2s-GATCN: Two-Stream Graph Attentional Convolutional Networks for Skeleton-Based Action Recognition
Electronics · 04.04.2023 · 12 (7) · 1711
DOI: 10.3390/electronics12071711 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 04.04.2023. Verfasst von Shu-Bo Zhou und 3 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Shanghai.
Abstract (Originalsprache)
As human actions can be characterized by the trajectories of skeleton joints, skeleton-based action recognition techniques have gained increasing attention in the field of intelligent recognition and behavior analysis. With the emergence of large datasets, graph convolutional network (GCN) approaches have been widely applied for skeleton-based action recognition and have achieved remarkable performances. In this paper, a novel GCN-based approach is proposed by introducing a convolutional block attention module (CBAM)-based graph attention block to compute the semantic correlations between any two vertices. By considering semantic correlations, our model can effectively identify the most discriminative vertex connections associated with specific actions, even when the two vertices are physically unconnected. Experimental results demonstrate that the proposed model is effective and outperforms existing methods.
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Shanghai
Zitieren
APA
Zhou, S., Chen, R., Jiang, X., & Pan, F. (2023). 2s-GATCN: Two-Stream Graph Attentional Convolutional Networks for Skeleton-Based Action Recognition. Electronics, 12(7), 1711. https://doi.org/10.3390/electronics12071711
Vancouver
Zhou S, Chen R, Jiang X, Pan F. 2s-GATCN: Two-Stream Graph Attentional Convolutional Networks for Skeleton-Based Action Recognition. Electronics. 2023;12(7):1711. doi:10.3390/electronics12071711
BibTeX
@article{Zhou2023,
author = {Zhou, Shu-Bo and Chen, Ran-Ran and Jiang, Xue-Qin and Pan, Feng},
title = {2s-GATCN: Two-Stream Graph Attentional Convolutional Networks for Skeleton-Based Action Recognition},
journal = {Electronics},
year = {2023},
volume = {12},
number = {7},
pages = {1711},
doi = {10.3390/electronics12071711}
}
EUVIMED