Contrastive Multiview Coding

2020/01/01 by Yonglong Tian, Dilip Krishnan, Phillip Isola · 1,788 citations
Computer Science · Mathematics · #Advanced Data Compression Techniques #Advanced Vision and Imaging #Artificial intelligence #Coding (social sciences) #Computer science #Computer vision #Mathematics #Video Coding and Compression Technologies

paper · doi:10.1007/978-3-030-58621-8_45

published in Lecture notes in computer science, 776-794 (Springer Science+Business Media)

crossref issued 2020/01/01 · crossref published 2020/01/01 · crossref published-print 2020/01/01 · openalex publication_date 2020/01/01 · crossref created 2020/11/26 · crossref published-online 2020/11/27 · crossref deposited 2024/11/26 · openalex created_date 2025/10/10 · crossref indexed 2026/07/29 · openalex updated_date 2026/08/04

Citations

• UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
• Unsupervised Visual Representation Learning by Context Prediction
• Separate visual pathways for perception and action
• The Development of Embodied Cognition: Six Lessons from Babies
• Two-Stream Convolutional Networks for Action Recognition in Videos
• ImageNet classification with deep convolutional neural networks
• Representation Learning: A Review and New Perspectives
• Pixel Recurrent Neural Networks
• Adversarial Feature Learning
• Unsupervised Representation Learning by Predicting Image Rotations
• Generating Videos with Scene Dynamics
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Momentum Contrast for Unsupervised Visual Representation Learning

Cited by

• Learning from Temporal Gradient for Semi-supervised Action Recognition
• Latent Structure Mining With Contrastive Modality Fusion for Multimedia Recommendation
• PGL: Prior-Guided Local Self-supervised Learning for 3D Medical Image Segmentation
• Self-supervised Heterogeneous Graph Neural Network with Co-contrastive Learning
• Contrastive Feature Loss for Image Prediction
• Distilling Audio-Visual Knowledge by Compositional Contrastive Learning
• Self-Supervised Visual Feature Learning With Deep Neural Networks: A Survey
• CLDA: Contrastive Learning for Semi-Supervised Domain Adaptation
• Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts
• T-REGS: Minimum Spanning Tree Regularization for Self-Supervised Learning
• Learning Without Augmenting: Unsupervised Time Series Representation Learning via Frame Projections
• Contrastive Learning for Many-to-many Multilingual Neural Machine Translation
• Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID
• Exploring Structural Degradation in Dense Representations for Self-supervised Learning
• CoDS: Enhancing Collaborative Perception in Heterogeneous Scenarios via Domain Separation
• Your VAR Model is Secretly an Efficient and Explainable Generative Classifier
• Source-Free Object Detection with Detection Transformer
• VOLTAGE: A Versatile Contrastive Learning based OCR Methodology for ultra low-resource scripts through Auto Glyph Feature Extraction
• FairContrast: Enhancing Fairness through Contrastive learning and Customized Augmenting Methods on Tabular Data
• Self-Supervised Learning by Cross-Modal Audio-Video Clustering
• Self-Supervised Representation Learning as Mutual Information Maximization
• Momentum Contrast for Unsupervised Visual Representation Learning
• InfMasking: Unleashing Synergistic Information by Contrastive Multimodal Interactions
• Disentanglement of Variations with Multimodal Generative Modeling
• When Does Self-supervision Improve Few-shot Learning?
• EqCo: Equivalent Rules for Self-supervised Contrastive Learning
• Enriching Knowledge Distillation with Intra-Class Contrastive Learning
• Temporal vs. Spatial: Comparing DINOv3 and V-JEPA2 Feature Representations for Video Action Analysis
• DivCo: Diverse Conditional Image Synthesis via Contrastive Generative Adversarial Network
• Refining Pseudo Labels with Clustering Consensus over Generations for Unsupervised Object Re-identification
• A Validation Strategy for Deep Learning Models: Evaluating and Enhancing Robustness
• Global Minimizers of Sigmoid Contrastive Loss
• PRISM: Precision-Recall Informed Data-Free Knowledge Distillation via Generative Diffusion
• Scaling Law for Recommendation Models: Towards General-purpose User Representations
• Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification
• Improving Weakly Supervised Visual Grounding by Contrastive Knowledge Distillation
• Learning Representations from Audio-Visual Spatial Alignment
• VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text
• Contrastive Learning for Fair Representations
• Contrastive Learning with Stronger Augmentations
• Maximally Useful and Minimally Redundant: The Key to Self Supervised Learning for Imbalanced Data
• Exploring Simple Siamese Representation Learning
• Video-Based MPAA Rating Prediction: An Attention-Driven Hybrid Architecture Using Contrastive Learning
• Dimensionally Reduced Open-World Clustering: DROWCULA
• Foley Music: Learning to Generate Music from Videos
• Self-Supervised Learning via multi-Transformation Classification for Action Recognition
• RegionCL: Can Simple Region Swapping Contribute to Contrastive Learning?
• Dual-Model Weight Selection and Self-Knowledge Distillation for Medical Image Classification
• Spatiotemporal Contrastive Video Representation Learning
• Whitening for Self-Supervised Representation Learning
• Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style
• Contrastive Representation Learning with Trainable Augmentation Channel
• ITL-LIME: Instance-Based Transfer Learning for Enhancing Local Explanations in Low-Resource Data Settings
• NeMo: A Neuron-Level Modularizing-While-Training Approach for Decomposing DNN Models
• Borrowing From the Future: Enhancing Early Risk Assessment through Contrastive Learning
• Learning Robust Intervention Representations with Delta Embeddings
• Decoupled Contrastive Learning for Federated Learning
• Heterogeneous Contrastive Learning
• Multi-view Contrastive Learning for Online Knowledge Distillation
• Patch Pruning Strategy Based on Robust Statistical Measures of Attention Weight Diversity in Vision Transformers
• PreViTS: Contrastive Pretraining with Video Tracking Supervision
• Self-Supervised Pretraining and Controlled Augmentation Improve Rare Wildlife Recognition in UAV Images
• A Comprehensive Survey on Source-Free Domain Adaptation
• Improving Contrastive Learning by Visualizing Feature Transformation
• Unsupervised Disentanglement without Autoencoding: Pitfalls and Future Directions
• MixSiam: A Mixture-based Approach to Self-supervised Representation Learning
• Not All Negatives are Equal: Label-Aware Contrastive Loss for Fine-grained Text Classification
• Advancing Wildfire Risk Prediction via Morphology-Aware Curriculum Contrastive Learning
• DASViT: Differentiable Architecture Search for Vision Transformer
• On the Similarities of Embeddings in Contrastive Learning
• MvSR-NAT: Multi-view Subset Regularization for Non-Autoregressive Machine Translation
• The Impact of Spatiotemporal Augmentations on Self-Supervised Audiovisual Representation Learning
• Learning Cross-modal Contrastive Features for Video Domain Adaptation
• Robust Contrastive Learning Using Negative Samples with Diminished Semantics
• Ambiguity-Aware and High-Order Relation Learning for Multi-Grained Image-Text Matching
• A Principled Framework for Multi-View Contrastive Learning
• Divergence-Based Similarity Function for Multi-View Contrastive Learning
• Subject Invariant Contrastive Learning for Human Activity Recognition
• i-Mix: A Domain-Agnostic Strategy for Contrastive Representation Learning
• Leveraging the Structure of Medical Data for Improved Representation Learning
• Unsupervised Representation Learning for Binary Networks by Joint Classifier Learning
• A Theoretical Formulation on the Use of Multiple Positive Views in Contrastive Learning
• THAT: Two Head Adversarial Training for Improving Robustness at Scale
• Enhancing VICReg: Random-Walk Pairing for Improved Generalization and Better Global Semantics Capturing
• ASCNet: Self-supervised Video Representation Learning with Appearance-Speed Consistency
• Unsupervised Contrastive Learning Using Out-Of-Distribution Data for Long-Tailed Dataset
• Long-Tailed Learning for Generalized Category Discovery
• PROTOCOL: Partial Optimal Transport-enhanced Contrastive Learning for Imbalanced Multi-view Clustering
• Aligning Multimodal Representations through an Information Bottleneck
• Merging and Disentangling Views in Visual Reinforcement Learning for Robotic Manipulation
• Self-Supervised Contrastive Learning is Approximately Supervised Contrastive Learning
• DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representations
• Generalized Category Discovery via Reciprocal Learning and Class-Wise Distribution Regularization
• Self-Supervised Spatial Correspondence Across Modalities
• RadBERT-CL: Factually-Aware Contrastive Learning For Radiology Report Classification
• Adversarial Training with Contrastive Learning in NLP
• Online Unsupervised Learning of Visual Representations and Categories
• Jigsaw Clustering for Unsupervised Visual Representation Learning
• Balancing Robustness and Sensitivity using Feature Contrastive Learning
• Automatically Identify and Rectify: Robust Deep Contrastive Multi-view Clustering in Noisy Scenarios
• Multimodal Federated Learning: A Survey through the Lens of Different FL Paradigms
• A Contrastive Learning Foundation Model Based on Perfectly Aligned Sample Pairs for Remote Sensing Images
• Guiding the Experts: Semantic Priors for Efficient and Focused MoE Routing
• SPAR: Self-supervised Placement-Aware Representation Learning for Distributed Sensing
• On Learning Universal Representations Across Languages
• An Empirical Study of Graph Contrastive Learning
• OBoW: Online Bag-of-Visual-Words Generation for Self-Supervised Learning
• Learning View-Disentangled Human Pose Representation by Contrastive Cross-View Mutual Information Maximization
• A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning
• Contrastive Consolidation of Top-Down Modulations Achieves Sparsely Supervised Continual Learning
• Collaborative Unlabeled Data Optimization
• Multi-modal contrastive learning adapts to intrinsic dimensions of shared latent variables
• KFCNet: Knowledge Filtering and Contrastive Learning Network for Generative Commonsense Reasoning
• Understanding and Improving Robustness of Vision Transformers through Patch-based Negative Augmentation
• The Power of Contrast for Feature Learning: A Theoretical Analysis
• RayZer: A Self-supervised Large View Synthesis Model
• Layer-specific lipschitz modulation for fault-tolerant multimodal representation learning
• Zero-Flow Encoders
• Adept: Annotation-Denoising Auxiliary Tasks with Discrete Cosine Transform Map and Keypoint for Human-Centric Pretraining
• Examining the Impact of Optical Aberrations to Image Classification and Object Detection Models
• C²MOE: Consistency and Complementarity-guided Mixture of Experts for Incomplete Multimodal Emotion Learning
• I-Con: A Unifying Framework for Representation Learning
• Full-waveform variational inference with full common-image gathers and diffusion network
• Self-Supervised Change Detection in Multiview Remote Sensing Images
• Unsupervised Deep Representation Learning and Few-Shot Classification of PolSAR Images
• Beyond 3DMM: Learning to Capture High-Fidelity 3D Face Shape
• FedEPA: Enhancing Personalization and Modality Alignment in Multimodal Federated Learning
• Hypergraph Vision Transformers: Images are More than Nodes, More than Edges