Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting

2015/06/13 by Xingjian Shi, Shi, Xingjian, Zhourong Chen +12 · 490 citations
Computer Science · Earth and Planetary Sciences · Environmental Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Flood Risk Assessment and Management #Hydrological Forecasting Using AI #Meteorological Phenomena and Simulations #cs.CV

paper · pdf · doi:10.48550/arxiv.1506.04214

openalex publication_date 2015/06/13 · arxiv created 2015/09/19 · arxiv updated 2015/09/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

The goal of precipitation nowcasting is to predict the future rainfall intensity in a local region over a relatively short period of time. Very few previous studies have examined this crucial and challenging weather forecasting problem from the machine learning perspective. In this paper, we formulate precipitation nowcasting as a spatiotemporal sequence forecasting problem in which both the input and the prediction target are spatiotemporal sequences. By extending the fully connected LSTM (FC-LSTM) to have convolutional structures in both the input-to-state and state-to-state transitions, we propose the convolutional LSTM (ConvLSTM) and use it to build an end-to-end trainable model for the precipitation nowcasting problem. Experiments show that our ConvLSTM network captures spatiotemporal correlations better and consistently outperforms FC-LSTM and the state-of-the-art operational ROVER algorithm for precipitation nowcasting.

Citations

• On the difficulty of training Recurrent Neural Networks
• Sequence to Sequence Learning with Neural Networks

Cited by

• InterOCF: Spatio-Temporal 2D-3D Interaction for Camera-Only 4D Occupancy Forecasting
• LangPrecip: Language-Aware Multimodal Precipitation Nowcasting
• Neural ocean forecasting from sparse satellite-derived observations: a case-study for SSH dynamics and altimetry data
• Forecasting the Emergence and Evolution of Crash Hotspots: A Unified Deep Learning Framework for Proactive Traffic Safety
• Monitoring Post-Disaster Urban Recovery Using High-Resolution SAR Time Series and Unsupervised Learning: Evidence from the 2023 Türkiye-Syria Earthquake
• Physics-Informed CNN-LSTM for Street-Scale Urban Flood Prediction: Reconciling Aggregate Accuracy and Street-Level Plausibility
• RAPTOR: Real-Time High-Resolution UAV Video Prediction with Efficient Video Attention
• STLDM: Spatio-Temporal Latent Diffusion Model for Precipitation Nowcasting
• Effect of Activation Function and Model Optimizer on the Performance of Human Activity Recognition System Using Various Deep Learning Models
• Jensen-Shannon Divergence Message-Passing for Rich-Text Graph Representation Learning
• DK-STN: A Domain Knowledge Embedded Spatio-Temporal Network Model for MJO Forecast
• CRONOS: Continuous Time Reconstruction for 4D Medical Longitudinal Series
• CauSTream: Causal Spatio-Temporal Representation Learning for Streamflow Forecasting
• Tracking spatial temporal details in ultrasound long video via wavelet analysis and memory bank
• Multi-temporal Calving Front Segmentation
• Reconstruction as a Bridge for Event-Based Visual Question Answering
• REASAN: Learning Reactive Safe Navigation for Legged Robots
• A Diffusion-Based Framework for High-Resolution Precipitation Forecasting over CONUS
• A curated UK rain radar data set for training and benchmarking nowcasting models
• IE2Video: Adapting Pretrained Diffusion Models for Event-Based Video Reconstruction
• From Forecast to Action: A Deep Learning Model for Predicting Power Outages During Tropical Cyclones
• Cyclical Temporal Encoding and Hybrid Deep Ensembles for Multistep Energy Forecasting
• TabGRU: An Enhanced Design for Urban Rainfall Intensity Estimation Using Commercial Microwave Links
• S²-KD: Semantic-Spectral Knowledge Distillation Spatiotemporal Forecasting
• Deformation-aware Temporal Generation for Early Prediction of Alzheimers Disease
• Sparse-to-Field Reconstruction via Stochastic Neural Dynamic Mode Decomposition
• GazeProphetV2: Head-Movement-Based Gaze Prediction Enabling Efficient Foveated Rendering on Mobile VR
• Cloud4D: Estimating Cloud Properties at a High Spatial and Temporal Resolution
• Sequence-Adaptive Video Prediction in Continuous Streams using Diffusion Noise Optimization
• EvDiff: High Quality Video with an Event Camera
• Rectifying Distribution Shift in Cascaded Precipitation Nowcasting
• Fusing Biomechanical and Spatio-Temporal Features for Fall Prediction: Characterizing and Mitigating the Simulation-to-Reality Gap
• Real-time distortion prediction in metallic additive manufacturing via a physics-informed neural operator approach
• DINOv3 as a Frozen Encoder for CRPS-Oriented Probabilistic Rainfall Nowcasting
• Computationally-efficient deep learning models for nowcasting of precipitation: A solution for the Weather4cast 2025 challenge
• VitalBench: A Rigorous Multi-Center Benchmark for Long-Term Vital Sign Prediction in Intraoperative Care
• FlowCast: Advancing Precipitation Nowcasting with Conditional Flow Matching
• USF-Net: A Unified Spatiotemporal Fusion Network for Ground-Based Remote Sensing Cloud Image Sequence Extrapolation
• Fill the gaps: continuous in time interpolation of fluid dynamical simulations
• Temporal-Guided Visual Foundation Models for Event-Based Vision
• Precipitation nowcasting of satellite data using physically-aligned neural networks
• EventFlow: Real-Time Neuromorphic Event-Driven Classification of Two-Phase Boiling Flow Regimes
• Nowcast3D: Reliable precipitation nowcasting via gray-box learning
• Enhancing Heavy Rain Nowcasting with Multimodal Data: Integrating Radar and Satellite Observations
• Spiking Patches: Asynchronous, Sparse, and Efficient Tokens for Event Cameras
• Graph Network-based Structural Simulator: Graph Neural Networks for Structural Dynamics
• Leveraging an Atmospheric Foundational Model for Subregional Sea Surface Temperature Forecasting
• From Deterministic to Generative Deep Learning for Urban Air Quality Reconstruction from Sparse Observations
• Benchmarking ConvLSTM for One-Day-Ahead IMDAA Rainfall-Field Prediction across Four Indian Cities
• Skillful Precipitation Nowcasting using Deep Generative Models of Radar
• Learning Event-Based Motion Deblurring
• SMART: Simultaneous Multi-Agent Recurrent Trajectory Prediction
• A deep learning model for multi-modal spatio-temporal irradiance forecast
• Learning Various Length Dependence by Dual Recurrent Neural Networks
• Integrating Human Gaze into Attention for Egocentric Activity Recognition
• Adaptive Future Frame Prediction with Ensemble Network
• Wide and Narrow: Video Prediction from Context and Motion
• Spatial-Temporal Synchronous Graph Convolutional Networks: A New Framework for Spatial-Temporal Network Data Forecasting
• Feedback Attention for Cell Image Segmentation
• Stochastic Dynamics for Video Infilling
• Self-Supervised Visual Feature Learning With Deep Neural Networks: A Survey
• The Neural Painter: Multi-Turn Image Generation
• Learning to Deblur and Generate High Frame Rate Video with an Event Camera
• Efficient Spatialtemporal Context Modeling for Action Recognition
• Operational evaluation of data-driven forest fire forecasting models
• Scaling Autoregressive Video Models
• Temporal-Channel Transformer for 3D Lidar-Based Video Object Detection in Autonomous Driving
• Anomaly Detection in Video Sequences: A Benchmark and Computational Model
• Adaptive Spatio-Temporal Graphs with Self-Supervised Pretraining for Multi-Horizon Weather Forecasting
• Unlocking Out-of-Distribution Generalization in Dynamics through Physics-Guided Augmentation
• Learning from History: A Retrieval-Augmented Framework for Spatiotemporal Prediction
• Detecting Attended Visual Targets in Video
• Structured Temporal Causality for Interpretable Multivariate Time Series Anomaly Detection
• Single Image Reflection Removal through Cascaded Refinement
• Quantizing Space and Time: Fusing Time Series and Images for Earth Observation
• A Review of End-to-End Precipitation Prediction Using Remote Sensing Data: from Divination to Machine Learning
• Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting
• Estimating Continuum Robot Shape under External Loading using Spatiotemporal Neural Networks
• A Dilated Inception Network for Visual Saliency Prediction
• A Review of Deep Learning Methods for Irregularly Sampled Medical Time Series Data
• SolarBoost: Distributed Photovoltaic Power Forecasting Amid Time-varying Grid Capacity
• RadioMapMotion: A Dataset and Baseline for Proactive Spatio-Temporal Radio Environment Prediction
• Predicting Citywide Crowd Flows Using Deep Spatio-Temporal Residual Networks
• Future Frame Prediction for Robot-assisted Surgery
• SynCast: Synergizing Contradictions in Precipitation Nowcasting via Diffusion Sequential Preference Optimization
• A theoretical framework for self-supervised contrastive learning for continuous dependent data
• Deep Photovoltaic Nowcasting
• RainDiff: End-to-end Precipitation Nowcasting Via Token-wise Attention Diffusion
• Convolutional Attention in Betting Exchange Markets
• Convolution, attention and structure embedding
• DAWP: A framework for global observation forecasting via Data Assimilation and Weather Prediction in satellite observation space
• CSI Prediction Using Diffusion Models
• Interactive Atmospheric Composition Emulation for Next-Generation Earth System Models
• Are Video Models Emerging as Zero-Shot Learners and Reasoners in Medical Imaging?
• Learning Over Long Time Lags
• Video Abnormal Event Detection by Learning to Complete Visual Cloze Tests
• Multigrid Neural Memory
• Simple and Robust Forecasting of Spatiotemporally Correlated Small Earth Data with A Tabular Foundation Model
• An unsupervised long short-term memory neural network for event detection in cell videos
• Spatial Deconfounder: Interference-Aware Deconfounding for Spatial Causal Inference
• Learning Blind Video Temporal Consistency
• Climate Modeling with Neural Diffusion Equations
• SimCast: Enhancing Precipitation Nowcasting with Short-to-Long Term Knowledge Distillation
• Memory-Augmented Generative AI for Real-time Wireless Prediction in Dynamic Industrial Environments
• BlockGPT: Spatio-Temporal Modelling of Rainfall via Frame-Level Autoregression
• Foundation model of neural activity predicts response to new stimulus types
• Spatiotemporal Forecasting as Planning: A Model-Based Reinforcement Learning Approach with Generative World Models
• D-GAN: Deep Generative Adversarial Nets for Spatio-Temporal Prediction
• RainBench: Towards Global Precipitation Forecasting from Satellite Imagery
• Localizing Anomalies from Weakly-Labeled Videos
• Deep Learning for Physical Processes: Incorporating Prior Scientific Knowledge
• Machine Learning Workflows in Climate Modeling: Design Patterns and Insights from Case Studies
• Anatomy-DT: A Cross-Diffusion Digital Twin for Anatomical Evolution
• SoC-DT: Standard-of-Care Aligned Digital Twins for Patient-Specific Tumor Dynamics
• Deep learning model using continuous skin temperature data predicts labor onset
• A Video Machine Learning Framework for Spatiotemporal Analysis of Complex Urban Dynamics
• Deep Multi-Kernel Convolutional LSTM Networks and an Attention-Based Mechanism for Videos
• Motion-Nets: 6D Tracking of Unknown Objects in Unseen Environments using RGB
• MORPH: PDE Foundation Models with Arbitrary Data Modality
• Exploiting Spatio-Temporal Structure with Recurrent Winner-Take-All Networks
• Distributed Heteromodal Split Learning for Vision Aided mmWave Received Power Prediction
• Transformation-based Adversarial Video Prediction on Large-Scale Data
• Recurrence along Depth: Deep Convolutional Neural Networks with Recurrent Layer Aggregation
• Spontaneous symmetry breaking and Goldstone modes for deep information propagation
• Inception-inspired LSTM for Next-frame Video Prediction
• Enhanced prediction of vegetation responses to extreme drought using deep learning and Earth observation data
• Connectome-constrained networks predict neural activity across the fly visual system
• Machine learning spatio-temporal epidemiological model to evaluate Germany-county-level COVID-19 risk
• A Non-linear Function-on-Function Model for Regression with Time Series Data
• LORCK: Learnable Object-Resembling Convolution Kernels
• Climate-Adaptive and Cascade-Constrained Machine Learning Prediction for Sea Surface Height under Greenhouse Warming
• Time Series Forecasting Using a Hybrid Deep Learning Method: A Bi-LSTM Embedding Denoising Auto Encoder Transformer
• A Hybrid PCA-PR-Seq2Seq-Adam-LSTM Framework for Time-Series Power Outage Prediction
• A Comprehensive Survey of Machine Learning Based Localization with Wireless Signals
• Depth AnyEvent: A Cross-Modal Distillation Paradigm for Event-Based Monocular Depth Estimation
• Survey on semantic segmentation using deep learning techniques
• Modification method for single-stage object detectors that allows to\n exploit the temporal behaviour of a scene to improve detection accuracy
• Artificial neural networks ensemble methodology to predict significant wave height
• Deformable Kernel Convolutional Network for Video Extreme Super-Resolution
• B-TGAT: A Bi-directional Temporal Graph Attention Transformer for Clustering Multivariate Spatiotemporal Data
• DeepRain: ConvLSTM Network for Precipitation Prediction using Multichannel Radar Data
• CECT-Mamba: a Hierarchical Contrast-enhanced-aware Model for Pancreatic Tumor Subtyping from Multi-phase CECT
• Neural Predictive Belief Representations
• RealSmileNet: A Deep End-To-End Network for Spontaneous and Posed Smile Recognition
• An End-to-end Video Text Detector with Online Tracking
• Dynamic Adaptive Parsing of Temporal and Cross-Variable Patterns for Network State Classification
• Reconstructing High-fidelity Plasma Turbulence with Data-driven Tuning of Diffusion in Low Resolution Grids
• Deep Variational Luenberger-type Observer for Stochastic Video Prediction
• Hybrid Scheme of Kinematic Analysis and Lagrangian Koopman Operator Analysis for Short-term Precipitation Forecasting
• Stop using root-mean-square error as a precipitation target!
• Trellis Networks for Sequence Modeling
• Can deep learning beat numerical weather prediction?
• Sequential Neural Processes
• Accurate medium-range global weather forecasting with 3D neural networks
• Assessment of deep learning models integrated with weather and environmental variables for wildfire spread prediction and a case study of the 2023 Maui fires
• Deep Learning-Enhanced for Amine Emission Monitoring and Performance Analysis in Industrial Carbon Capture Plants
• Deep Complex Networks for Protocol-Agnostic Radio Frequency Device Fingerprinting in the Wild
• Exploiting temporal consistency for real-time video depth estimation
• SceneGen: Learning to Generate Realistic Traffic Scenes
• A review of radar-based nowcasting of precipitation and applicable machine learning techniques
• Topological Map Extraction from Overhead Images
• Mapping high-performance RNNs to in-memory neuromorphic chips
• Advanced Torrential Loss Function for Precipitation Forecasting
• Model Linkage Selection for Cooperative Learning
• Dynamic Kernel Distillation for Efficient Pose Estimation in Videos
• Temporal Flow Matching for Learning Spatio-Temporal Trajectories in 4D Longitudinal Medical Imaging
• Learning compact generalizable neural representations supporting perceptual grouping
• KFNet: Learning Temporal Camera Relocalization using Kalman Filtering
• A Lightweight Crowd Model for Robot Social Navigation
• STRATA-TS: Selective Knowledge Transfer for Urban Time Series Forecasting with Retrieval-Guided Reasoning
• A Comparative Study of Using Spatial-Temporal Graph Convolutional Networks for Predicting Availability in Bike Sharing Schemes
• Position-based Content Attention for Time Series Forecasting with Sequence-to-sequence RNNs
• Learning Synergistic Attention for Light Field Salient Object Detection
• Forecasting Smog Events Using ConvLSTM: A Spatio-Temporal Approach for Aerosol Index Prediction in South Asia
• GazeProphet: Software-Only Gaze Prediction for VR Foveated Rendering
• TENT: Tensorized Encoder Transformer for Temperature Forecasting
• Observation-guided Interpolation Using Graph Neural Networks for High-Resolution Nowcasting in Switzerland
• RegimeNAS: Regime-Aware Differentiable Architecture Search With Theoretical Guarantees for Financial Trading
• HyperTea: A Hypergraph-based Temporal Enhancement and Alignment Network for Moving Infrared Small Target Detection
• A Retrieval Augmented Spatio-Temporal Framework for Traffic Prediction
• A Structured Model For Action Detection
• Discrete Residual Flow for Probabilistic Pedestrian Behavior Prediction
• MoNet: Motion-based Point Cloud Prediction Network
• Use of 1D-CNN for input data size reduction of LSTM in Hourly Rainfall-Runoff modeling
• Load Forecasting on A Highly Sparse Electrical Load Dataset Using Gaussian Interpolation
• FairDRL-ST: Disentangled Representation Learning for Fair Spatio-Temporal Mobility Prediction
• Lightning Prediction under Uncertainty: DeepLight with Hazy Loss
• A Benchmark for Temporal Color Constancy
• Enhancing Spatiotemporal Networks with xLSTM: A Scalar LSTM Approach for Cellular Traffic Forecasting
• HiSTM: Hierarchical Spatiotemporal Mamba for Cellular Traffic Forecasting
• Effective Abstract Reasoning with Dual-Contrast Network
• RPCANet++: Deep Interpretable Robust PCA for Sparse Object Segmentation
• Predictive and Causal Implications of using Shapley Value for Model Interpretation
• Minimal Convolutional RNNs Accelerate Spatiotemporal Learning
• Temporally Identity-Aware SSD with Attentional LSTM
• FairST: Equitable Spatial and Temporal Demand Prediction for New Mobility Systems
• HyTIP: Hybrid Temporal Information Propagation for Masked Conditional Residual Video Coding
• Neuromorphic Computing with Multi-Frequency Oscillations: A Bio-Inspired Approach to Artificial Intelligence
• HyPCV-Former: Hyperbolic Spatio-Temporal Transformer for 3D Point Cloud Video Anomaly Detection
• Mamba-based Efficient Spatio-Frequency Motion Perception for Video Camouflaged Object Detection
• The Garden of Forking Paths: Towards Multi-Future Trajectory Prediction
• CS-SHRED: Enhancing SHRED for Robust Recovery of Spatiotemporal Dynamics
• TESPEC: Temporally-Enhanced Self-Supervised Pretraining for Event Cameras
• Deep Learning for Spatio-Temporal Data Mining: A Survey
• Convolutional Recurrent Reconstructive Network for Spatiotemporal Anomaly Detection in Solder Paste Inspection
• Complex Valued Gated Auto-encoder for Video Frame Prediction
• SPACE: A Simulator for Physical Interactions and Causal Learning in 3D Environments
• Learning Dynamical Systems from Partial Observations
• Counting People by Estimating People Flows
• Flow-Grounded Spatial-Temporal Video Prediction from Still Images
• Theoretical Investigation of Composite Neural Network
• Learning Monocular Visual Odometry via Self-Supervised Long-Term Modeling
• Multi-Grained Temporal-Spatial Graph Learning for Stable Traffic Flow Forecasting
• Unsupervised Multimodal Video-to-Video Translation via Self-Supervised Learning
• ARMA Nets: Expanding Receptive Field for Dense Prediction
• Textual Echo Cancellation
• Joint Spatial and Layer Attention for Convolutional Networks
• Automatic Video Object Segmentation via Motion-Appearance-Stream Fusion and Instance-aware Segmentation
• Light Future: Multimodal Action Frame Prediction via InstructPix2Pix
• Spatio-temporal Video Re-localization by Warp LSTM
• Non-Local ConvLSTM for Video Compression Artifact Reduction
• A Distributed SGD Algorithm with Global Sketching for Deep Learning Training Acceleration
• Mutual Suppression Network for Video Prediction using Disentangled Features
• CWY Parametrization: a Solution for Parallelized Optimization of Orthogonal and Stiefel Matrices
• Towards Rolling Shutter Correction and Deblurring in Dynamic Scenes
• FingerVision Tactile Sensor Design and Slip Detection Using Convolutional LSTM Network
• VideoLSTM Convolves, Attends and Flows for Action Recognition
• Assessing the Performance of Deep Learning Algorithms for Newsvendor Problem
• A Temporally-Aware Interpolation Network for Video Frame Inpainting
• Open-World Stereo Video Matching with Deep RNN
• Deep Learning Models for Predicting Wildfires from Historical Remote-Sensing Data
• Data-driven geophysical forecasting: Simple, low-cost, and accurate baselines with kernel methods
• Deep Learning Based Motion Planning For Autonomous Vehicle Using Spatiotemporal LSTM Network
• High Speed and High Dynamic Range Video with an Event Camera
• Cubic LSTMs for Video Prediction
• Recurrent Filter Learning for Visual Tracking
• Optimizing Drivers' Discount Order Acceptance Strategies: A Policy-Improved Deep Deterministic Policy Gradient Framework
• Learning to Forecast and Refine Residual Motion for Image-to-Video Generation
• Learned Video Compression via Joint Spatial-Temporal Correlation Exploration
• Spatio-Temporal Deep Learning Models for Tip Force Estimation During Needle Insertion
• Machine Learning for Spatiotemporal Sequence Forecasting: A Survey
• Recurrent Neural Network from Adder's Perspective: Carry-lookahead RNN
• CNN-based Realized Covariance Matrix Forecasting
• Hierarchical Opacity Propagation for Image Matting
• Can Active Memory Replace Attention?
• IoT Network Behavioral Fingerprint Inference with Limited Network Trace for Cyber Investigation: A Meta Learning Approach
• RGB-D-based Human Motion Recognition with Deep Learning: A Survey
• Recurrent U-net: Deep learning to predict daily summertime ozone in the United States
• Video Object Segmentation and Tracking: A Survey
• Predictive Process Model Monitoring using Recurrent Neural Networks
• Improving Sales Forecasting Accuracy: A Tensor Factorization Approach with Demand Awareness
• Atmos-Bench: 3D Atmospheric Structures for Climate Insight
• SimAug: Learning Robust Representations from Simulation for Trajectory Prediction
• SeqHAND:RGB-Sequence-Based 3D Hand Pose and Shape Estimation
• Effective Self-Attention-Based Deep Learning Model with Evolutionary Grid Search for Robust Wave Farm Energy Forecasting
• Deformable Dynamic Convolution for Accurate yet Efficient Spatio-Temporal Traffic Prediction
• BioAnalyst: A Foundation Model for Biodiversity
• Image Generation from Layout
• Convolutional LSTMs for Cloud-Robust Segmentation of Remote Sensing Imagery
• DIFFUMA: High-Fidelity Spatio-Temporal Video Prediction via Dual-Path Mamba and Diffusion Enhancement
• RecSal : Deep Recursive Supervision for Visual Saliency Prediction
• Learning Human-Object Interactions by Graph Parsing Neural Networks
• Probability Trajectory: One New Movement Description for Trajectory Prediction
• Hierarchical Interaction Summarization and Contrastive Prompting for Explainable Recommendations
• EmissionNet: Air Quality Pollution Forecasting for Agriculture
• Learning Semantic-Aware Dynamics for Video Prediction
• MotionRNN: A Flexible Model for Video Prediction with Spacetime-Varying Motions
• Forward Prediction for Physical Reasoning
• Referring Image Segmentation via Cross-Modal Progressive Comprehension
• LiDAR-based Online 3D Video Object Detection with Graph-based Message Passing and Spatiotemporal Transformer Attention
• Transformer with Koopman-Enhanced Graph Convolutional Network for Spatiotemporal Dynamics Forecasting
• Recurrent Neural Network for (Un-)supervised Learning of Monocular VideoVisual Odometry and Depth
• VORNet: Spatio-temporally Consistent Video Inpainting for Object Removal
• Visual Explanation using Attention Mechanism in Actor-Critic-based Deep Reinforcement Learning
• Neural Dynamic Modes: Computational Imaging of Dynamical Systems from Sparse Observations
• Cross-Modal Self-Attention Network for Referring Image Segmentation
• Robustifying Sequential Neural Processes
• CineMyoPS: Segmenting Myocardial Pathologies from Cine Cardiac MR
• Large Language Models for Crash Detection in Video: A Survey of Methods, Datasets, and Challenges
• Dance Dance ConvLSTM
• Anomaly Detection in Video Using Predictive Convolutional Long Short-Term Memory Networks
• PhyUnfold-Net: Advancing Remote Sensing Change Detection with Physics-Guided Deep Unfolding
• Learning to Detect Objects with a 1 Megapixel Event Camera
• Do Echo Top Heights Improve Deep Learning Nowcasts?
• KISS: Keeping It Simple for Scene Text Recognition
• Rethinking the Form of Latent States in Image Captioning
• Computing a human-like reaction time metric from stable recurrent vision models
• Extending Recurrent Neural Aligner for Streaming End-to-End Speech Recognition in Mandarin
• Frequency-Aligned Knowledge Distillation for Lightweight Spatiotemporal Forecasting
• Pedestrian Intention and Trajectory Prediction in Unstructured Traffic Using IDD-PeD
• Zooming Slow-Mo: Fast and Accurate One-Stage Space-Time Video Super-Resolution
• Storm Surge in Color: RGB-Encoded Physics-Aware Deep Learning for Storm Surge Forecasting
• Deep RNN Framework for Visual Sequential Applications
• Deep Learning for Optimal Deployment of UAVs with Visible Light Communications
• Composite Neural Network: Theory and Application to PM2.5 Prediction
• FAF: A Feature-Adaptive Framework for Few-Shot Time Series Forecasting
• ReCoGNet: Recurrent Context-Guided Network for 3D MRI Prostate Segmentation
• VideoPCDNet: Video Parsing and Prediction with Phase Correlation Networks
• Deep Uncertainty Quantification: A Machine Learning Approach for Weather Forecasting
• ST-GraphNet: A Spatio-Temporal Graph Neural Network for Understanding and Predicting Automated Vehicle Crash Severity
• Self-supervised Point Cloud Prediction Using 3D Spatio-temporal Convolutional Networks
• Physical-Virtual Collaboration Modeling for Intra-and Inter-Station Metro Ridership Prediction
• Residual Connection-Enhanced ConvLSTM for Lithium Dendrite Growth Prediction
• Lightweight Temporal Self-Attention for Classifying Satellite Image Time Series
• DerainCycleGAN: Rain Attentive CycleGAN for Single Image Deraining and Rainmaking
• HydroChronos: Forecasting Decades of Surface Water Change
• A Novel Video Salient Object Detection Method via Semi-supervised Motion Quality Perception
• Multi-Grained Spatio-temporal Modeling for Lip-reading
• MoNetV2: Enhanced Motion Network for Freehand 3D Ultrasound Reconstruction
• COME: Adding Scene-Centric Forecasting Control to Occupancy World Model
• Formant Tracking Using Dilated Convolutional Networks Through Dense Connection with Gating Mechanism
• FDNet: A Deep Learning Approach with Two Parallel Cross Encoding Pathways for Precipitation Nowcasting
• Latent Neural Differential Equations for Video Generation
• Application of LSTM architectures for next frame forecasting in Sentinel-1 images time series
• IAUnet: Global Context-Aware Feature Learning for Person Re-Identification
• Efficient Semantic Video Segmentation with Per-frame Inference
• Latent Representation Learning of Multi-scale Thermophysics: Application to Dynamics in Shocked Porous Energetic Material
• Hard Encoding of Physics for Learning Spatiotemporal Dynamics
• Real-Time Per-Garment Virtual Try-On with Temporal Consistency for Loose-Fitting Garments
• Long-term Forecasting using Higher Order Tensor RNNs
• Recursive Fusion and Deformable Spatiotemporal Attention for Video Compression Artifact Reduction
• DeepGLEAM: A hybrid mechanistic and deep learning model for COVID-19 forecasting
• PointRNN: Point Recurrent Neural Network for Moving Point Cloud Processing
• Beyond Tracking: Selecting Memory and Refining Poses for Deep Visual Odometry
• Multi-axis Attentive Prediction for Sparse EventData: An Application to Crime Prediction
• CCLSTM: Coupled Convolutional Long-Short Term Memory Network for Occupancy Flow Forecasting
• Implicit Neural Representation for Video Restoration
• Representing ill-known parts of a numerical model using a machine learning approach
• ConvTransformer: A Convolutional Transformer Network for Video Frame Synthesis
• CrevNet: Conditionally Reversible Video Prediction
• Temporally Folded Convolutional Neural Networks for Sequence Forecasting
• Improving Subseasonal Forecasting in the Western U.S. with Machine Learning
• Learning Scene Dynamics from Point Cloud Sequences
• A Sequence-to-Sequence ConvLSTM Approach for Leaf Area Index Forecasting over the South-Central United States
• Video Saliency Prediction Using Enhanced Spatiotemporal Alignment Network
• Pseudo grid-based physics-informed convolutional-recurrent network solving the integrable nonlinear lattice equations
• Multi-layer Feature Aggregation for Deep Scene Parsing Models
• WeatherBench: A benchmark dataset for data-driven weather forecasting
• FiniteNet: A Fully Convolutional LSTM Network Architecture for Time-Dependent Partial Differential Equations
• Joint Video Enhancement with Deblurring, Super-Resolution, and Frame Interpolation Network
• Progressive Image Deraining Networks: A Better and Simpler Baseline
• Unsupervised Motion Representation Learning with Capsule Autoencoders
• Learning Optical Flow Field via Neural Ordinary Differential Equation
• Efficient Egocentric Action Recognition with Multimodal Data
• PMNO: A novel physics guided multi-step neural operator predictor for partial differential equations
• Joint Resource Management for Energy-efficient UAV-assisted SWIPT-MEC: A Deep Reinforcement Learning Approach
• Pseudo-Labeling Driven Refinement of Benchmark Object Detection Datasets via Analysis of Learning Patterns
• Deep Learning Weather Models for Subregional Ocean Forecasting: A Case Study on the Canary Current Upwelling System
• One-Shot Imitation Filming of Human Motion Videos
• An Effective Dynamic Spatio-temporal Framework with Multi-Source Information for Traffic Prediction
• A neural network trained to predict future video frames mimics critical properties of biological neuronal responses and perception
• Finding a Needle in a Haystack: Tiny Flying Object Detection in 4K Videos using a Joint Detection-and-Tracking Approach
• Ocean-E2E: Hybrid Physics-Based and Data-Driven Global Forecasting of Extreme Marine Heatwaves with End-to-End Neural Assimilation
• Streaming Object Detection for 3-D Point Clouds
• Predicting the Dynamics of Complex System via Multiscale Diffusion Autoencoder
• Hierarchical Human Parsing with Typed Part-Relation Reasoning
• Exploiting deep learning in forecasting the occurrence of severe haze in Southeast Asia
• Differentiating Objects by Motion: Joint Detection and Tracking of Small Flying Objects
• ISTD-GCN: Iterative Spatial-Temporal Diffusion Graph Convolutional Network for Traffic Speed Forecasting
• Chasing Ghosts: Instruction Following as Bayesian State Tracking
• Predicting the Future with Transformational States
• Road Segmentation Using CNN with GRU
• Turb-L1: Achieving Long-term Turbulence Tracing By Tackling Spectral Bias
• Performance and Generalizability Impacts of Incorporating Location Encoders into Deep Learning for Dynamic PM2.5 Estimation
• Contextualized Spatial-Temporal Network for Taxi Origin-Destination Demand Prediction
• Trajectory Prediction using Equivariant Continuous Convolution
• Skilful nowcasting of extreme precipitation with NowcastNet
• Multi-task Learning For Joint Action and Gesture Recognition
• Hephaestus Minicubes: A Global, Multi-Modal Dataset for Volcanic Unrest Monitoring
• Interpretable Deep Feature Propagation for Early Action Recognition
• RWF-2000: An Open Large Scale Video Database for Violence Detection
• Causal Spatio-Temporal Prediction: An Effective and Efficient Multi-Modal Approach
• ExARNN: An Environment-Driven Adaptive RNN for Learning Non-Stationary Power Dynamics
• Sparse Diffusion Autoencoder for Test-time Adapting Prediction of Complex Systems
• Simultaneous Energy Harvesting and Gait Recognition using Piezoelectric Energy Harvester
• Convolutional LSTM Neural Networks for Modeling Wildland Fire Dynamics
• Vehicular Intrusion Detection System for Controller Area Network: A Comprehensive Survey and Evaluation
• Local Supports Global: Deep Camera Relocalization with Sequence Enhancement
• Foresight Diffusion: Improving Sampling Consistency in Predictive Diffusion Models
• Estimating Perceptual Attributes of Haptic Textures Using Visuo-Tactile Data
• An investigation of model-free planning
• MetaSTH-Sleep: Towards Effective Few-Shot Sleep Stage Classification for Health Management with Spatial-Temporal Hypergraph Enhanced Meta-Learning
• Disentangled Image Matting
• Physics-Guided Learning of Meteorological Dynamics for Weather Downscaling and Forecasting
• MGANet: A Robust Model for Quality Enhancement of Compressed Video
• Cloud Detection and Classification Algorithms for Himawari-8 Imager Measurements Based on Deep Learning
• Parrotron: An End-to-End Speech-to-Speech Conversion Model and its Applications to Hearing-Impaired Speech and Speech Separation
• Robust Pedestrian Attribute Recognition Using Group Sparsity for Occlusion Videos
• Gaze-Enhanced Multimodal Turn-Taking Prediction in Triadic Conversations
• Surrogate Modeling of 3D Rayleigh-Benard Convection with Equivariant Autoencoders
• Investigating Active Sampling for Hardness Classification with Vision-Based Tactile Sensors
• Tropical Cyclone Track Prediction with an Encoding-to-Forecasting Deep Learning Model
• Dynamic Spatial-Temporal Representation Learning for Traffic Flow Prediction
• ChromFound: Towards A Universal Foundation Model for Single-Cell Chromatin Accessibility Data
• msf-CNN: Patch-based Multi-Stage Fusion with Convolutional Neural Networks for TinyML
• Predicting Weather Uncertainty with Deep Convnets
• A Physics-Informed Spatiotemporal Deep Learning Framework for Turbulent Systems
• Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey
• How to use score-based diffusion in earth system science: A satellite nowcasting example
• LIP: Learning Instance Propagation for Video Object Segmentation
• MFogHub: Bridging Multi-Regional and Multi-Satellite Data for Global Marine Fog Detection and Forecasting
• Complete CVDL Methodology for Investigating Hydrodynamic Instabilities
• LCPNet: Latent Consistent Proximal Unfolding Network for Infrared Small Target Detection
• RainPro-8: An Efficient Deep Learning Model to Estimate Rainfall Probabilities Over 8 Hours
• Unsupervised learning of the brain connectivity dynamic using residual D-net
• Identifying critical transfer zones to coordinate transit with on-demand services using crowdsourced trajectory data
• Structural Causal Discovery and Predictive Sufficiency in High-Dimensional Dynamical Systems
• Video-based Person Re-Identification using Gated Convolutional Recurrent Neural Networks
• STAS: Adaptive Selecting Spatio-Temporal Deep Features for Improving Bias Correction on Precipitation
• Epileptic Seizure Classification with Symmetric and Hybrid Bilinear Models
• Augmenting correlation structures in spatial data using deep generative models
• High-fidelity Grain Growth Modeling: Leveraging Deep Learning for Fast Computations
• Deep Learning for Spatio-Temporal Data Mining: A Survey
• Early Estimation of User's Intention of Tele-Operation Using Object Affordance and Hand Motion in a Dual First-Person Vision
• Learning to infer in recurrent biological networks
• Time Series Analysis and Forecasting of COVID-19 Cases Using LSTM and ARIMA Models
• PeSANet: Physics-encoded Spectral Attention Network for Simulating PDE-Governed Complex Systems
• Finite Volume Neural Network: Modeling Subsurface Contaminant Transport
• Instance-wise Graph-based Framework for Multivariate Time Series Forecasting
• Global Collinearity-aware Polygonizer for Polygonal Building Mapping in Remote Sensing
• Efficient and Phase-aware Video Super-resolution for Cardiac MRI
• Deep Sequence Learning for Accurate Gestational Age Estimation from a $25 Doppler Device
• Gaussian Process Nowcasting: Application to COVID-19 Mortality Reporting
• Light Field Saliency Detection with Dual Local Graph Learning andReciprocative Guidance
• Sat-JEPA-Diff: Bridging Self-Supervised Learning and Generative Diffusion for Remote Sensing
• Feature Boosting Network For 3D Pose Estimation
• Precipitation Nowcasting with Star-Bridge Networks
• A study of Chinese regional hierarchical structure based on surnames
• Deep Video Super-Resolution Network Using Dynamic Upsampling Filters Without Explicit Motion Compensation
• Model predictive control design for dynamical systems learned by Long Short-Term Memory Networks
• A Distributed Neural Network Architecture for Robust Non-Linear Spatio-Temporal Prediction
• Deep Learning-based Segmentation of Cerebral Aneurysms in 3D TOF-MRA using Coarse-to-Fine Framework
• DiffusionNet: Accelerating the solution of Time-Dependent partial differential equations using deep learning
• Recurrent Back-Projection Network for Video Super-Resolution
• Understanding Road Layout from Videos as a Whole
• Simple vs complex temporal recurrences for video saliency prediction
• Multidimensional precipitation index prediction based on CNN-LSTM hybrid framework
• Axial-UNet: A Neural Weather Model for Precipitation Nowcasting
• VTire: A Bimodal Visuotactile Tire with High-Resolution Sensing Capability
• SSA-UNet: Advanced Precipitation Nowcasting via Channel Shuffling
• On the Role of Computation in Reinforcement Learning
• Cine Cardiac MRI Motion Artifact Reduction Using a Recurrent Neural Network
• Stochastic Adversarial Video Prediction
• Coupled Recurrent Network (CRN)
• IntrinSeqNet: Learning to Estimate the Reflectance from Varying Illumination
• Disease Detection in Weakly Annotated Volumetric Medical Images using a Convolutional LSTM Network
• Enhancing sea surface salinity short-term prediction using physically informed deep learning
• HybridNet: Integrating Model-based and Data-driven Learning to Predict Evolution of Dynamical Systems
• Predicting Citywide Crowd Flows in Irregular Regions Using Multi-View Graph Convolutional Networks
• Learning to Recognize Actions on Objects in Egocentric Video With Attention Dictionaries
• Rethinking multiscale cardiac electrophysiology with machine learning and predictive modelling
• Bridging the Gap Between Training and Inference for Spatio-Temporal Forecasting
• Stable Attention Response for Reliable Precipitation Nowcasting
• ECGDeDRDNet: A deep learning-based method for Electrocardiogram noise removal using a double recurrent dense network
• One shot PACS: Patient specific Anatomic Context and Shape prior aware recurrent registration-segmentation of longitudinal thoracic cone beam CTs
• Deep learning in photoacoustic tomography: current approaches and future directions
• Monitoring Driving in a Monotonous Environment: Classification and Recognition of Driving Fatigue Based on Long Short-Term Memory Network
• A novel hybrid neural network of fluid-structure interaction prediction for two cylinders in tandem arrangement
• How to systematically develop an effective AI-based bias correction model?
• Lighting Enhancement Aids Reconstruction of Colonoscopic Surfaces
• Predicting Future Opioid Incidences Today
• Rethinking Traffic Flow Forecasting: From Transition to Generatation
• Deep Convolution for Irregularly Sampled Temporal Point Clouds
• Energy-Aware Pattern Disentanglement: A Generalizable Pattern Assisted Architecture for Multi-task Time Series Analysis
• Urban Anomaly Analytics: Description, Detection, and Prediction
• CLCI-Net: Cross-Level Fusion and Context Inference Networks for Lesion Segmentation of Chronic Stroke
• Application of Multi-channel 3D-cube Successive Convolution Network for Convective Storm Nowcasting
• RiWNet: A moving object instance segmentation Network being Robust in adverse Weather conditions
• Complex sequential understanding through the awareness of spatial and temporal concepts
• Exploit Camera Raw Data for Video Super- Resolution via Hidden Markov Model Inference
• Recurrent Existence Determination Through Policy Optimization
• Spatial-temporal Conv-sequence Learning with Accident Encoding for Traffic Flow Prediction
• Parallel Multi-Graph Convolution Network For Metro Passenger Volume Prediction
• Learning from Counting: Leveraging Temporal Classification for Weakly Supervised Object Localization and Detection
• Planning Robot Motion using Deep Visual Prediction
• Recurrent neural network-based volumetric fluorescence microscopy
• Prediction Of Temperature And Rainfall In Bangladesh Using Long Short Term Memory Recurrent Neural Networks
• Multi-resolution Score-Based Variational Graphical Diffusion for Causal Disaster System Modeling and Inference
• EMF: Event Meta Formers for Event-based Real-time Traffic Object Detection
• Beyond Static Forecasting: Unleashing the Power of World Models for Mobile Traffic Extrapolation
• Physical Scales Matter: The Role of Receptive Fields and Advection in Satellite-Based Thunderstorm Nowcasting with Convolutional Neural Networks
• Predicting the critical behavior of complex dynamic systems via learning the governing mechanisms
• DG-STMTL: A Novel Graph Convolutional Network for Multi-Task Spatio-Temporal Traffic Forecasting
• Deep Learning Meets Teleconnections: Improving S2S Predictions for European Winter Weather
• SRVP: Strong Recollection Video Prediction Model Using Attention-Based Spatiotemporal Correlation Fusion
• AI-Driven Consensus: Modeling Multi-Agent Networks with Long-Range Interactions through path-Laplacian Matrices
• LIAF-Net: Leaky Integrate and Analog Fire Network for Lightweight and Efficient Spatiotemporal Information Processing
• PINP: Physics-Informed Neural Predictor with latent estimation of fluid flows
• Towards Efficient Real-Time Video Motion Transfer via Generative Time Series Modeling
• Biomechanical Constraints Assimilation in Deep-Learning Image Registration: Application to sliding and locally rigid deformations

Related

• Precipitation Nowcasting: Leveraging bidirectional LSTM and 1D CNN
• Deep Learning for Precipitation Nowcasting: A Benchmark and A New Model
• Computationally-efficient deep learning models for nowcasting of precipitation: A solution for the Weather4cast 2025 challenge
• DeepRain: ConvLSTM Network for Precipitation Prediction using Multichannel Radar Data
• Multi-Source Temporal Attention Network for Precipitation Nowcasting