Shuffle Graph Convolutional Network for Skeleton-Based Action Recognition
Journal of Advanced Computational Intelligence and Intelligent Informatics · 20.09.2023 · 27 (5) · 790-800
DOI: 10.20965/jaciii.2023.p0790 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Advanced Computational Intelligence and Intelligent Informatics, online erschienen am 20.09.2023. Verfasst von Qiwei Yu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 25 Literaturangaben. Gefördert von: China Railway Group, Natural Science Foundation of Beijing Municipality.
Abstract (Originalsprache)
A shuffle graph convolutional network (Shuffle-GCN) is proposed to recognize human action by analyzing skeleton data. It uses channel split and channel shuffle operations to process multi-feature channels of skeleton data, which reduces the computational cost of graph convolution operation. Compared with the classical two-stream adaptive graph convolutional network model, the proposed method achieves a higher precision with 1/3 of the floating-point operations (FLOPs). Even more, a channel-level topology modeling method is designed to extract more motion information of human skeleton by learning the graph topology from different channels dynamically. The performance of Shuffle-GCN is tested under 56,880 action clips from the NTU RGB+D dataset with the accuracy 96.0% and the computational complexity 12.8 GFLOPs. The proposed method offers feasible solutions for developing practical applications of action recognition.
Förderung
- China Railway Group
- Natural Science Foundation of Beijing Municipality
Zitieren
APA
Yu, Q., Dai, Y., Hirota, K., Shao, S., & Dai, W. (2023). Shuffle Graph Convolutional Network for Skeleton-Based Action Recognition. Journal of Advanced Computational Intelligence and Intelligent Informatics, 27(5), 790-800. https://doi.org/10.20965/jaciii.2023.p0790
Vancouver
Yu Q, Dai Y, Hirota K, Shao S, Dai W. Shuffle Graph Convolutional Network for Skeleton-Based Action Recognition. Journal of Advanced Computational Intelligence and Intelligent Informatics. 2023;27(5):790-800. doi:10.20965/jaciii.2023.p0790
BibTeX
@article{Yu2023,
author = {Yu, Qiwei and Dai, Yaping and Hirota, Kaoru and Shao, Shuai and Dai, Wei},
title = {Shuffle Graph Convolutional Network for Skeleton-Based Action Recognition},
journal = {Journal of Advanced Computational Intelligence and Intelligent Informatics},
year = {2023},
volume = {27},
number = {5},
pages = {790--800},
doi = {10.20965/jaciii.2023.p0790}
}
EUVIMED