mlsanityData to 13 Oct 2026

SCVRL: Shuffled Contrastive Video Representation Learning

arXiv 2205.11710 ↗First posted 24 May 2022cs.CVcited by 14

Not on the map. Why?

Abstract (arXiv)

We propose SCVRL, a novel contrastive-based framework for self-supervised learning for videos. Differently from previous contrast learning based methods that mostly focus on learning visual semantics (e.g., CVRL), SCVRL is capable of learning both semantic and motion patterns. For that, we reformulate the popular shuffling pretext task within a modern contrastive learning paradigm. We show that our transformer-based network has a natural capacity to learn motion in self-supervised settings and achieves strong performance, outperforming CVRL on four benchmarks.

Key facts. Cited by 14 papers in the map (data through 13 Oct 2026). Builds on 39 of its 54 references that are in the map. First posted on arXiv 24 May 2022.

Builds on

39 of 54 references.

References · 39

  1. 2017Attention Is All You Needcited by 60,106
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,304
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,043
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,009
  5. 2018Representation Learning with Contrastive Predictive Codingcited by 7,712
  6. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,492
  7. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,730
  8. 2020Exploring Simple Siamese Representation Learningcited by 2,860
  9. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,850
  10. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,285
  11. 2017The Kinetics Human Action Video Datasetcited by 1,900
  12. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,841
27 more
  1. 2021ViViT: A Video Vision Transformercited by 1,615
  2. 2021Is Space-Time Attention All You Need for Video Understanding?cited by 1,614
  3. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,590
  4. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,427
  5. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,381
  6. 2017The "something something" video database for learning and evaluating visual common sensecited by 1,093
  7. 2019Self-Supervised Learning of Pretext-Invariant Representationscited by 808
  8. 2019Learning Representations by Maximizing Mutual Information Across Viewscited by 733
  9. 2021Do Vision Transformers See Like Convolutional Neural Networks?cited by 674
  10. 2020Spatiotemporal Contrastive Video Representation Learningcited by 372
  11. 2019Learning Correspondence from the Cycle-Consistency of Timecited by 269
  12. 2017Unsupervised Representation Learning by Sorting Sequencescited by 219
  13. 2021Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encodingcited by 207
  14. 2020SpeedNet: Learning the Speediness in Videoscited by 171
  15. 2018Tracking Emerges by Colorizing Videoscited by 166
  16. 2020Self-supervised Video Representation Learning by Pace Predictioncited by 139
  17. 2017Representation Learning by Learning to Countcited by 120
  18. 2021Broaden Your Views for Self-Supervised Video Learningcited by 108
  19. 2019Only Time Can Tell: Discovering Temporal Data for Temporal Modelingcited by 66
  20. 2021Stochastic Image-to-Video Synthesis using cINNscited by 49
  21. 2019DynamoNet: Dynamic Action and Motion Networkcited by 48
  22. 2021iPOKE: Poking a Still Image for Controlled Stochastic Video Synthesiscited by 42
  23. 2020DiVA: Diverse Visual Feature Aggregation for Deep Metric Learningcited by 40
  24. 2018Improving Spatiotemporal Self-Supervision by Deep Reinforcement Learningcited by 35
  25. 2018Self-Supervised Video Hashing with Hierarchical Binary Auto-encodercited by 34
  26. 2020Sharing Matters for Generalization in Deep Metric Learningcited by 15
  27. 2021Behavior-Driven Synthesis of Human Dynamicscited by 14

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2022: 3; 2023: 4; 2024: 2; 2025: 1; 2026: 4.

14 papers.

Sort:

By area:

  1. 2023Verbs in Action: Improving verb understanding in video-language modelscited by 76
  2. 2024TOMATO: Assessing Visual Temporal Reasoning Capabilities in Multimodal Foundation Modelscited by 71
  3. 2025Seeing the Arrow of Time in Large Multimodal Modelscited by 29
  4. 2022Self-supervised video pretraining yields robust and more human-aligned visual representationscited by 20
  5. 2023Deciphering and integrating invariants for neural operator learning with various physical mechanismscited by 15
  6. 2022Learning Transferable Spatiotemporal Representations from Natural Script Knowledgecited by 6
  7. 2023Self-supervised dense representation learning for live-cell microscopy with time arrow predictioncited by 3
  8. 2026SemanticMoments: Training-Free Motion Similarity via Third Moment Featurescited by 3
  9. 2022Self-supervised Pre-training for Semantic Segmentation in an Indoor Scenecited by 1
  10. 2023SMC-NCA: Semantic-guided Multi-level Contrast for Semi-supervised Temporal Action Segmentationcited by 1
  11. 2024SITAR: Semi-supervised Image Transformer for Action Recognitioncited by 1
  12. 2026Seeing Fast and Slow: Learning the Flow of Time in Videoscited by 1
2 more
  1. 2026Automatic Funny Scene Extraction from Long-form Cinematic Videoscited by 0
  2. 2026The Shape of Time: Video-Token Contrast for Temporal Understanding in VideoLMscited by 0