mlsanityData to 14 Oct 2026

Deep video representation learning: a survey

arXiv 2405.06574 ↗First posted 10 May 2024cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

This paper provides a review on representation learning for videos. We classify recent spatiotemporal feature learning methods for sequential visual data and compare their pros and cons for general video analysis. Building effective features for videos is a fundamental problem in computer vision tasks involving video analysis and understanding. Existing features can be generally categorized into spatial and temporal features. Their effectiveness under variations of illumination, occlusion, view and background are discussed. Finally, we discuss the remaining challenges in existing deep video representation learning studies.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 127 of its 203 references that are in the map. First posted on arXiv 10 May 2024.

Builds on

127 of 203 references.

References · 127

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2017Mask R-CNNcited by 7,277
  5. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,270
  6. 2018SlowFast Networks for Video Recognitioncited by 1,867
  7. 2021Is Space-Time Attention All You Need for Video Understanding?cited by 1,620
  8. 2021ViViT: A Video Vision Transformercited by 1,620
  9. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,209
  10. 2015Multi-Scale Context Aggregation by Dilated Convolutionscited by 1,133
  11. 2014Two-Stream Convolutional Networks for Action Recognition in Videoscited by 1,068
  12. 2017The 2017 DAVIS Challenge on Video Object Segmentationcited by 957
38 more
  1. 2016Temporal Segment Networks: Towards Good Practices for Deep Action Recognitioncited by 902
  2. 2021Multiscale Vision Transformerscited by 897
  3. 2018TSM: Temporal Shift Module for Efficient Video Understandingcited by 856
  4. 2016NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysiscited by 686
  5. 2020Image Segmentation Using Deep Learning: A Surveycited by 660
  6. 2019Self-supervised Visual Feature Learning with Deep Neural Networks: A Surveycited by 657
  7. 2017Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classificationcited by 521
  8. 2014Long-term Recurrent Convolutional Networks for Visual Recognition and Descriptioncited by 484
  9. 2017Representation Learning on Graphs: Methods and Applicationscited by 457
  10. 2019Video Object Segmentation using Space-Time Memory Networkscited by 438
  11. 2019Video Instance Segmentationcited by 393
  12. 2016Convolutional Two-Stream Network Fusion for Video Action Recognitioncited by 384
  13. 2018YouTube-VOS: A Large-Scale Video Object Segmentation Benchmarkcited by 383
  14. 2020Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognitioncited by 343
  15. 2019Video Classification with Channel-Separated Convolutional Networkscited by 290
  16. 2021Video Transformer Networkcited by 272
  17. 2021Coordinate Attention for Efficient Mobile Network Designcited by 241
  18. 2019Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognitioncited by 228
  19. 2021Keeping Your Eye on the Ball: Trajectory Attention in Video Transformerscited by 224
  20. 2020TDN: Temporal Difference Networks for Efficient Action Recognitioncited by 183
  21. 2019FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentationcited by 178
  22. 2019Listen to Look: Action Recognition by Previewing Audiocited by 163
  23. 2019An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognitioncited by 151
  24. 2016Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognitioncited by 143
  25. 2021End-to-End Referring Video Object Segmentation with Multimodal Transformerscited by 135
  26. 2019SCSampler: Sampling Salient Clips from Video for Efficient Action Recognitioncited by 134
  27. 2021Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusioncited by 129
  28. 2017A New Representation of Skeleton Sequences for 3D Action Recognitioncited by 126
  29. 2021Diverse Part Discovery: Occluded Person Re-identification with Part-Aware Transformercited by 120
  30. 2019Why Can't I Dance in the Mall? Learning to Mitigate Scene Bias in Action Recognitioncited by 117
  31. 2018ECO: Efficient Convolutional Network for Online Video Understandingcited by 115
  32. 2019Peeking into the Future: Predicting Future Person Activities and Locations in Videoscited by 114
  33. 2017CDC: Convolutional-De-Convolutional Networks for Precise Temporal Action Localization in Untrimmed Videoscited by 112
  34. 2016A Survey of Multi-View Representation Learningcited by 107
  35. 2018Actor and Action Video Segmentation from a Sentencecited by 106
  36. 2017View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Datacited by 105
  37. 2021Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayerscited by 104
  38. 2019Skeleton-Based Action Recognition with Multi-Stream Adaptive Graph Convolutional Networkscited by 103

50 most cited of 127 All 127 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 2.

4 papers.

  1. 2025DLFR-VAE: Dynamic Latent Frame Rate VAE for Video Generationcited by 4
  2. 2025VideoCompressa: Data-Efficient Video Understanding via Joint Temporal Compression and Spatial Reconstructioncited by 3
  3. 2026The Benefits of Temporal Correlations: SGD Learns k-Juntas from Random Walks Efficientlycited by 1
  4. 2026Towards Bitstream-corrupted Harsh Visual Understanding: Through Bitstream Language Modeling as Robust Semantic Priorscited by 0