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

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...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2023-02
Main Authors: Wang, Shengqin, Zhang, Yongji, Hong, Qi, Zhao, Minghao, Jiang, Yu
Format: Article
Language:English
Subjects:
Activity recognition
Data integration
Graph theory
Time dependence
Topology
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2331-8422