mlsanityData to 7 Oct 2026

Dynamic Spatial-temporal Hypergraph Convolutional Network for Skeleton-based Action Recognition

arXiv 2302.08689 ↗First posted 17 Feb 2023cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Skeleton-based action recognition relies on the extraction of spatial-temporal topological information. Hypergraphs can establish prior unnatural dependencies for the skeleton. However, the existing methods only focus on the construction of spatial topology and ignore the time-point dependence. This paper proposes a dynamic spatial-temporal hypergraph convolutional network (DST-HCN) to capture spatial-temporal information for skeleton-based action recognition. DST-HCN introduces a time-point hypergraph (TPH) to learn relationships at time points. With multiple spatial static hypergraphs and dynamic TPH, our network can learn more complete spatial-temporal features. In addition, we use the high-order information fusion module (HIF) to fuse spatial-temporal information synchronously. Extensive experiments on NTU RGB+D, NTU RGB+D 120, and NW-UCLA datasets show that our model achieves state-of-the-art, especially compared with hypergraph methods.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 19 of its 32 references that are in the map. First posted on arXiv 17 Feb 2023.

Builds on

19 of 32 references.

References · 19

  1. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  2. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,199
  3. 2016NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysiscited by 683
  4. 2019NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understandingcited by 530
  5. 2018Hypergraph Neural Networkscited by 482
  6. 2020Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognitioncited by 339
  7. 2021Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognitioncited by 317
  8. 2019Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognitioncited by 135
  9. 2014Cross-view Action Modeling, Learning and Recognitioncited by 134
  10. 2021Constructing Stronger and Faster Baselines for Skeleton-based Action Recognitioncited by 87
  11. 2020Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action Recognitioncited by 82
  12. 2021Skeleton-Contrastive 3D Action Representation Learningcited by 76
7 more
  1. 2021Skeleton Cloud Colorization for Unsupervised 3D Action Representation Learningcited by 58
  2. 2021Edge Representation Learning with Hypergraphscited by 37
  3. 2021Topology-aware Convolutional Neural Network for Efficient Skeleton-based Action Recognitioncited by 29
  4. 2021Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognitioncited by 22
  5. 2022Focal and Global Spatial-Temporal Transformer for Skeleton-based Action Recognitioncited by 18
  6. 2022Skeleton-based Action Recognition via Temporal-Channel Aggregationcited by 13
  7. 2021Dynamic Hypergraph Convolutional Networks for Skeleton-Based Action Recognitioncited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 1; 2026: 1.

4 papers.

  1. 2024Adaptive Hyper-Graph Convolution Network for Skeleton-based Human Action Recognition with Virtual Connectionscited by 11
  2. 2024Autoregressive Adaptive Hypergraph Transformer for Skeleton-based Activity Recognitioncited by 4
  3. 2025HFGCN:Hypergraph Fusion Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 0
  4. 2026E2E-GNet: An End-to-End Skeleton-based Geometric Deep Neural Network for Human Motion Recognitioncited by 0