Video self-supervised learning
Video SSL, VideoSSL and SSL video research refer to self-supervised learning for video, including self-supervised video representation learning, video representation pretraining and masked video modeling.
Research collection · maintained with the survey
Video SSL & VideoSSL Papers by Year & Venue
A researcher-maintained catalog of video self-supervised learning and self-supervised video representation learning papers, organized by verified publication year and latest confirmed venue.
Collection snapshot
Repository statistics
Public counts are generated from verified publication years and venues.
282representation-learning papers
2016–2026years covered
64normalized venues
Research coverage
Video SSL terminology, datasets and venues
The catalog keeps per-paper cards focused on year and venue while this overview explains the broader research scope.
Video understanding datasets
The collection covers research using UCF101, HMDB51, Kinetics-400, Kinetics-600, Kinetics-700, Something-Something V1, Something-Something V2, Diving48, EPIC-KITCHENS, AVA, FineGYM, Charades, Ego4D and related datasets.
Conferences and journals
Verified venues include CVPR, ICCV, ECCV, NeurIPS, ICLR, AAAI, WACV, ACM Multimedia, specialist workshops and peer-reviewed journals, with arXiv retained only when no later publication is confirmed.
Interactive research index
Browse the paper collection
Filter the catalog instead of scrolling through a single long bibliography. The GitHub README keeps the traditional year-by-year list.
2026CVPR
Progressive Mask Distillation for Self-supervised Video Representation
2026CVPR
TrackMAE: Video Representation Learning via Track Mask and Predict
2026arXiv / Preprint
V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning
2026CVPR
From Static to Dynamic: Exploring Self-supervised Image-to-Video Representation Transfer Learning
2026arXiv / Preprint
The TIME Machine: On The Power of Motion for Efficient Perception
2026arXiv / Preprint
TrAction: Action Recognition with Sparse Trajectories
2026arXiv / Preprint
OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence
2026arXiv / Preprint
Factorized Latent Dynamics for Video JEPA: An Empirical Study of Auxiliary Objectives
2026arXiv / Preprint
Self-Supervised Learning of Structured Dynamics from Videos
2026arXiv / Preprint
Depth-Wise Representation Development Under Blockwise Self-Supervised Learning for Video Vision Transformers
2026Engineering Applications of Artificial Intelligence
Beyond reconstruction: Enhancing masked autoencoders with contrastive learning for video representation learning
2026ECCV
Structured-Noise Masked Modeling for Video, Audio and Beyond
2026ICLR
Rethinking JEPA: Compute-Efficient Video SSL with Frozen Teachers
2026CVPR
Recurrent Video Masked Autoencoders
2026ICLR
Dual Perspectives on Non-Contrastive Self-Supervised Learning
2026International Journal of Computer Vision
Self-Supervised Video Representation Learning in a Heuristic Decoupled Perspective
2026IEEE TCSVT
BIMM: Brain Inspired Masked Modeling for Video Representation Learning
2025CVPR Workshops
Efficient VideoMAE via Temporal Progressive Training
2025ICCV
An Empirical Study of Autoregressive Pre-training from Videos
2025ICCV Workshops
Reinforcement Learning Meets Masked Video Modeling: Trajectory-Guided Adaptive Token Selection
2025ACROSET
Entropy-Guided Masked Autoencoding for Self-Supervised Human Action Recognition Using Video Swin Transformer
2025ICCV Workshops
Privacy Preservation Using Superimposed 3D-Models for Self-Supervised Training in Action Recognition
2025Machine Learning
Learning Complementary Knowledge via Trusted Multi-view Space Decomposition for Self-Supervised Contrastive Learning
2025NeurIPS
OSKAR: Omnimodal Self-supervised Knowledge Abstraction and Representation
2025arXiv / Preprint
MME: Video Representation Learning as World Model for Understanding and Planning
2025ICCV Workshops
Hashtag2Action: Data Engineering and Self-Supervised Pre-Training for Action Recognition in Short-Form Videos
2025Cluster Computing
Kdhiera: boosting self-supervised masked video modeling via hierarchical knowledge distillation
2025Proceedings of SPIE
Self-supervised video representation learning based on foreground and temporal information.
2025IJCV
Feature Hallucination for Self-supervised Action Recognition
2025CVPR Workshops
ViDROP: Video Dense Representation through Spatio-Temporal Sparsity
2025CVPR
SF2T: Self-supervised Fragment Finetuning of Video-LLMs for Fine-Grained Understanding
2025arXiv / Preprint
V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
2025CVPR
When the Future Becomes the Past: Taming Temporal Correspondence for Self-supervised Video Representation Learning
2025NeurIPS
Self-Supervised Learning of Motion Concepts by Optimizing Counterfactuals
2025ICMR
Label Ranker: Self-aware Preference for Classification Label Position in Visual Masked Self-supervised Pre-trained Model
2025CVPR
AutoSSVH: Exploring Automated Frame Sampling for Efficient Self-Supervised Video Hashing
2025AAAI
Efficient Self-Supervised Video Hashing with Selective State Spaces
2025Image and Vision Computing
Exemplar-free class incremental action recognition based on self-supervised learning
2025CVPR
Learning from Streaming Video with Orthogonal Gradients
2025arXiv / Preprint
Intuitive physics understanding emerges from self-supervised pretraining on natural videos
2025Pattern Analysis and Applications
ST-HViT: spatial-temporal hierarchical vision transformer for action recognition
2025Pattern Recognition Letters
Advancing video self-supervised learning via image foundation models
2025CVPR
SMILE: Infusing Spatial and Motion Semantics in Masked Video Learning
2025CVPR Workshops
A Large-Scale Analysis on Contextual Self-Supervised Video Representation Learning
2025Proceedings of SPIE
Progressive self-supervised spatio-temporal feature learning based on video sequence saliency
2025arXiv / Preprint
CrossVideoMAE: Self-Supervised Image-Video Representation Learning with Masked Autoencoders
2025EURASIP Journal on Image and Video Processing
Motion-driven Adaptive Frame Selection Strategy for Video Action Recognition
2025Signal, Image and Video Processing
Mitigating background bias in self-supervised video representation learning
2025TMLR
ARVideo: Autoregressive Pretraining for Self-Supervised Video Representation Learning
2025ICCV Workshops
Learning Video Representations without Natural Videos
2025IEEE TIFS
Collaboratively Self-supervised Video Representation Learning for Action Recognition
2024CVPR
Asymmetric Masked Distillation for Pre-Training Small Foundation Models
2024ECCV
Data Collection-free Masked Video Modeling
2024ECCV
Text-Guided Video Masked Autoencoder
2024BMVC
FILS: Self-Supervised Video Feature Prediction In Semantic Language Space
2024NeurIPS
Extending Video Masked Autoencoders to 128 Frames
2024arXiv / Preprint
Scaling 4D Representations
2024CVPR
VideoMAC: Video Masked Autoencoders Meet ConvNets
2024arXiv / Preprint
Self-supervised Video Object Segmentation with Distillation Learning of Deformable Attention
2024ECCV
Towards Latent Masked Image Modeling for Self-supervised Visual Representation Learning
2024ECCV
SIGMA: Sinkhorn-Guided Masked Video Modeling
2024CVPR Workshops
ST2ST: Self-Supervised Test-time Adaptation for Video Action Recognition
2024CogSci
Self-supervised learning of video representations from a child's perspective
2024ECCV
ViC-MAE: Self-supervised Representation Learning from Images and Video with Contrastive Masked Autoencoders
2024CVPR
Learning to Predict Activity Progress by Self-Supervised Video Alignment
2024Pattern Recognition
Repeat and learn: Self-supervised visual representations learning by Repeated Scene Localization
2024CVPR
ES3: Evolving Self-Supervised Learning of Robust Audio-Visual Speech Representations
2024WACV
Self-supervised Learning of Semantic Correspondence Using Web Videos
2024IPEC
Video Compression and Action Recognition in Self-supervised Learning
2024WACV
CycleCL: Self-supervised Learning for Periodic Videos
2024ICME Workshops
Self-Supervised Learning via Multi-Transformation Classification for Action Recognition
2024Pattern Recognition
Motion-guided spatiotemporal multitask feature discrimination for self-supervised video representation learning
2024CVPR
What When and Where? Self-Supervised Spatio-Temporal Grounding in Untrimmed Multi-Action Videos from Narrated Instructions
2024Applied Intelligence
Clustering-based multi-featured self-supervised learning for human activities and video retrieval
2024ICASSP Workshops
Positive and negative sampling strategies for self-supervised learning on audio-video data
2024AAAI
No More Shortcuts: Realizing the Potential of Temporal Self-Supervision
2024Pattern Recognition Letters
GLOCAL: A self-supervised learning framework for global and local motion estimation
2024IEEE TCSVT
Self-supervised Video Representation Learning via Capturing Semantic Changes Indicated by Saccades
2024IEEE TMM
MAR: Masked Autoencoders for Efficient Action Recognition
2024CVPR
VicTR: Video-conditioned Text Representations for Activity Recognition
2024IEEE Transactions on Cybernetics
Self-Supervised Video Representation Learning by Video Incoherence Detection
2024ICLR
Structured Video-Language Modeling with Temporal Grouping and Spatial Grounding
2024BMVC
MotionMAE: Self-supervised Video Representation Learning with Motion-Aware Masked Autoencoders
2024ICML
EVEREST: Efficient Masked Video Autoencoder by Removing Redundant Spatiotemporal Tokens
2024AAAI
XKD: Cross-modal Knowledge Distillation with Domain Alignment for Video Representation Learning
2024Visual Intelligence
Controllable Augmentations for Video Representation Learning
2023NeurIPS
Self-supervised object-centric learning for videos
2023NeurIPS
Language-based Action Concept Spaces Improve Video Self-Supervised Learning
2023NeurIPS
Uncovering the Hidden Dynamics of Video Self-supervised Learning under Distribution Shifts
2023NeurIPS
Self-supervised video pretraining yields robust and more human-aligned visual representation
2023CVPR
AdaMAE: Adaptive Masking for Efficient Spatiotemporal Learning with Masked Autoencoders
2023ICCV
Spatio-Temporal Crop Aggregation for Video Representation Learning
2023ICCV
Motion-Guided Masking for Spatiotemporal Representation Learning
2023ACM Multimedia
Fine-Grained Spatiotemporal Motion Alignment for Contrastive Video Representation Learning
2023ICCV
Unmasked Teacher: Towards Training-Efficient Video Foundation Models
2023arXiv / Preprint
Concatenated Masked Autoencoders as Spatial-Temporal Learner
2023ICTAI
AV-MaskEnhancer: Enhancing Video Representations through Audio-Visual Masked Autoencoder
2023CVPR
OmniMAE: Single Model Masked Pretraining on Images and Videos
2023CVPR
TimeBalance: Temporally-Invariant and Temporally-Distinctive Video Representations for Semi-Supervised Action Recognition
2023Image and Vision Computing
Attentive spatial-temporal contrastive learning for self-supervised video representation
2023ICCV
MGMAE: Motion Guided Masking for Video Masked Autoencoding
2023MVA
Cross-modal Manifold Cutmix for Self-supervised Video Representation Learning
2023ACM Multimedia
CHAIN: Exploring Global-Local Spatio-Temporal Information for Improved Self-Supervised Video Hashing
2023ACM Multimedia
Data-Efficient Masked Video Modeling for Self-supervised Action Recognition
2023IEEE Internet of Things Journal
Temporal Transformer Networks with Self-Supervision for Action Recognition
2023arXiv / Preprint
CMAE-V: Contrastive Masked Autoencoders for Video Action Recognition
2023Computer Vision and Image Understanding
Learning Representational Invariances for Data-Efficient Action Recognition
2023Neurocomputing
SOR-TC: Self-attentive octave ResNet with temporal consistency for compressed video action recognition
2023CVPR
Masked Motion Encoding for Self-Supervised Video Representation Learning
2023Signal, Image and Video Processing
Spatiotemporal consistency enhancement self-supervised representation learning for action recognition
2023IEEE TIP
Self-Supervised Video-Based Action Recognition With Disturbances
2023CVPR
Masked Video Distillation: Rethinking Masked Feature Modeling for Self-supervised Video Representation Learning
2023Engineering Applications of Artificial Intelligence
Enhancing motion visual cues for self-supervised video representation learning
2023Advanced Engineering Informatics
Continuous frame motion sensitive self-supervised collaborative network for video representation learning
2023Signal, Image and Video Processing
Self-supervised pretext task collaborative multi-view contrastive learning for video action recognition
2023IEEE TPAMI
Self-Supervised Learning from Untrimmed Videos via Hierarchical Consistency
2023AAAI
Audio-Visual Contrastive Learning with Temporal Self-Supervision
2023CVPR
Video Test-Time Adaptation for Action Recognition
2023AAAI
Self-Supervised Video Representation Learning via Latent Time Navigation
2023ICASSP
Temporal Contrastive Learning with Curriculum
2023ICLR Workshops
Nearest-Neighbor Inter-Intra Contrastive Learning from Unlabeled Videos
2023ICCV
Tubelet-Contrastive Self-Supervision for Video-Efficient Generalization
2023ICASSP
Multi-scale Compositional Constraints for Representation Learning on Videos
2023WACV
Flavr: Flow-agnostic Video Representations for Fast Frame Interpolation
2023arXiv / Preprint
HomE: Homography-Equivariant Video Representation Learning
2023WACV
ViewCLR: Learning Self-supervised Video Representation for Unseen Viewpoints
2023CVPR
Videomae v2: Scaling Video Masked Autoencoders with Dual Masking
2023AAAI
Self-Supervised Audio-Visual Representation Learning with Relaxed Cross-Modal Synchronicity
2023WACV
Previts: contrastive pretraining with video tracking supervision
2023CVPR
Modeling Video As Stochastic Processes for Fine-Grained Video Representation Learning
2023ICCV
Learning Fine-Grained Features for Pixel-wise Video Correspondences
2023CVPR Workshops
Cali-NCE: Boosting Cross-Modal Video Representation Learning With Calibrated Alignment
2023IEEE TNNLS
Self-supervised motion perception for spatiotemporal representation learning
2023Machine Vision and Applications
Similarity Contrastive Estimation for Image and Video Soft Contrastive Self-Supervised Learning
2023ICIP
Self-Supervised Contrastive Learning for Audio-Visual Action Recognition
2023IEEE TMM
Self-Supervised Scene-Debiasing for Video Representation Learning via Background Patching
2023IEEE TMM
LgNet: A local-global network for action recognition and beyond
2023IEEE TCSVT
Unsupervised Video-Based Action Recognition With Imagining Motion and Perceiving Appearance
2023AAAI
Spatiotemporal Augmentation on Selective Frequencies for Video Representation Learning
2023IEEE TCSVT
Consistent Intra-video Contrastive Learning with Asynchronous Long-term Memory Bank
2022CVPR
BEVT: BERT Pretraining of Video Transformers
2022NeurIPS
Masked Autoencoders As Spatiotemporal Learners
2022CVPR
SPAct: Self-supervised Privacy Preservation for Action Recognition
2022AAAI
Suppressing Static Visual Cues via Normalizing Flows for Self-Supervised Video Representation Learning
2022CVPR
Self-supervised Video Transformer
2022ACM TOMM
Exploring Relations in Untrimmed Videos for Self-Supervised Learning
2022ACM Multimedia
MaMiCo: Macro-to-Micro Semantic Correspondence for Self-supervised Video Representation Learning
2022IEEE TIP
TCGL: Temporal Contrastive Graph for Self-Supervised Video Representation Learning
2022CVPR
Cross-Architecture Self-supervised Video Representation Learning
2022AAAI
Contrastive spatio-temporal pretext learning for self-supervised video representation
2022CVPR
Transrank: Self-supervised video representation learning via ranking-based transformation recognition
2022CVPR
Learning from untrimmed videos: Self-supervised video representation learning with hierarchical consistency
2022CVPR
Motion-aware contrastive video representation learning via foreground-background merging
2022ICME
Self-Supervised Video Representation Learning with Motion-Contrastive Perception
2022IEEE TCSVT
Self-supervised video representation learning using improved instance-wise contrastive learning and deep clustering
2022Computer Vision and Image Understanding
TCLR: Temporal contrastive learning for video representation
2022AAAI
Self-supervised spatiotemporal representation learning by exploiting video continuity
2022CVPR
Probabilistic representations for video contrastive learning
2022CVPR
Contextualized spatio-temporal contrastive learning with self-supervision
2022NeurIPS
VideoMAE: Masked Autoencoders Are Data-Efficient Learners for Self-Supervised Video Pre-Training
2022WACV
Self-supervised video representation learning with cross-stream prototypical contrasting
2022CVPR
SLIC: Self-supervised learning with iterative clustering for human action videos
2022ECCV
GOCA: guided online cluster assignment for self-supervised video representation Learning
2022ACCV
TCVM: Temporal Contrasting Video Montage Framework for Self-supervised Video Representation Learning
2022ECCV
Static and Dynamic Concepts for Self-supervised Video Representation Learning
2022ECCV
SOS! Self-supervised Learning over Sets of Handled Objects in Egocentric Action Recognition
2022CVPR Workshops
Self-Supervised Video Representation Learning with Cascade Positive Retrieval
2022IEEE JSTSP
Self-Supervised Learning of Audio Representations From Audio-Visual Data Using Spatial Alignment
2022WACV
Hierarchically decoupled spatial-temporal contrast for self-supervised video representation learning
2022ICME
Spatio-temporal self-supervision enhanced transformer networks for action recognition
2022ICPR
Inter-Intra Cross-Modality Self-Supervised Video Representation Learning by Contrastive Clustering
2022CVPR Workshops
SCVRL: Shuffled Contrastive Video Representation Learning
2022arXiv / Preprint
InternVideo: General Video Foundation Models via Generative and Discriminative Learning
2022ICANN
Video Motion Perception for Self-supervised Representation Learning
2022IEEE TCSVT
An improved inter-intra contrastive learning framework on self-supervised video representation
2022CVPR Workshops
Auxiliary Learning for Self-Supervised Video Representation via Similarity-based Knowledge Distillation
2022ECCV
Motion Sensitive Contrastive Learning for Self-supervised Video Representation
2022NCC
Unsupervised Learning of Spatio-Temporal Representation with Multi-Task Learning for Video Retrieval
2022ECCV
Federated Self-supervised Learning for Video Understanding
2022Neurocomputing
Contrastive predictive coding with transformer for video representation learning
2022Applied Intelligence
Video representation learning by identifying spatio-temporal transformation
2022BMVC
On temporal granularity in self-supervised video representation learning
2022ICML Workshops
LAVA: Language Audio Vision Alignment for Data-Efficient Video Pre-Training
2022arXiv / Preprint
It Takes Two: Masked Appearance-Motion Modeling for Self-supervised Video Transformer Pre-training
2022BMVC
MAC: Mask-Augmentation for Motion-Aware Video Representation Learning
2022AVSS
Temporal-Invariant Video Representation Learning with Dynamic Temporal Resolutions.
2022ACM Multimedia
Dual Contrastive Learning for Spatio-temporal Representation
2022ECCV Workshops
MoQuad: Motion-focused Quadruple Construction for Video Contrastive Learning
2022arXiv / Preprint
On Negative Sampling for Audio-Visual Contrastive Learning from Movies
2022CVPR
Frame-wise Action Representations for Long Videos via Sequence Contrastive Learning
2022CVPR
Masked Feature Prediction for Self-Supervised Visual Pre-Training
2022arXiv / Preprint
Pixel-level Correspondence for Self-Supervised Learning from Video
2022CVPR
Temporal Alignment Networks for Long-Term Video
2022arXiv / Preprint
SimVTP: Simple Video Text Pre-Training with Masked Autoencoders
2022ICLR
Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction
2022IEEE TPAMI
Self-supervised video representation learning by uncovering spatio-temporal statistics
2021BMVC
Inter-intra Variant Dual Representations for Self-supervised Video Recognition
2021NeurIPS
VIMPAC: Video Pre-Training via Masked Token Prediction and Contrastive Learning
2021arXiv / Preprint
Watching too much television is good: Self-supervised audio-visual representation learning from movies and tv shows
2021ICPR
Temporally coherent embeddings for self-supervised video representation learning
2021CVPR
Audio-visual instance discrimination with cross-modal agreement
2021CVPR
Removing the background by adding the background: Towards background robust self-supervised video representation learning
2021AAAI
Enhancing unsupervised video representation learning by decoupling the scene and the motion
2021AAAI
SeCo: Exploring Sequence Supervision for Unsupervised Representation Learning
2021ICCV
Enhancing self-supervised video representation learning via multi-level feature optimization
2021AAAI
RSPNet: Relative Speed Perception for Unsupervised Video Representation Learning
2021CVPR
VideoMoCo: Contrastive Video Representation Learning with Temporally Adversarial Examples
2021ICCV
On compositions of transformations in contrastive self-supervised learning
2021CVPR
Unsupervised visual representation learning by tracking patches in video
2021CVPR
A large-scale study on unsupervised spatiotemporal representation learning
2021CVPR
CoCon: Cooperative-Contrastive Learning
2021NeurIPS
VATT: Transformers for multimodal self-supervised learning from raw video, audio and text
2021ICCV
ASCNet: Self-supervised video representation learning with appearance-speed consistency
2021IEEE Access
Self-supervised visual learning by variable playback speeds prediction of a video
2021ICCV
Self-supervised video representation learning with meta-contrastive network
2021ICCV
Long short view feature decomposition via contrastive video representation learning
2021ICCV
Time-equivariant contrastive video representation learning
2021CVPR
Self-supervised video representation learning by context and motion decoupling
2021WACV
Unsupervised video representation learning by bidirectional feature prediction
2021ICLR
Self-supervised learning of compressed video representations
2021CVPR
Spatiotemporal contrastive video representation learning
2021arXiv / Preprint
MoDist: Motion Distillation for Self-Supervised Video Representation Learning
2021ICCV
Broaden your views for self-supervised video learning
2021ICCV
Vi2CLR: Video and image for visual contrastive learning of representation
2021ICCV
Contrast and order representations for video self-supervised learning
2021ICCV
Motion-augmented self-training for video recognition at smaller scale
2021ICCV Workshops
Video contrastive learning with global context
2021ICCV
Motion-focused contrastive learning of video representations
2021BMVC
Back to the Future: Cycle Encoding Prediction for Self-supervised Video Representation Learning
2021ICCV
Composable augmentation encoding for video representation learning
2021ICCV
Learning temporal dynamics from cycles in narrated video
2021ICCV
CrossCLR: Cross-Modal Contrastive Learning for Multi-Modal Video Representations
2021ICLR
Watching the World Go By: Representation Learning from Unlabeled Videos
2021ICLR
Parameter Efficient Multimodal Transformers for Video Representation Learning
2021ICLR
Active Contrastive Learning of Audio-Visual Video Representations
2020Sensors
Self-Supervised Learning to Detect Key Frames in Videos
2020ECCV
Self-supervised motion representation via scattering local motion cues
2020ACM Multimedia
Self-supervised video representation learning using inter-intra contrastive framework
2020arXiv / Preprint
Video representation learning with visual tempo consistency
2020arXiv / Preprint
Self-supervised temporal discriminative learning for video representation learning
2020NeurIPS
Self-supervised learning by cross-modal audio-video clustering
2020ECCV
Self-supervised video representation learning by pace prediction
2020CVPR
Unsupervised learning from video with deep neural embeddings
2020ECCV Workshops
Unsupervised learning of video representations via dense trajectory clustering
2020ECCV
Video representation learning by recognizing temporal transformations
2020CVPR
Video playback rate perception for self-supervised spatio-temporal representation learning
2020NeurIPS
Self-supervised co-training for video representation learning
2020AAAI
Video cloze procedure for self-supervised spatio-temporal learning
2020CVPR
End-to-end learning of visual representations from uncurated instructional videos
2020CVPR
SpeedNet: Learning the Speediness in Videos
2020ECCV
Contrastive multiview coding
2020Signal Processing: Image Communication
Self-supervised video representation learning by maximizing mutual information
2020ECCV
Memory-augmented dense predictive coding for video representation learning
2020CVPR
Evolving losses for unsupervised video representation learning
2020arXiv / Preprint
AudioVisual SlowFast Networks for Video Recognition
2020NeurIPS
Cycle-Contrast for Self-Supervised Video Representation Learning
2020arXiv / Preprint
Can temporal information help with contrastive self-supervised learning?
2020NeurIPS
Self-supervised multimodal versatile networks
2020arXiv / Preprint
Pretext-Contrastive Learning: Toward Good Practices in Self-Supervised Video Representation Learning
2020arXiv / Preprint
UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation
2020ECCV
Self-supervised learning of audio-visual objects from video
2020CVPR
Speech2Action: Cross-Modal Supervision for Action Recognition
2020ACM Multimedia
Look, Listen, and Attend: Co-Attention Network for Self-Supervised Audio-Visual Representation Learning
2019CVPR
Self-supervised spatio-temporal representation learning for videos by predicting motion and appearance statistics
2019ICCV Workshops
Video representation learning by dense predictive coding
2019CVPR
Self-supervised spatiotemporal learning via video clip order prediction
2019WACV
Video Jigsaw: Unsupervised Learning of Spatiotemporal Context for Video Action Recognition
2019AAAI
Self-supervised video representation learning with space-time cubic puzzles
2019arXiv / Preprint
Learning Video Representations Using Contrastive Bidirectional Transformer
2019ICCV
DynamoNet: Dynamic Action and Motion Network
2019CVPR
Temporal Cycle-Consistency Learning
2019ICCV
VideoBERT: A Joint Model for Video and Language Representation Learning
2018CVPR
Geometry Guided Convolutional Neural Networks for Self-Supervised Video Representation Learning
2018arXiv / Preprint
Self-Supervised Spatiotemporal Feature Learning via Video Rotation Prediction
2018NeurIPS
Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization
2018ECCV
Audio-Visual Scene Analysis with Self-Supervised Multisensory Features
2018CVPR
Compressed Video Action Recognition
2018ECCV
Improving Spatiotemporal Self-Supervision by Deep Reinforcement Learning
2018CVPR
Learning and Using the Arrow of Time
2017ICCV
Unsupervised Representation Learning by Sorting Sequences
2017CVPR
Self-Supervised Video Representation Learning With Odd-One-Out Networks
2016ECCV
Shuffle and Learn: Unsupervised Learning Using Temporal Order Verification
Page 1
Surveys and evaluation
Research resources
Survey and benchmarking work that helps place individual methods in context.
Unifying Video Self-Supervised Learning across Families of Tasks: A Survey
Ishan Dave*, Malitha Gunawardhana*, Limalka Sadith, Honglu Zhou, Liel David, Daniel Harari, Mubarak Shah, Muhammad Hairs Khan
Self-Supervised Learning for Videos: A Survey
Madeline C. Schiappa, Yogesh S. Rawat, And Mubarak Shah
SEVERE++: Evaluating Benchmark Sensitivity in Generalization of Video Representation Learning
Fida Mohammad Thoker, Letian Jiang, Chen Zhao, Piyush Bagad, Hazel Doughty, Bernard Ghanem, Cees G. M. Snoek
How Effective are Self-Supervised Models for Contact Identification in Videos
Malitha Gunawardhana, Limalka Sadith, Liel David, Daniel Harari, Muhammad Haris Khan
Benchmarking self-supervised video representation learning
Akash Kumar, Ashlesha Kumar, Vibhav Vineet, Yogesh Singh Rawat
A Large-scale Study of Spatiotemporal Representation Learning with a New Benchmark on Action Recognition
Deng, A., Yang, T., & Chen, C.
How Severe Is Benchmark-Sensitivity in Video Self-supervised Learning?
Fida Mohammad Thoker, Hazel Doughty, Piyush Bagad, Cees Snoek
Field guide
Video self-supervised learning FAQ
What is video self-supervised learning?
Video self-supervised learning learns useful spatial and temporal representations from videos without requiring a manually annotated label for every training example. Common objectives include masked reconstruction, contrastive learning, temporal prediction, motion modeling and cross-modal learning.
What do Video SSL, VideoSSL and SSL video mean?
Video SSL and VideoSSL are common abbreviations for video self-supervised learning. SSL video is another search phrasing for the same research area, which is also described as self-supervised video representation learning or video representation pretraining.
Which publication metadata is shown?
Each catalog entry displays its confirmed publication year and latest verified venue, alongside the title, authors and research links.
How are later conference or journal publications handled?
When a preprint is later published at a conference or journal, the public entry is updated to the latest confirmed venue while the supporting audit record remains in the repository.