mlsanityData to 7 Oct 2026

Expressive Keypoints for Skeleton-based Action Recognition via Skeleton Transformation

arXiv 2406.18011 ↗First posted 26 Jun 2024cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

In the realm of skeleton-based action recognition, the traditional methods which rely on coarse body keypoints fall short of capturing subtle human actions. In this work, we propose Expressive Keypoints that incorporates hand and foot details to form a fine-grained skeletal representation, improving the discriminative ability for existing models in discerning intricate actions. To efficiently model Expressive Keypoints, the Skeleton Transformation strategy is presented to gradually downsample the keypoints and prioritize prominent joints by allocating the importance weights. Additionally, a plug-and-play Instance Pooling module is exploited to extend our approach to multi-person scenarios without surging computation costs. Extensive experimental results over seven datasets present the superiority of our method compared to the state-of-the-art for skeleton-based human action recognition. Code is available at https://github.com/YijieYang23/SkeleT-GCN.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 36 of its 52 references that are in the map. First posted on arXiv 26 Jun 2024.

Builds on

36 of 52 references.

References · 36

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  3. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,259
  4. 2015Fast R-CNNcited by 2,930
  5. 2017The Kinetics Human Action Video Datasetcited by 1,894
  6. 2018SlowFast Networks for Video Recognitioncited by 1,862
  7. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  8. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,199
  9. 2014Two-Stream Convolutional Networks for Action Recognition in Videoscited by 1,067
  10. 2016NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysiscited by 683
  11. 2020X3D: Expanding Architectures for Efficient Video Recognitioncited by 635
  12. 2018Real-world Anomaly Detection in Surveillance Videoscited by 570
24 more
  1. 2019NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understandingcited by 530
  2. 2020Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognitioncited by 339
  3. 2021Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognitioncited by 317
  4. 2021Revisiting Skeleton-based Action Recognitioncited by 256
  5. 2020Whole-Body Human Pose Estimation in the Wildcited by 178
  6. 2014Cross-view Action Modeling, Learning and Recognitioncited by 134
  7. 2018Co-occurrence Feature Learning from Skeleton Data for Action Recognition and Detection with Hierarchical Aggregationcited by 106
  8. 2019Skeleton-Based Action Recognition with Multi-Stream Adaptive Graph Convolutional Networkscited by 103
  9. 2017PKU-MMD: A Large Scale Benchmark for Continuous Multi-Modal Human Action Understandingcited by 101
  10. 2022Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 85
  11. 2022PYSKL: Towards Good Practices for Skeleton Action Recognitioncited by 83
  12. 2021Skeleton-Contrastive 3D Action Representation Learningcited by 76
  13. 2022PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequencescited by 68
  14. 2020A Survey on 3D Skeleton-Based Action Recognition Using Learning Methodcited by 46
  15. 2022STAR-Transformer: A Spatio-temporal Cross Attention Transformer for Human Action Recognitioncited by 43
  16. 2019SkeleMotion: A New Representation of Skeleton Joint Sequences Based on Motion Information for 3D Action Recognitioncited by 42
  17. 2021VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Livingcited by 35
  18. 2018Glimpse Clouds: Human Activity Recognition from Unstructured Feature Pointscited by 33
  19. 2022DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognitioncited by 26
  20. 2019Skeleton Image Representation for 3D Action Recognition based on Tree Structure and Reference Jointscited by 25
  21. 2023Unified Keypoint-based Action Recognition Framework via Structured Keypoint Poolingcited by 19
  22. 2021Skeleton-Based Mutually Assisted Interacted Object Localization and Human Action Recognitioncited by 13
  23. 2017Skeleton Boxes: Solving skeleton based action detection with a single deep convolutional neural networkcited by 7
  24. 2019Skeleton-based Action Recognition of People Handling Objectscited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 5; 2026: 1.

6 papers.

  1. 2025Body-Hand Modality Expertized Networks with Cross-attention for Fine-grained Skeleton Action Recognitioncited by 3
  2. 2025Evolving Skeletons: Motion Dynamics in Action Recognitioncited by 1
  3. 2025AI-Based Stroke Rehabilitation Domiciliary Assessment System with ST_GCN Attentioncited by 0
  4. 2025Label-Efficient Skeleton-based Recognition with Stable-Invertible Graph Convolutional Networkscited by 0
  5. 2025Active Learning for GCN-based Action Recognitioncited by 0
  6. 2026BHaRNet: Reliability-Aware Body-Hand Modality Expertized Networks for Fine-grained Skeleton Action Recognitioncited by 0