English

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

Computer Vision and Pattern Recognition 2023-02-20 v1

Abstract

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.

Keywords

Cite

@article{arxiv.2302.08689,
  title  = {Dynamic Spatial-temporal Hypergraph Convolutional Network for Skeleton-based Action Recognition},
  author = {Shengqin Wang and Yongji Zhang and Hong Qi and Minghao Zhao and Yu Jiang},
  journal= {arXiv preprint arXiv:2302.08689},
  year   = {2023}
}
R2 v1 2026-06-28T08:42:29.246Z