mlsanityData to 7 Oct 2026

Bootstrapped Representation Learning for Skeleton-Based Action Recognition

arXiv 2202.02232 ↗First posted 4 Feb 2022cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

In this work, we study self-supervised representation learning for 3D skeleton-based action recognition. We extend Bootstrap Your Own Latent (BYOL) for representation learning on skeleton sequence data and propose a new data augmentation strategy including two asymmetric transformation pipelines. We also introduce a multi-viewpoint sampling method that leverages multiple viewing angles of the same action captured by different cameras. In the semi-supervised setting, we show that the performance can be further improved by knowledge distillation from wider networks, leveraging once more the unlabeled samples. We conduct extensive experiments on the NTU-60 and NTU-120 datasets to demonstrate the performance of our proposed method. Our method consistently outperforms the current state of the art on both linear evaluation and semi-supervised benchmarks.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 47 of its 65 references that are in the map. First posted on arXiv 4 Feb 2022.

Builds on

47 of 65 references.

References · 47

  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. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  6. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  7. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  8. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  9. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  10. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
  11. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,424
  12. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,379
35 more
  1. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,375
  2. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  3. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,199
  4. 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,161
  5. 2016Colorful Image Colorizationcited by 1,113
  6. 2015Unsupervised Visual Representation Learning by Context Predictioncited by 1,062
  7. 2019Self-Supervised Learning of Pretext-Invariant Representationscited by 806
  8. 2016NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysiscited by 683
  9. 2019NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understandingcited by 530
  10. 2020Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognitioncited by 339
  11. 2016Learning Representations for Automatic Colorizationcited by 251
  12. 2019Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognitioncited by 228
  13. 2016Split-Brain Autoencoders: Unsupervised Learning by Cross-Channel Predictioncited by 217
  14. 2016An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Datacited by 126
  15. 2017A New Representation of Skeleton Sequences for 3D Action Recognitioncited by 125
  16. 2018Co-occurrence Feature Learning from Skeleton Data for Action Recognition and Detection with Hierarchical Aggregationcited by 106
  17. 2017View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Datacited by 105
  18. 20213D Human Action Representation Learning via Cross-View Consistency Pursuitcited by 105
  19. 2017PKU-MMD: A Large Scale Benchmark for Continuous Multi-Modal Human Action Understandingcited by 101
  20. 2020MS2L: Multi-Task Self-Supervised Learning for Skeleton Based Action Recognitioncited by 92
  21. 2020Stronger, Faster and More Explainable: A Graph Convolutional Baseline for Skeleton-based Action Recognitioncited by 91
  22. 2019PREDICT & CLUSTER: Unsupervised Skeleton Based Action Recognitioncited by 90
  23. 2021Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Recognitioncited by 89
  24. 2017Interpretable 3D Human Action Analysis with Temporal Convolutional Networkscited by 88
  25. 2021Exponential Moving Average Normalization for Self-supervised and Semi-supervised Learningcited by 78
  26. 2021Skeleton-Contrastive 3D Action Representation Learningcited by 76
  27. 2019Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searchingcited by 70
  28. 2020Augmented Skeleton Based Contrastive Action Learning with Momentum LSTM for Unsupervised Action Recognitioncited by 59
  29. 2017Skeleton-based Action Recognition with Convolutional Neural Networkscited by 54
  30. 2020Adversarial Self-Supervised Learning for Semi-Supervised 3D Action Recognitioncited by 34
  31. 2017Skeleton based action recognition using translation-scale invariant image mapping and multi-scale deep cnncited by 26
  32. 2018Unsupervised Feature Learning of Human Actions as Trajectories in Pose Embedding Manifoldcited by 26
  33. 2020Prototypical Contrast and Reverse Prediction: Unsupervised Skeleton Based Action Recognitioncited by 25
  34. 2021Momentum^2 Teacher: Momentum Teacher with Momentum Statistics for Self-Supervised Learningcited by 14
  35. 2020Sparse Semi-Supervised Action Recognition with Active Learningcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 6; 2024: 1; 2025: 0; 2026: 1.

8 papers.

  1. 2023HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representationscited by 42
  2. 2023Pyramid Self-attention Polymerization Learning for Semi-supervised Skeleton-based Action Recognitioncited by 11
  3. 2023Skeleton-based Action Recognition through Contrasting Two-Stream Spatial-Temporal Networkscited by 9
  4. 2023Balanced Representation Learning for Long-tailed Skeleton-based Action Recognitioncited by 3
  5. 2023Cross-Model Cross-Stream Learning for Self-Supervised Human Action Recognitioncited by 2
  6. 2024Extended multi-stream temporal-attention module for skeleton-based human action recognition (HAR)cited by 2
  7. 2023Motion-R3: Fast and Accurate Motion Annotation via Representation-based Representativeness Rankingcited by 0
  8. 2026ASMa: Asymmetric Spatio-temporal Masking for Skeleton Action Representation Learningcited by 0