mlsanityData to 7 Oct 2026

3D Human Action Representation Learning via Cross-View Consistency Pursuit

arXiv 2104.14466 ↗First posted 29 Apr 2021cs.CVcited by 105

Not on the map. Why?

Abstract (arXiv)

In this work, we propose a Cross-view Contrastive Learning framework for unsupervised 3D skeleton-based action Representation (CrosSCLR), by leveraging multi-view complementary supervision signal. CrosSCLR consists of both single-view contrastive learning (SkeletonCLR) and cross-view consistent knowledge mining (CVC-KM) modules, integrated in a collaborative learning manner. It is noted that CVC-KM works in such a way that high-confidence positive/negative samples and their distributions are exchanged among views according to their embedding similarity, ensuring cross-view consistency in terms of contrastive context, i.e., similar distributions. Extensive experiments show that CrosSCLR achieves remarkable action recognition results on NTU-60 and NTU-120 datasets under unsupervised settings, with observed higher-quality action representations. Our code is available at https://github.com/LinguoLi/CrosSCLR.

Key facts. Cited by 105 papers in the map (data through 7 Oct 2026). Builds on 40 of its 65 references that are in the map. First posted on arXiv 29 Apr 2021.

Builds on

40 of 65 references.

References · 40

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  5. 2020Supervised Contrastive Learningcited by 2,803
  6. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  7. 2017The Kinetics Human Action Video Datasetcited by 1,894
  8. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,838
  9. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
  10. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,379
  11. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,199
  12. 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,161
28 more
  1. 2016Colorful Image Colorizationcited by 1,113
  2. 2016NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysiscited by 683
  3. 2019NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understandingcited by 530
  4. 2015Unsupervised Learning of Video Representations using LSTMscited by 434
  5. 2020Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognitioncited by 339
  6. 2017On human motion prediction using recurrent neural networkscited by 336
  7. 2019S4L: Self-Supervised Semi-Supervised Learningcited by 335
  8. 2020Self-supervised Co-training for Video Representation Learningcited by 232
  9. 2019Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognitioncited by 228
  10. 2017Unsupervised Representation Learning by Sorting Sequencescited by 219
  11. 2019An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognitioncited by 151
  12. 2018Self-Supervised Video Representation Learning with Space-Time Cubic Puzzlescited by 149
  13. 2019Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognitioncited by 135
  14. 2017A New Representation of Skeleton Sequences for 3D Action Recognitioncited by 125
  15. 2017View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Datacited by 105
  16. 2018Boosting Self-Supervised Learning via Knowledge Transfercited by 92
  17. 2019Self-supervised Spatio-temporal Representation Learning for Videos by Predicting Motion and Appearance Statisticscited by 92
  18. 2020MS2L: Multi-Task Self-Supervised Learning for Skeleton Based Action Recognitioncited by 92
  19. 2019PREDICT & CLUSTER: Unsupervised Skeleton Based Action Recognitioncited by 90
  20. 2018View Adaptive Neural Networks for High Performance Skeleton-based Human Action Recognitioncited by 84
  21. 2020Augmented Skeleton Based Contrastive Action Learning with Momentum LSTM for Unsupervised Action Recognitioncited by 59
  22. 2017Skeleton-based Action Recognition with Convolutional Neural Networkscited by 54
  23. 2018Iterative Reorganization with Weak Spatial Constraints: Solving Arbitrary Jigsaw Puzzles for Unsupervised Representation Learningcited by 51
  24. 2017Unsupervised Learning of Long-Term Motion Dynamics for Videoscited by 37
  25. 2018Unsupervised Learning of View-invariant Action Representationscited by 32
  26. 2020Unsupervised 3D Human Pose Representation with Viewpoint and Pose Disentanglementcited by 32
  27. 2018Unsupervised Feature Learning of Human Actions as Trajectories in Pose Embedding Manifoldcited by 26
  28. 2019Skeleton Image Representation for 3D Action Recognition based on Tree Structure and Reference Jointscited by 25

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 18; 2023: 33; 2024: 19; 2025: 16; 2026: 12.

105 papers.

Sort:

By area:

  1. 2022MotionBERT: A Unified Perspective on Learning Human Motion Representationscited by 188
  2. 2021Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Recognitioncited by 89
  3. 2023SignBERT+: Hand-model-aware Self-supervised Pre-training for Sign Language Understandingcited by 59
  4. 2023HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representationscited by 42
  5. 2023Actionlet-Dependent Contrastive Learning for Unsupervised Skeleton-Based Action Recognitioncited by 41
  6. 2023SkeletonMAE: Graph-based Masked Autoencoder for Skeleton Sequence Pre-trainingcited by 41
  7. 2023Masked Motion Predictors are Strong 3D Action Representation Learnerscited by 41
  8. 2022CMD: Self-supervised 3D Action Representation Learning with Cross-modal Mutual Distillationcited by 38
  9. 2021UNIK: A Unified Framework for Real-world Skeleton-based Action Recognitioncited by 35
  10. 2022Contrastive Positive Mining for Unsupervised 3D Action Representation Learningcited by 34
  11. 2022Global-local Motion Transformer for Unsupervised Skeleton-based Action Learningcited by 33
  12. 2022Hierarchical Consistent Contrastive Learning for Skeleton-Based Action Recognition with Growing Augmentationscited by 31
38 more
  1. 2021OpenHands: Making Sign Language Recognition Accessible with Pose-based Pretrained Models across Languagescited by 30
  2. 2022Hierarchically Self-Supervised Transformer for Human Skeleton Representation Learningcited by 30
  3. 2022Hierarchical Contrast for Unsupervised Skeleton-based Action Representation Learningcited by 30
  4. 2022SkeletonMAE: Spatial-Temporal Masked Autoencoders for Self-supervised Skeleton Action Recognitioncited by 29
  5. 2024Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognitioncited by 29
  6. 2023Self-supervised Action Representation Learning from Partial Spatio-Temporal Skeleton Sequencescited by 25
  7. 2023HaLP: Hallucinating Latent Positives for Skeleton-based Self-Supervised Learning of Actionscited by 25
  8. 2023Zero-shot Skeleton-based Action Recognition via Mutual Information Estimation and Maximizationcited by 24
  9. 2022ViA: View-invariant Skeleton Action Representation Learning via Motion Retargetingcited by 22
  10. 2023Hulk: A Universal Knowledge Translator for Human-Centric Taskscited by 22
  11. 2023Part Aware Contrastive Learning for Self-Supervised Action Recognitioncited by 21
  12. 2021ViewCLR: Learning Self-supervised Video Representation for Unseen Viewpointscited by 20
  13. 2021Contrast-reconstruction Representation Learning for Self-supervised Skeleton-based Action Recognitioncited by 19
  14. 2023Prompted Contrast with Masked Motion Modeling: Towards Versatile 3D Action Representation Learningcited by 19
  15. 2022Contrastive Learning from Spatio-Temporal Mixed Skeleton Sequences for Self-Supervised Skeleton-Based Action Recognitioncited by 17
  16. 2023Graph Contrastive Learning for Skeleton-based Action Recognitioncited by 17
  17. 2023Spatiotemporal Decouple-and-Squeeze Contrastive Learning for Semi-Supervised Skeleton-based Action Recognitioncited by 16
  18. 2023Self-Supervised 3D Action Representation Learning with Skeleton Cloud Colorizationcited by 16
  19. 2023LAC: Latent Action Composition for Skeleton-based Action Segmentationcited by 15
  20. 2024MacDiff: Unified Skeleton Modeling with Masked Conditional Diffusioncited by 15
  21. 2024USDRL: Unified Skeleton-Based Dense Representation Learning with Multi-Grained Feature Decorrelationcited by 15
  22. 2025AthletePose3D: A Benchmark Dataset for 3D Human Pose Estimation and Kinematic Validation in Athletic Movementscited by 14
  23. 2025Heterogeneous Skeleton-Based Action Representation Learningcited by 12
  24. 2023Pyramid Self-attention Polymerization Learning for Semi-supervised Skeleton-based Action Recognitioncited by 11
  25. 2023Self-Supervised Video Representation Learning via Latent Time Navigationcited by 11
  26. 2023SCD-Net: Spatiotemporal Clues Disentanglement Network for Self-supervised Skeleton-based Action Recognitioncited by 11
  27. 2024Vision-Language Meets the Skeleton: Progressively Distillation with Cross-Modal Knowledge for 3D Action Representation Learningcited by 11
  28. 2022Unsupervised Human Action Recognition with Skeletal Graph Laplacian and Self-Supervised Viewpoints Invariancecited by 10
  29. 2021Real-time 3D human action recognition based on Hyperpoint sequencecited by 9
  30. 2022Contrastive Learning with Cross-Modal Knowledge Mining for Multimodal Human Activity Recognitioncited by 9
  31. 2023Skeleton-based Action Recognition through Contrasting Two-Stream Spatial-Temporal Networkscited by 9
  32. 2024Zero-Shot Skeleton-based Action Recognition with Dual Visual-Text Alignmentcited by 9
  33. 2022Bootstrapped Representation Learning for Skeleton-Based Action Recognitioncited by 8
  34. 2023A Co-training Approach for Noisy Time Series Learningcited by 8
  35. 2024Identity-free Artificial Emotional Intelligence via Micro-Gesture Understandingcited by 8
  36. 2022Multimodal Emotion Recognition with Modality-Pairwise Unsupervised Contrastive Losscited by 7
  37. 2024An Information Compensation Framework for Zero-Shot Skeleton-based Action Recognitioncited by 7
  38. 2024Idempotent Unsupervised Representation Learning for Skeleton-Based Action Recognitioncited by 7

50 most cited of 105 All 105 (JSON)