mlsanityData to 7 Oct 2026

A New Representation of Skeleton Sequences for 3D Action Recognition

arXiv 1703.03492 ↗First posted 9 Mar 2017cs.CVcited by 125

Not on the map. Why?

Abstract (arXiv)

This paper presents a new method for 3D action recognition with skeleton sequences (i.e., 3D trajectories of human skeleton joints). The proposed method first transforms each skeleton sequence into three clips each consisting of several frames for spatial temporal feature learning using deep neural networks. Each clip is generated from one channel of the cylindrical coordinates of the skeleton sequence. Each frame of the generated clips represents the temporal information of the entire skeleton sequence, and incorporates one particular spatial relationship between the joints. The entire clips include multiple frames with different spatial relationships, which provide useful spatial structural information of the human skeleton. We propose to use deep convolutional neural networks to learn long-term temporal information of the skeleton sequence from the frames of the generated clips, and then use a Multi-Task Learning Network (MTLN) to jointly process all frames of the generated clips in parallel to incorporate spatial structural information for action recognition. Experimental results clearly show the effectiveness of the proposed new representation and feature learning method for 3D action recognition.

Key facts. Cited by 125 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 Mar 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 23; 2022: 30; 2023: 38; 2024: 20; 2025: 8; 2026: 6.

125 papers.

Sort:

By area:

  1. 2021Revisiting Skeleton-based Action Recognitioncited by 256
  2. 20213D Human Action Representation Learning via Cross-View Consistency Pursuitcited by 105
  3. 2021Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Recognitioncited by 89
  4. 2022Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognitioncited by 71
  5. 2021Skeleton Cloud Colorization for Unsupervised 3D Action Representation Learningcited by 58
  6. 2022MVSTER: Epipolar Transformer for Efficient Multi-View Stereocited by 50
  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. 2022Hypergraph Transformer for Skeleton-based Action Recognitioncited by 36
  10. 2024LLMs are Good Action Recognizerscited by 36
  11. 2022Hierarchical Temporal Transformer for 3D Hand Pose Estimation and Action Recognition from Egocentric RGB Videoscited by 35
  12. 2022Contrastive Positive Mining for Unsupervised 3D Action Representation Learningcited by 34
38 more
  1. 2022IGFormer: Interaction Graph Transformer for Skeleton-based Human Interaction Recognitioncited by 31
  2. 2022Hierarchical Consistent Contrastive Learning for Skeleton-Based Action Recognition with Growing Augmentationscited by 31
  3. 2022Hierarchically Self-Supervised Transformer for Human Skeleton Representation Learningcited by 30
  4. 2021Topology-aware Convolutional Neural Network for Efficient Skeleton-based Action Recognitioncited by 29
  5. 2021GeomNet: A Neural Network Based on Riemannian Geometries of SPD Matrix Space and Cholesky Space for 3D Skeleton-Based Interaction Recognitioncited by 27
  6. 2023Motion Question Answering via Modular Motion Programscited by 27
  7. 2022DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognitioncited by 26
  8. 2021BASAR:Black-box Attack on Skeletal Action Recognitioncited by 25
  9. 2021Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action Recognitioncited by 25
  10. 2023Self-supervised Action Representation Learning from Partial Spatio-Temporal Skeleton Sequencescited by 25
  11. 2022Joint-bone Fusion Graph Convolutional Network for Semi-supervised Skeleton Action Recognitioncited by 24
  12. 2023Zero-shot Skeleton-based Action Recognition via Mutual Information Estimation and Maximizationcited by 24
  13. 2021Understanding the Robustness of Skeleton-based Action Recognition under Adversarial Attackcited by 23
  14. 2021Generative Adversarial Graph Convolutional Networks for Human Action Synthesiscited by 23
  15. 2022Temporal-Viewpoint Transportation Plan for Skeletal Few-shot Action Recognitioncited by 22
  16. 2023Part Aware Contrastive Learning for Self-Supervised Action Recognitioncited by 21
  17. 2023Prompted Contrast with Masked Motion Modeling: Towards Versatile 3D Action Representation Learningcited by 19
  18. 2021Recognizing Actions in Videos from Unseen Viewpointscited by 18
  19. 2022Focal and Global Spatial-Temporal Transformer for Skeleton-based Action Recognitioncited by 18
  20. 2023Navigating Open Set Scenarios for Skeleton-based Action Recognitioncited by 17
  21. 2023Spatiotemporal Decouple-and-Squeeze Contrastive Learning for Semi-Supervised Skeleton-based Action Recognitioncited by 16
  22. 2023Self-Supervised 3D Action Representation Learning with Skeleton Cloud Colorizationcited by 16
  23. 2021Skeleton-Based Mutually Assisted Interacted Object Localization and Human Action Recognitioncited by 13
  24. 2022Skeleton-based Action Recognition via Temporal-Channel Aggregationcited by 13
  25. 2024Simba: Mamba augmented U-ShiftGCN for Skeletal Action Recognition in Videoscited by 13
  26. 2022Video Unsupervised Domain Adaptation with Deep Learning: A Comprehensive Surveycited by 12
  27. 2023One-Shot Action Recognition via Multi-Scale Spatial-Temporal Skeleton Matchingcited by 12
  28. 2024Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognitioncited by 12
  29. 2023SCD-Net: Spatiotemporal Clues Disentanglement Network for Self-supervised Skeleton-based Action Recognitioncited by 11
  30. 20213D Skeleton-based Few-shot Action Recognition with JEANIE is not so Na"ivecited by 10
  31. 2023Hard No-Box Adversarial Attack on Skeleton-Based Human Action Recognition with Skeleton-Motion-Informed Gradientcited by 10
  32. 2021Dynamic Hypergraph Convolutional Networks for Skeleton-Based Action Recognitioncited by 9
  33. 2022ERA: Expert Retrieval and Assembly for Early Action Predictioncited by 9
  34. 2023Skeleton-based Action Recognition through Contrasting Two-Stream Spatial-Temporal Networkscited by 9
  35. 2021STAR: Sparse Transformer-based Action Recognitioncited by 8
  36. 2022Bootstrapped Representation Learning for Skeleton-Based Action Recognitioncited by 8
  37. 2023Overcoming Topology Agnosticism: Enhancing Skeleton-Based Action Recognition through Redefined Skeletal Topology Awarenesscited by 8
  38. 2022Understanding the Vulnerability of Skeleton-based Human Activity Recognition via Black-box Attackcited by 7

50 most cited of 125 All 125 (JSON)