Intelligence to Analyze Fashion Trends
• VLUC: An Empirical Benchmark for Video-Like Urban Computing on Citywide Crowd and Traffic Prediction
• Position, Padding and Predictions: A Deeper Look at Position Information in CNNs
• OpenPose: Realtime Multi-Person 2D Pose Estimation Using Part Affinity Fields
• UPSNet: A Unified Panoptic Segmentation Network
• Dual Attention Networks for Visual Reference Resolution in Visual Dialog
• From Data to Modeling: Fully Open-vocabulary Scene Graph Generation
• A Novel Shape-Aware Topological Representation for GPR Data with DNN Integration
• BCNet: Searching for Network Width with Bilaterally Coupled Network
• A Contrastive Learning Foundation Model Based on Perfectly Aligned Sample Pairs for Remote Sensing Images
• SaSi: A Self-augmented and Self-interpreted Deep Learning Approach for Few-shot Cryo-ET Particle Detection
• The Role of Video Generation in Enhancing Data-Limited Action Understanding
• Adaptive and Azimuth-Aware Fusion Network of Multimodal Local Features for 3D Object Detection
• Distilling Object Detectors via Decoupled Features
• Implicit Feature Alignment: Learn to Convert Text Recognizer to Text Spotter
• Min-Entropy Latent Model for Weakly Supervised Object Detection
• Optimizing the Trade-off between Single-Stage and Two-Stage Object Detectors using Image Difficulty Prediction
• Learning a Domain Classifier Bank for Unsupervised Adaptive Object Detection
• Tasks Integrated Networks: Joint Detection and Retrieval for Image Search
• CSTrack: Enhancing RGB-X Tracking via Compact Spatiotemporal Features
• Shape-Texture Debiased Neural Network Training
• Locality-Aware Zero-Shot Human-Object Interaction Detection
• Force Prompting: Video Generation Models Can Learn and Generalize Physics-based Control Signals
• Revolutionizing Wildfire Detection with Convolutional Neural Networks: A VGG16 Model Approach
• CentripetalNet: Pursuing High-quality Keypoint Pairs for Object Detection
• AM-LFS: AutoML for Loss Function Search
• Pillar-based Object Detection for Autonomous Driving
• Scene Text Detection with Scribble Lines
• Staircase Recognition and Location Based on Polarization Vision
• VL-SAM-V2: Open-World Object Detection with General and Specific Query Fusion
• WIDER Face and Pedestrian Challenge 2018: Methods and Results
• EMPNet: Neural Localisation and Mapping Using Embedded Memory Points
• Distill CLIP (DCLIP): Enhancing Image-Text Retrieval via Cross-Modal Transformer Distillation
• A Comprehensive Approach for UAV Small Object Detection with Simulation-based Transfer Learning and Adaptive Fusion
• Greedy Network Enlarging
• Federated Few-Shot Learning with Adversarial Learning
• Deep Learning Based Instance Segmentation in 3D Biomedical Images Using Weak Annotation
• Efficient DETR: Improving End-to-End Object Detector with Dense Prior
• Bottom-Up Temporal Action Localization with Mutual Regularization
• Value of Temporal Dynamics Information in Driving Scene Segmentation
• Cell Detection in Microscopy Images with Deep Convolutional Neural Network and Compressed Sensing
• Mitigating Context Bias in Domain Adaptation for Object Detection using Mask Pooling
• EllipseNet: Anchor-Free Ellipse Detection for Automatic Cardiac Biometrics in Fetal Echocardiography
• Complex-YOLO: Real-time 3D Object Detection on Point Clouds
• Image Resizing by Reconstruction from Deep Features
• LookUP: Vision-Only Real-Time Precise Underground Localisation for Autonomous Mining Vehicles
• Category-wise Attack: Transferable Adversarial Examples for Anchor Free Object Detection
• Gradient Centralization: A New Optimization Technique for Deep Neural Networks
• LANCE: Efficient Low-Precision Quantized Winograd Convolution for Neural Networks Based on Graphics Processing Units
• Towards more transferable adversarial attack in black-box manner
• Conceptual Text Region Network: Cognition-Inspired Accurate Scene Text Detection
• Learning Question-Guided Video Representation for Multi-Turn Video Question Answering
• Image Captioning with Unseen Objects
• Convolutional Auto-encoding of Sentence Topics for Image Paragraph Generation
• PCONV: The Missing but Desirable Sparsity in DNN Weight Pruning for Real-time Execution on Mobile Devices
• Saccader: Improving Accuracy of Hard Attention Models for Vision
• CityFlow: A City-Scale Benchmark for Multi-Target Multi-Camera Vehicle Tracking and Re-Identification
• Visual Question Answering based on Local-Scene-Aware Referring Expression Generation
• Training Compact CNNs for Image Classification using Dynamic-coded Filter Fusion
• Smart-Inspect: Micro Scale Localization and Classification of Smartphone Glass Defects for Industrial Automation
• The Devil is in Classification: A Simple Framework for Long-tail Object Detection and Instance Segmentation
• InfoDet: A Dataset for Infographic Element Detection
• How To Train Your Deep Multi-Object Tracker
• Real-time Traffic Accident Anticipation with Feature Reuse
• Self-Supervised Object Detection via Generative Image Synthesis
• A Software Architecture for Autonomous Vehicles: Team LRM-B Entry in the First CARLA Autonomous Driving Challenge
• An Accurate and Real-time Self-blast Glass Insulator Location Method Based On Faster R-CNN and U-net with Aerial Images
• MSDU-net: A Multi-Scale Dilated U-net for Blur Detection
• Towards Panoptic 3D Parsing for Single Image in the Wild
• Context-Gated Convolution
• A Simple yet Effective Baseline for Robust Deep Learning with Noisy Labels
• Structured Multimodal Attentions for TextVQA
• A Holistic Approach for Data-Driven Object Cutout
• ApproxDet: Content and Contention-Aware Approximate Object Detection for Mobiles
• Measuring Generalisation to Unseen Viewpoints, Articulations, Shapes and Objects for 3D Hand Pose Estimation under Hand-Object Interaction
• 3D Aggregated Faster R-CNN for General Lesion Detection
• Task-Aware Variational Adversarial Active Learning
• Extending Dataset Pruning to Object Detection: A Variance-based Approach
• What leads to generalization of object proposals?
• DDR-ID: Dual Deep Reconstruction Networks Based Image Decomposition for Anomaly Detection
• Adaptive Reconstruction Network for Weakly Supervised Referring Expression Grounding
• Generative Models as a Data Source for Multiview Representation Learning
• Distilling Pixel-Wise Feature Similarities for Semantic Segmentation
• Detailed Evaluation of Modern Machine Learning Approaches for Optic Plastics Sorting
• Boosting Weakly Supervised Object Detection with Progressive Knowledge Transfer
• AdvReal: Physical Adversarial Patch Generation Framework for Security Evaluation of Object Detection Systems
• SuperPure: Efficient Purification of Localized and Distributed Adversarial Patches via Super-Resolution GAN Models
• Self-Classification Enhancement and Correction for Weakly Supervised Object Detection
• FBNetV5: Neural Architecture Search for Multiple Tasks in One Run
• Forward and Backward Information Retention for Accurate Binary Neural Networks
• Object Instance Mining for Weakly Supervised Object Detection
• ULSD: Unified Line Segment Detection across Pinhole, Fisheye, and Spherical Cameras
• Grounding Chest X-Ray Visual Question Answering with Generated Radiology Reports
• Learning Predicates as Functions to Enable Few-shot Scene Graph Prediction
• DP-Image: Differential Privacy for Image Data in Feature Space
• Single Domain Generalization for Few-Shot Counting via Universal Representation Matching
• OBoW: Online Bag-of-Visual-Words Generation for Self-Supervised Learning
• SG-Net: Spatial Granularity Network for One-Stage Video Instance Segmentation
• AuxDet: Auxiliary Metadata Matters for Omni-Domain Infrared Small Target Detection
• Embodied Visual Recognition
• Deeply Aligned Adaptation for Cross-domain Object Detection
• InstructSAM: A Training-Free Framework for Instruction-Oriented Remote Sensing Object Recognition
• Multispectral Detection Transformer with Infrared-Centric Feature Fusion
• IA-MOT: Instance-Aware Multi-Object Tracking with Motion Consistency
• WiderPerson: A Diverse Dataset for Dense Pedestrian Detection in the Wild
• OSSDD - a New Open Dataset for Sentinel-1 Ship Detection
• DyFrDet: Towards Accurate Small Object Detection via Dynamic Frequency Suppression with Label Disambiguation
• Oral Imaging for Malocclusion Issues Assessments: OMNI Dataset, Deep Learning Baselines and Benchmarking
• Self-supervised Pre-training with Hard Examples Improves Visual Representations
• Slender Object Detection: Diagnoses and Improvements
• DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer
• Cyclic Co-Learning of Sounding Object Visual Grounding and Sound Separation
• Frustum Fusion: Pseudo-LiDAR and LiDAR Fusion for 3D Detection
• Training Deep Learning Based Denoisers without Ground Truth Data
• Learning to Fuse Asymmetric Feature Maps in Siamese Trackers
• A Normalized Gaussian Wasserstein Distance for Tiny Object Detection
• Robotic Monitoring of Colorimetric Leaf Sensors for Precision Agriculture
• Can artificial intelligence be integrated into pest monitoring schemes to help achieve sustainable agriculture? An entomological, management and computational perspective
• AppleGrowthVision: A large-scale stereo dataset for phenological analysis, fruit detection, and 3D reconstruction in apple orchards
• Chinese Street View Text: Large-scale Chinese Text Reading with Partially Supervised Learning
• Learning Person Re-identification Models from Videos with Weak Supervision
• FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking
• A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning
• VisualGPT: Data-efficient Adaptation of Pretrained Language Models for Image Captioning
• Semantic Dense Reconstruction with Consistent Scene Segments
• Automated Quality Evaluation of Cervical Cytopathology Whole Slide Images Based on Content Analysis
• Decoupling Classifier for Boosting Few-shot Object Detection and Instance Segmentation
• RepPoints: Point Set Representation for Object Detection
• Embodied Passive Aeroacoustic Perception Enables Relative Sensing and Pursuit Between Aerial Robots
• Student Helping Teacher: Teacher Evolution via Self-Knowledge Distillation
• Switching Loss for Generalized Nucleus Detection in Histopathology
• Few-Shot Object Detection with Attention-RPN and Multi-Relation Detector
• Jointly Cross- and Self-Modal Graph Attention Network for Query-Based Moment Localization
• Universal Domain Adaptation through Self Supervision
• MetaAlign: Coordinating Domain Alignment and Classification for Unsupervised Domain Adaptation
• FPAENet: Pneumonia Detection Network Based on Feature Pyramid Attention Enhancement
• Recent Advances in Object Detection in the Age of Deep Convolutional Neural Networks
• A Multi-task Convolutional Neural Network for Autonomous Robotic Grasping in Object Stacking Scenes
• AGI-Elo: How Far Are We From Mastering A Task?
• VisDA-2021 Competition Universal Domain Adaptation to Improve Performance on Out-of-Distribution Data
• DSIC: Dynamic Sample-Individualized Connector for Multi-Scale Object Detection
• Deformation Robust Roto-Scale-Translation Equivariant CNNs
• ProMi: An Efficient Prototype-Mixture Baseline for Few-Shot Segmentation with Bounding-Box Annotations
• Is Semantic SLAM Ready for Embedded Systems ? A Comparative Survey
• Quantized Neural Networks via -1, +1 Encoding Decomposition and Acceleration
• KGAlign: Joint Semantic-Structural Knowledge Encoding for Multimodal Fake News Detection
• A method for detecting text of arbitrary shapes in natural scenes that improves text spotting
• Clouds of Oriented Gradients for 3D Detection of Objects, Surfaces, and Indoor Scene Layouts
• FiGKD: Fine-Grained Knowledge Distillation via High-Frequency Detail Transfer
• FeDepth: Federated Learning for Depth Estimation under Robot Heterogeneity
• Localize to Classify and Classify to Localize: Mutual Guidance in Object Detection
• Unpaired Image Captioning via Scene Graph Alignments
• Interpretable Neural Computation for Real-World Compositional Visual Question Answering
• Bi-Dimensional Feature Alignment for Cross-Domain Object Detection
• Training Generative Adversarial Networks in One Stage
• Single View Physical Distance Estimation using Human Pose
• Experimental Study on Automatically Assembling Custom Catering Packages With a 3-DOF Delta Robot Using Deep Learning Methods
• Beyond Symmetric Fusion: Exploiting Task-Dependent Modality Strengths for RGB-Event Small Object Detection
• Backbone Can Not be Trained at Once: Rolling Back to Pre-trained Network for Person Re-Identification
• Pix2seq: A Language Modeling Framework for Object Detection
• Adversarial Semantic Contour for Object Detection
• Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detection
• A Serverless Cloud-Fog Platform for DNN-Based Video Analytics with Incremental Learning
• Contrastive Object-level Pre-training with Spatial Noise Curriculum Learning
• GeoMM: On Geodesic Perspective for Multi-modal Learning
• Activity Driven Weakly Supervised Object Detection
• Prime-Aware Adaptive Distillation
• A Light and Smart Wearable Platform with Multimodal Foundation Model for Enhanced Spatial Reasoning in People with Blindness and Low Vision
• Disambiguating Reference in Visually Grounded Dialogues through Joint Modeling of Textual and Multimodal Semantic Structures
• The Case for High-Accuracy Classification: Think Small, Think Many!
• Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey
• LIP: Learning Instance Propagation for Video Object Segmentation
• Mask R-CNN Based Object Detection for Intelligent Wireless Power Transfer
• UICopilot: Automating UI Synthesis via Hierarchical Code Generation from Webpage Designs
• OpenViDial 2.0: A Larger-Scale, Open-Domain Dialogue Generation Dataset with Visual Contexts
• Mixing Real and Synthetic Data to Enhance Neural Network Training -- A Review of Current Approaches
• INTERACTION Dataset: An INTERnational, Adversarial and Cooperative moTION Dataset in Interactive Driving Scenarios with Semantic Maps
• Learnable Histogram: Statistical Context Features for Deep Neural Networks
• Self-supervised Robust Object Detectors from Partially Labelled Datasets
• Dim and Small Target Detection for Drone Broadcast Frames Based on Time-Frequency Analysis
• HWNet v2: An Efficient Word Image Representation for Handwritten Documents
• Multi-step Reasoning via Recurrent Dual Attention for Visual Dialog
• FDIR: Harmonizing Fidelity and Human-Machine Preference in Lossy Compression Image Restoration
• Using Cross-Domain Detection Loss to Infer Multi-Scale Information for Improved Tiny Head Tracking
• End-to-end Autonomous Driving Perception with Sequential Latent Representation Learning
• MLMA-Net: multi-level multi-attentional learning for multi-label object detection in textile defect images
• Learning Informative Attention Weights for Person Re-Identification
• Temporal HeartNet: Towards Human-Level Automatic Analysis of Fetal Cardiac Screening Video
• OVC-Net: Object-Oriented Video Captioning with Temporal Graph and Detail Enhancement
• CenterFace: Joint Face Detection and Alignment Using Face as Point
• Long Activity Video Understanding using Functional Object-Oriented Network
• Learning Feature-to-Feature Translator by Alternating Back-Propagation for Generative Zero-Shot Learning
• FSD: Feature Skyscraper Detector for Stem End and Blossom End of Navel Orange
• Balance-Oriented Focal Loss with Linear Scheduling for Anchor Free Object Detection
• HMPNet: A Feature Aggregation Architecture for Maritime Object Detection from a Shipborne Perspective
• Object detection in adverse weather conditions for autonomous vehicles using Instruct Pix2Pix
• Simple multi-dataset detection
• Robustness Analysis against Adversarial Patch Attacks in Fully Unmanned Stores
• Self-supervised learning for autonomous vehicles perception: A conciliation between analytical and learning methods
• Cloud-based Image Classification Service Is Not Robust To Simple Transformations: A Forgotten Battlefield
• Unbiased Scene Graph Generation via Rich and Fair Semantic Extraction
• Deep Reinforcement Learning for Active Human Pose Estimation
• Attribute Aware Pooling for Pedestrian Attribute Recognition
• Custom Object Detection via Multi-Camera Self-Supervised Learning
• Scene-Aware Error Modeling of LiDAR/Visual Odometry for Fusion-based Vehicle Localization
• AdaScale: Towards Real-time Video Object Detection Using Adaptive Scaling
• SparseMeXT Unlocking the Potential of Sparse Representations for HD Map Construction
• Language-Driven Dual Style Mixing for Single-Domain Generalized Object Detection
• GradAug: A New Regularization Method for Deep Neural Networks
• Autonomous Robotic Pruning in Orchards and Vineyards: a Review
• LA-IMR: Latency-Aware, Predictive In-Memory Routing and Proactive Autoscaling for Tail-Latency-Sensitive Cloud Robotics
• Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds
• RiFCN: Recurrent Network in Fully Convolutional Network for Semantic Segmentation of High Resolution Remote Sensing Images
• AIBench: An Industry Standard Internet Service AI Benchmark Suite
• IQDet: Instance-wise Quality Distribution Sampling for Object Detection
• Differentiable NMS via Sinkhorn Matching for End-to-End Fabric Defect Detection
• Transformer-Based Dual-Optical Attention Fusion Crowd Head Point Counting and Localization Network
• YOPOv2-Tracker: An End-to-End Agile Tracking and Navigation Framework from Perception to Action
• Memorizing Comprehensively to Learn Adaptively: Unsupervised Cross-Domain Person Re-ID with Multi-level Memory
• Improve Object Detection by Data Enhancement based on Generative Adversarial Nets
• Geometric-Topological Perception and Motion Prior for Real-Time Satellite Video Object Tracking
• VALISENS: A Validated Innovative Multi-Sensor System for Cooperative Automated Driving
• Feature Representation Transferring to Lightweight Models via Perception Coherence
• Aggressive Perception-Aware Navigation using Deep Optical Flow Dynamics and PixelMPC
• AutoDNNchip: An Automated DNN Chip Predictor and Builder for Both FPGAs and ASICs
• OICSR: Out-In-Channel Sparsity Regularization for Compact Deep Neural Networks
• Deep Learning for Automatic Quality Grading of Mangoes: Methods and Insights
• SimMIL: A Universal Weakly Supervised Pre-Training Framework for Multi-Instance Learning in Whole Slide Pathology Images
• The Application of Deep Learning for Lymph Node Segmentation: A Systematic Review
• SADet: Learning An Efficient and Accurate Pedestrian Detector
• Training Binary Neural Networks through Learning with Noisy Supervision
• Dome-DETR: DETR with Density-Oriented Feature-Query Manipulation for Efficient Tiny Object Detection
• Automating Infrastructure Surveying: A Framework for Geometric Measurements and Compliance Assessment Using Point Cloud Data
• Progressive Localization Networks for Language-based Moment Localization
• Segmentation task for fashion and apparel
• Fashion Retrieval via Graph Reasoning Networks on a Similarity Pyramid
• Anchors Based Method for Fingertips Position Estimation from a Monocular RGB Image using Deep Neural Network
• NAS-FCOS: Efficient Search for Object Detection Architectures
• White Light Specular Reflection Data Augmentation for Deep Learning Polyp Detection
• PaniCar: Securing the Perception of Advanced Driving Assistance Systems Against Emergency Vehicle Lighting
• Visual Affordance Prediction: Survey and Reproducibility
• Dynamic Graph: Learning Instance-aware Connectivity for Neural Networks
• A Simple Detector with Frame Dynamics is a Strong Tracker
• Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model
• A Unified Hardware Architecture for Convolutions and Deconvolutions in CNN
• Spatio-temporal Tubelet Feature Aggregation and Object Linking in Videos
• Transforming faces into video stories -- VideoFace2.0
• QEBA: Query-Efficient Boundary-Based Blackbox Attack
• DeepVoting: A Robust and Explainable Deep Network for Semantic Part Detection under Partial Occlusion
• OMNIA Faster R-CNN: Detection in the wild through dataset merging and soft distillation
• Lattice Fusion Networks for Image Denoising
• Spatially Attentive Output Layer for Image Classification
• Road Damage Detection and Classification with Detectron2 and Faster R-CNN
• MA 3 : Model Agnostic Adversarial Augmentation for Few Shot learning
• OODTE: A Differential Testing Engine for the ONNX Optimizer
• Automated ARAT Scoring Using Multimodal Video Analysis, Multi-View Fusion, and Hierarchical Bayesian Models: A Clinician Study
• Focal-SAM: Focal Sharpness-Aware Minimization for Long-Tailed Classification
• End-to-end Flow Correlation Tracking with Spatial-temporal Attention
• Training Object Detectors from Few Weakly-Labeled and Many Unlabeled Images
• Localization Distillation for Dense Object Detection
• Farmland Parcel Delineation Using Spatio-temporal Convolutional Networks
• Lightweight Mask R-CNN for Long-Range Wireless Power Transfer Systems
• Ego-Exo: Transferring Visual Representations from Third-person to First-person Videos
• A Review on Object Pose Recovery: from 3D Bounding Box Detectors to Full 6D Pose Estimators
• Scan2Plan: Efficient Floorplan Generation from 3D Scans of Indoor Scenes
• Leveraging Localization for Multi-camera Association
• Fast Object Detection with Latticed Multi-Scale Feature Fusion
• Scale Matters: Temporal Scale Aggregation Network for Precise Action Localization in Untrimmed Videos
• Efficient Vision-based Vehicle Speed Estimation
• MoVie: Revisiting Modulated Convolutions for Visual Counting and Beyond
• The Newspaper Navigator Dataset: Extracting And Analyzing Visual Content from 16 Million Historic Newspaper Pages in Chronicling America
• Self-Adaptive Reconfigurable Arrays (SARA): Using ML to Assist Scaling GEMM Acceleration
• Global Collinearity-aware Polygonizer for Polygonal Building Mapping in Remote Sensing
• PREMISE: Matching-based Prediction for Accurate Review Recommendation
• Spatial Semantic Embedding Network: Fast 3D Instance Segmentation with Deep Metric Learning
• Deep Learning Meets SAR
• Learning from Web Data with Self-Organizing Memory Module
• Finding and Visualizing Weaknesses of Deep Reinforcement Learning Agents
• Recurrent Autoregressive Networks for Online Multi-Object Tracking
• Deep Multi-task Learning for Facial Expression Recognition and Synthesis Based on Selective Feature Sharing
• Scene Graph Generation for Better Image Captioning?
• Learning Cross-modal Context Graph for Visual Grounding
• Modularized Textual Grounding for Counterfactual Resilience
• Straight to Shapes: Real-time Detection of Encoded Shapes
• Dense Scene Multiple Object Tracking with Box-Plane Matching
• Knowledge Distillation By Sparse Representation Matching
• Self-Supervised Learning by Estimating Twin Class Distributions
• Visual Trajectory Prediction of Vessels for Inland Navigation
• Every Pixel Matters: Center-aware Feature Alignment for Domain Adaptive Object Detector
• On Robustness of Lane Detection Models to Physical-World Adversarial Attacks in Autonomous Driving
• E2E-VLP: End-to-End Vision-Language Pre-training Enhanced by Visual Learning
• MalariAI: A Label-Resilient Decoupled Framework for Annotation-Agnostic Cell Segmentation and Explainable Stage Classification in Dense Malaria Blood Smears
• A Possible Reason for why Data-Driven Beats Theory-Driven Computer Vision
• Colonoscopy Polyp Detection: Domain Adaptation From Medical Report Images to Real-time Videos
• Optimal Gradient Checkpoint Search for Arbitrary Computation Graphs
• Segmentation is All You Need
• Decoupling Localization and Classification in Single Shot Temporal Action Detection
• Live Reconstruction of Large-Scale Dynamic Outdoor Worlds
• Revisiting Locally Supervised Learning: an Alternative to End-to-end Training
• Multi Voxel-Point Neurons Convolution (MVPConv) for Fast and Accurate 3D Deep Learning
• mr2NST: Multi-Resolution and Multi-Reference Neural Style Transfer for Mammography
• Matching Images and Text with Multi-modal Tensor Fusion and Re-ranking
• Real-Time Grasping Strategies Using Event Camera
• A Computing Kernel for Network Binarization on PyTorch
• Scene-based Factored Attention for Image Captioning
• CMSN: Continuous Multi-stage Network and Variable Margin Cosine Loss for Temporal Action Proposal Generation
• Maria: A Visual Experience Powered Conversational Agent
• Zero-Shot Scene Graph Relation Prediction through Commonsense Knowledge Integration
• The Role of Artificial Intelligence in the SKA Era
• An Annotation Saved is an Annotation Earned: Using Fully Synthetic Training for Object Instance Detection
• Focal and efficient IOU loss for accurate bounding box regression
• Boosting Few-Shot Visual Learning With Self-Supervision
• Deep Texture-Aware Features for Camouflaged Object Detection
• An All-in-One Network for Dehazing and Beyond
• SynthText3D: Synthesizing Scene Text Images from 3D Virtual Worlds
• Trimmed Action Recognition, Dense-Captioning Events in Videos, and Spatio-temporal Action Localization with Focus on ActivityNet Challenge 2019
• Enabling Highly Efficient Capsule Networks Processing Through A PIM-Based Architecture Design
• Geometric Pose Affordance: 3D Human Pose with Scene Constraints
• Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstruction
• UAV maritime small object detection via frequency-spatial dual-domain synergistic perception and multi-granularity feature fusion
• Synthetic Data Generation and Adaption for Object Detection in Smart Vending Machines
• Automated Steel Bar Counting and Center Localization with Convolutional Neural Networks
• RFBTD: RFB Text Detector
• Chainer: A Deep Learning Framework for Accelerating the Research Cycle
• MADAN: Multi-source Adversarial Domain Aggregation Network for Domain Adaptation
• Visual Tracking via Reliable Memories
• ExpandNets: Linear Over-parameterization to Train Compact Convolutional Networks
• Adversarial Cross-Domain Action Recognition with Co-Attention
• CFUN: Combining Faster R-CNN and U-net Network for Efficient Whole Heart Segmentation
• Spiking Neural Network based Region Proposal Networks for Neuromorphic Vision Sensors
• Low-Latency Human Action Recognition with Weighted Multi-Region Convolutional Neural Network
• Fast Fine-Grained Image Classification via Weakly Supervised Discriminative Localization
• Jo-SRC: A Contrastive Approach for Combating Noisy Labels
• Horizontal-to-Vertical Video Conversion
• UFO: A UniFied TransfOrmer for Vision-Language Representation Learning
• Model Rubik's Cube: Twisting Resolution, Depth and Width for TinyNets
• Plumber: Diagnosing and Removing Performance Bottlenecks in Machine Learning Data Pipelines
• Large-Scale Generative Data-Free Distillation
• Stereo Frustums: A Siamese Pipeline for 3D Object Detection
• Robust Attentive Deep Neural Network for Exposing GAN-generated Faces
• Mi YouTube es Su YouTube? Analyzing the Cultures using YouTube Thumbnails of Popular Videos
• Generating Question Relevant Captions to Aid Visual Question Answering
• BUZz: BUffer Zones for defending adversarial examples in image classification
• Straight to Shapes++: Real-time Instance Segmentation Made More Accurate
• STELA: A Real-Time Scene Text Detector with Learned Anchor
• EfficientPose: An efficient, accurate and scalable end-to-end 6D multi object pose estimation approach
• Detecting and Mitigating Hateful Content in Multimodal Memes with Vision-Language Models
• M6: A Chinese Multimodal Pretrainer
• Beyond Human Performance: A Vision-Language Multi-Agent Approach for Quality Control in Pharmaceutical Manufacturing
• Smoothed Gaussian Mixture Models for Video Classification and Recommendation
• 1st place solution for AVA-Kinetics Crossover in AcitivityNet Challenge 2020
• Multi-Channel CNN-based Object Detection for Enhanced Situation Awareness
• Multiple Object Tracking by Flowing and Fusing
• Efficient Model Performance Estimation via Feature Histories
• Deep Lidar CNN to Understand the Dynamics of Moving Vehicles
• CGaP: Continuous Growth and Pruning for Efficient Deep Learning
• Conv-MPN: Convolutional Message Passing Neural Network for Structured Outdoor Architecture Reconstruction
• LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding
• Make Both Ends Meet: A Synergistic Optimization Infrared Small Target Detection with Streamlined Computational Overhead
• Zoomer: Adaptive Image Focus Optimization for Black-box MLLM
• Learning to Borrow Features for Improved Detection of Small Objects in Single-Shot Detectors
• XeMap: Contextual Referring in Large-Scale Remote Sensing Environments
• Cascade Detector Analysis and Application to Biomedical Microscopy
• RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder
• CMT: A Cascade MAR with Topology Predictor for Multimodal Conditional CAD Generation
• Style-Adaptive Detection Transformer for Single-Source Domain Generalized Object Detection
• Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection
• Pose Estimation for Non-Cooperative Rendezvous Using Neural Networks
• OG-HFYOLO :Orientation gradient guidance and heterogeneous feature fusion for deformation table cell instance segmentation
• T2ID-CAS: Diffusion Model and Class Aware Sampling to Mitigate Class Imbalance in Neck Ultrasound Anatomical Landmark Detection
• Foundation Model-Driven Framework for Human-Object Interaction Prediction with Segmentation Mask Integration
• DG-DETR: Toward Domain Generalized Detection Transformer
• GLACIER: Rethinking Mass Spectrum Prediction as an Object Detection Problem
• Toward Generalizable Whole Brain Representations with High-Resolution Light-Sheet Data
• A Multimodal Pipeline for Clinical Data Extraction: Applying Vision-Language Models to Scans of Transfusion Reaction Reports
• More Clear, More Flexible, More Precise: A Comprehensive Oriented Object Detection benchmark for UAV
• SynergyAmodal: Deocclude Anything with Text Control
• Crowd Detection Using Very-Fine-Resolution Satellite Imagery
• Improving Small Drone Detection Through Multi-Scale Processing and Data Augmentation
• Bridging Short- and Long-Term Dependencies: A CNN-Transformer Hybrid for Financial Time Series Forecasting
• Swapped Logit Distillation via Bi-level Teacher Alignment
• ODExAI: A Comprehensive Object Detection Explainable AI Evaluation
• CapsFake: A Multimodal Capsule Network for Detecting Instruction-Guided Deepfakes
• Transcending Dimensions using Generative AI: Real-Time 3D Model Generation in Augmented Reality
• Boosting Single-domain Generalized Object Detection via Vision-Language Knowledge Interaction
• AIBuildAI: An AI Agent for Automatically Building AI Models
• R-Sparse R-CNN: SAR Ship Detection Based on Background-Aware Sparse Learnable Proposals
• VISUALCENT: Visual Human Analysis using Dynamic Centroid Representation
• Dream-Box: Object-wise Outlier Generation for Out-of-Distribution Detection
• Examining the Impact of Optical Aberrations to Image Classification and Object Detection Models
• S3MOT: Monocular 3D Object Tracking with Selective State Space Model
• Multi-Agent Object Detection Framework Based on Raspberry Pi YOLO Detector and Slack-Ollama Natural Language Interface
• Achieving Human Parity on Visual Question Answering
• Traffic-Aware Multi-Camera Tracking of Vehicles Based on ReID and Camera Link Model
• WUTDet: A 100K-Scale Ship Detection Dataset and Benchmarks with Dense Small Objects
• Multi-Stream Attention Learning for Monocular Vehicle Velocity and Inter-Vehicle Distance Estimation
• RetinaTrack: Online Single Stage Joint Detection and Tracking
• Design and Interpretation of Universal Adversarial Patches in Face Detection
• Improved Selective Refinement Network for Face Detection
• DIVE: Inverting Conditional Diffusion Models for Discriminative Tasks
• CompConv: A Compact Convolution Module for Efficient Feature Learning
• CS-R-FCN: Cross-supervised Learning for Large-Scale Object Detection
• The Semantic Lifecycle in Embodied AI: Acquisition, Representation and Storage via Foundation Models
• AUTHENTICATION: Identifying Rare Failure Modes in Autonomous Vehicle Perception Systems using Adversarially Guided Diffusion Models
• A Decade of You Only Look Once (YOLO) for Object Detection: A Review
• FreqAdapt: Frequency-Adaptive Processing for RAW Object Detection
• An FPGA-Accelerated Design for Deep Learning Pedestrian Detection in Self-Driving Vehicles
• EHSOD: CAM-Guided End-to-end Hybrid-Supervised Object Detection with Cascade Refinement
• AIBench: An Agile Domain-specific Benchmarking Methodology and an AI Benchmark Suite
• Expressing Objects just like Words: Recurrent Visual Embedding for Image-Text Matching
• Learning Object Scale With Click Supervision for Object Detection
• Improving Open-World Object Localization by Discovering Background
• Cooperating RPN's Improve Few-Shot Object Detection
• Learning Temporal Pose Estimation from Sparsely-Labeled Videos
• ALET (Automated Labeling of Equipment and Tools): A Dataset, a Baseline and a Usecase for Tool Detection in the Wild
• A Review of 3D Object Detection with Vision-Language Models
• Multi-Grained Compositional Visual Clue Learning for Image Intent Recognition
• MASF-YOLO: An Improved YOLOv11 Network for Small Object Detection on Drone View
• Advances in Deep Learning for Hyperspectral Image Analysis—Addressing Challenges Arising in Practical Imaging Scenarios
• A Multimodal Hybrid Late-Cascade Fusion Network for Enhanced 3D Object Detection
• Fast Object Removal Attacks on Safety-Critical Video-based Perception Systems
• CIVIL: Causal and Intuitive Visual Imitation Learning
• ShuffleBlock: Shuffle to Regularize Deep Convolutional Neural Networks
• Identifying Lead Water Service Lines Using Ultrasonic Stress Wave Propagation and 1D-Convolutional Neural Network
• Learning to Recognize Actions on Objects in Egocentric Video With Attention Dictionaries
• GoDP: Globally Optimized Dual Pathway deep network architecture for facial landmark localization in-the-wild
• Robustness Emerges Early in Training Dynamics, but Is Not Preserved
• ColorFD: A Finite-Difference Guided Black-Box Physical Adversarial Attack for Remote Sensing Object Detection
• Object as Hotspots: An Anchor-Free 3D Object Detection Approach via Firing of Hotspots
• FUSEP: A Multi-Center Benchmark for Diverse Tasks in Early Pregnancy Fetal Ultrasound Screening
• Adversarially Robust Abductive Fusion of Pre-trained Transformer-based Perception Models
• Stampnet: Unsupervised Multi-Class Object Discovery
• SMOT: Single-Shot Multi Object Tracking
• Multi-Object Tracking with Siamese Track-RCNN
• Learning Fixation Point Strategy for Object Detection and Classification
• BorderDet: Border Feature for Dense Object Detection
• 3D-Aware Ellipse Prediction for Object-Based Camera Pose Estimation
• A Cost-Effective Person-Following System for Assistive Unmanned Vehicles with Deep Learning at the Edge
• Differentiable Neural Architecture Learning for Efficient Neural Network Design
• Enabling Incremental Knowledge Transfer for Object Detection at the Edge
• MDSSD: Multi-scale Deconvolutional Single Shot Detector for Small Objects
• SegICP: Integrated deep semantic segmentation and pose estimation
• Neural Architecture Search by Estimation of Network Structure Distributions
• Universal Lymph Node Detection in Multiparametric MRI with Selective Augmentation
• Active Perception for Ambiguous Objects Classification
• Online PCB Defect Detector On A New PCB Defect Dataset
• DPGP: A Hybrid 2D-3D Dual Path Potential Ghost Probe Zone Prediction Framework for Safe Autonomous Driving
• Think Hierarchically, Act Dynamically: Hierarchical Multi-modal Fusion and Reasoning for Vision-and-Language Navigation
• Multi-Task Learning With Coarse Priors for Robust Part-Aware Person Re-Identification
• Detecting and Tracking Communal Bird Roosts in Weather Radar Data
• GraftNet: An Engineering Implementation of CNN for Fine-grained Multi-label Task
• Cell Detection from Imperfect Annotation by Pseudo Label Selection Using P-classification
• FRDet: Balanced and Lightweight Object Detector based on Fire-Residual Modules for Embedded Processor of Autonomous Driving
• SA-Net: Robust State-Action Recognition for Learning from Observations
• IAN: Combining Generative Adversarial Networks for Imaginative Face Generation
• Collaboration Analysis Using Deep Learning
• MTSGL: Multi-Task Structure Guided Learning for Robust and Interpretable SAR Aircraft Recognition
• Scene-Aware Location Modeling for Data Augmentation in Automotive Object Detection
• Label-Attention Transformer with Geometrically Coherent Objects for Image Captioning
• A Single-Shot Arbitrarily-Shaped Text Detector based on Context Attended Multi-Task Learning
• An attention-fused network for semantic segmentation of very-high-resolution remote sensing imagery
• Deep learning in photoacoustic tomography: current approaches and future directions
• Statistical Management of the False Discovery Rate in Medical Instance Segmentation Based on Conformal Risk Control
• Relationship Oriented Affordance Learning through Manipulation Graph Construction
• Combining Deep Learning With Optical Coherence Tomography Imaging to Determine Scalp Hair and Follicle Counts
• Driving Scene Perception Network: Real-Time Joint Detection, Depth Estimation and Semantic Segmentation
• Unsupervised Object Detection with LiDAR Clues
• Structured Binary Neural Networks for Accurate Image Classification and Semantic Segmentation
• You Sense Only Once Beneath: Ultra-Light Real-Time Underwater Object Detection
• Measuring the Utilization of Public Open Spaces by Deep Learning: a Benchmark Study at the Detroit Riverfront
• Object-Based Visual Camera Pose Estimation From Ellipsoidal Model and 3D-Aware Ellipse Prediction
• Multimodal Perception for Goal-oriented Navigation: A Survey
• The Open Images Dataset V4
• Deep-learning-based image segmentation integrated with optical microscopy for automatically searching for two-dimensional materials
• SAGA: Semantic-Aware Gray color Augmentation for Visible-to-Thermal Domain Adaptation across Multi-View Drone and Ground-Based Vision Systems
• Context Aware Grounded Teacher for Source Free Object Detection
• SuoiAI: Building a Dataset for Aquatic Invertebrates in Vietnam
• An Efficient Aerial Image Detection with Variable Receptive Fields
• EmoSEM: Segment and Explain Emotion Stimuli in Visual Art
• Enhance Then Search: An Augmentation-Search Strategy with Foundation Models for Cross-Domain Few-Shot Object Detection
• Affinity LCFCN: Learning to Segment Fish with Weak Supervision
• Progressive Multi-Source Domain Adaptation for Personalized Facial Expression Recognition
• Task-based Loss Functions in Computer Vision: A Comprehensive Review
• Text Detection and Recognition in the Wild: A Review
• SoDA: Multi-Object Tracking with Soft Data Association
• FingerNet: Pushing The Limits of Fingerprint Recognition Using Convolutional Neural Network
• Slot Based Image Augmentation System for Object Detection
• STN-OCR: A single Neural Network for Text Detection and Text Recognition
• ISTD-YOLO: A Multi-Scale Lightweight High-Performance Infrared Small Target Detection Algorithm
• Single Document Image Highlight Removal via A Large-Scale Real-World Dataset and A Location-Aware Network
• Semi-supervised Active Learning for Instance Segmentation via Scoring Predictions
• A Deep Learning-Based FPGA Function Block Detection Method With Bitstream to Image Transformation
• Driver Behavior Analysis Using Lane Departure Detection Under Challenging Conditions
• Compile Scene Graphs with Reinforcement Learning
• Recovering hard-to-find object instances by sampling context-based object proposals
• A Unified Mixture-View Framework for Unsupervised Representation Learning
• HPC AI500: The Methodology, Tools, Roofline Performance Models, and Metrics for Benchmarking HPC AI Systems
• Background Learnable Cascade for Zero-Shot Object Detection
• Captioning Images with Novel Objects via Online Vocabulary Expansion
• Object-Aware Instance Labeling for Weakly Supervised Object Detection
• HMPE:HeatMap Embedding for Efficient Transformer-Based Small Object Detection
• Decoupled IoU Regression for Object Detection
• Autonomous and Cooperative Design of the Monitor Positions for a Team of UAVs to Maximize the Quantity and Quality of Detected Objects
• Condensing Two-stage Detection with Automatic Object Key Part Discovery
• Scaling Object Detection by Transferring Classification Weights
• Contralaterally Enhanced Networks for Thoracic Disease Detection
• Res2Net: A New Multi-Scale Backbone Architecture
• Denoising Large-Scale Image Captioning from Alt-text Data using Content\n Selection Models
• AsymmNet: Towards ultralight convolution neural networks using asymmetrical bottlenecks
• Team PFDet's Methods for Open Images Challenge 2019
• BoxCars: Improving Fine-Grained Recognition of Vehicles Using 3-D Bounding Boxes in Traffic Surveillance
• Deep learning techniques for in-crop weed recognition in large-scale grain production systems: a review
• On the detection-to-track association for online multi-object tracking
• BiDet: An Efficient Binarized Object Detector
• Pacemaker: Intermediate Teacher Knowledge Distillation For On-The-Fly Convolutional Neural Network
• A Joint Intensity-Neuromorphic Event Imaging System for Resource Constrained Devices
• Deep divergence-based approach to clustering
• Configurable 3D Scene Synthesis and 2D Image Rendering with Per-pixel Ground Truth Using Stochastic Grammars
• Growing status observation for oil palm trees using Unmanned Aerial Vehicle (UAV) images
• ASFD: Automatic and Scalable Face Detector
• SRG: Snippet Relatedness-Based Temporal Action Proposal Generator
• Learning from Web Data: the Benefit of Unsupervised Object Localization
• Local Aggregation for Unsupervised Learning of Visual Embeddings
• IvaNet: Learning to jointly detect and segment objets with the help of Local Top-Down Modules
• Learning a Layout Transfer Network for Context Aware Object Detection
• Frustum VoxNet for 3D object detection from RGB-D or Depth images
• Visual and Semantic Knowledge Transfer for Large Scale Semi-Supervised Object Detection
• Deep Learning for Scene Classification: A Survey
• SlowFast Networks for Video Recognition
• Learning from Counting: Leveraging Temporal Classification for Weakly Supervised Object Localization and Detection
• CogTree: Cognition Tree Loss for Unbiased Scene Graph Generation
• Context-Awareness and Interpretability of Rare Occurrences for Discovery and Formalization of Critical Failure Modes
• Weak Cube R-CNN: Weakly Supervised 3D Detection using only 2D Bounding Boxes
• Ellipse Detection and Localization with Applications to Knots in Sawn Lumber Images
• Deep learning‐based seabird detection in fisheries for seabird protection
• Structure-aware completion of photogrammetric meshes in urban road environment
• Collaborative Perception Datasets for Autonomous Driving: A Review
• Weak Supervision helps Emergence of Word-Object Alignment and improves Vision-Language Tasks
• Robo-SGG: Exploiting Layout-Oriented Normalization and Restitution Can Improve Robust Scene Graph Generation
• Quantum Computing Supported Adversarial Attack-Resilient Autonomous Vehicle Perception Module for Traffic Sign Classification
• Accurate Tracking of Arabidopsis Root Cortex Cell Nuclei in 3D Time-Lapse Microscopy Images Based on Genetic Algorithm
• Edge Approximation Text Detector
• Securing the Skies: A Comprehensive Survey on Anti-UAV Methods, Benchmarking, and Future Directions
• MEC-Patch: Visible-Infrared Cross-Modal Adversarial Attack Driven by Intrinsic Material Emissivity Laws
• Pose-aware instance segmentation framework from cone beam CT images for tooth segmentation
• Shape-Aware Oriented Bounding Box (OBB) to Horizontal Bounding Box (HBB) Conversion
• DocSAM: Unified Document Image Segmentation via Query Decomposition and Heterogeneous Mixed Learning
• Graph Network for Sign Language Tasks
• PatrolVision: Automated License Plate Recognition in the wild
• CFIS-YOLO: A Lightweight Multi-Scale Fusion Network for Edge-Deployable Wood Defect Detection
• YOLO-RS: Remote Sensing Enhanced Crop Detection Methods
• GATE3D: Generalized Attention-based Task-synergized Estimation in 3D*
• REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformers
• COUNTS: Benchmarking Object Detectors and Multimodal Large Language Models under Distribution Shifts
• Density-based Object Detection in Crowded Scenes
• Foundation Models for Remote Sensing: An Analysis of MLLMs for Object Localization
• Small Object Detection with YOLO: A Performance Analysis Across Model Versions and Hardware
• Improving Multimodal Hateful Meme Detection Exploiting LMM-Generated Knowledge
• A survey on recent trends in robotics and artificial intelligence in the furniture industry
• Using Vision Language Models for Safety Hazard Identification in Construction
• MBE-ARI: A Multimodal Dataset Mapping Bi-directional Engagement in Animal-Robot Interaction
• Automatic recognition of isolated piglet outliers based on multi-object tracking
• VLMT: Vision-Language Multimodal Transformer for Multimodal Multi-hop Question Answering
• Title block detection and information extraction for enhanced building drawings search
• Perception-R1: Pioneering Perception Policy with Reinforcement Learning
• AerialVG: A Challenging Benchmark for Aerial Visual Grounding by Exploring Positional Relations
• pychop: Emulating Low-Precision Arithmetic in Numerical Methods and Neural Networks
• RASMD: RGB And SWIR Multispectral Driving Dataset for Robust Perception in Adverse Conditions
• WS-DETR: Robust Water Surface Object Detection through Vision-Radar Fusion with Detection Transformer
• A Scale Invariant Flatness Measure for Deep Network Minima
• Visually Similar Pair Alignment for Robust Cross-Domain Object Detection
• Class Imbalance Correction for Improved Universal Lesion Detection and Tagging in CT
• D-Feat Occlusions: Diffusion Features for Robustness to Partial Visual Occlusions in Object Recognition
• Joint Learning of Neural Transfer and Architecture Adaptation for Image Recognition
• Don't Lag, RAG: Training-Free Adversarial Detection Using RAG
• GAMDTP: Dynamic Trajectory Prediction with Graph Attention Mamba Network
• Feedback-Enhanced Hallucination-Resistant Vision-Language Model for Real-Time Scene Understanding
• Strawberry Detection using Mixed Training on Simulated and Real Data
• DebGCD: Debiased Learning with Distribution Guidance for Generalized Category Discovery

Related

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Fast R-CNN
• Relief R-CNN : Utilizing Convolutional Features for Fast Object Detection
• R-FCN: Object Detection via Region-based Fully Convolutional Networks
• R-CNN minus R