EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Graph Convolutional Network with Multi-View Topology for Lightweight Skeleton-Based Action Recognition

Liangliang Wang, Xu Zhang, Chuang Zhang

Symmetry · 04.08.2025 · 17 (8) · 1235

DOI: 10.3390/sym17081235 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Symmetry, online erschienen am 04.08.2025. Verfasst von Liangliang Wang und 2 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Skeleton-based action recognition is an important subject in deep learning. Graph Convolutional Networks (GCNs) have demonstrated strong performance by modeling the human skeleton as a natural topological graph, representing the connections between joints. However, most existing methods rely on non-adaptive topologies or insufficiently expressive representations. To address these limitations, we propose a Multi-view Topology Refinement Graph Convolutional Network (MTR-GCN), which is efficient, lightweight, and delivers high performance. Specifically: (1) We propose a new spatial topology modeling approach that incorporates two views. A dynamic view fuses joint information from dual streams in a pairwise manner, while a static view encodes the shortest static paths between joints, preserving the original connectivity relationships. (2) We propose a new MultiScale Temporal Convolutional Network (MSTC), which is efficient and lightweight. (3) Furthermore, we introduce a new temporal topology strategy by modeling temporal frames as a graph, which strengthens the extraction of temporal features. By modeling the human skeleton as both a spatial and a temporal graph, we reveal a topological symmetry between space and time within the unified spatio-temporal framework. The proposed model achieves state-of-the-art performance on several benchmark datasets, including NTU RGB + D (XSub: 92.8%, XView: 96.8%), NTU RGB + D 120 (XSub: 89.6%, XSet: 90.8%), and NW-UCLA (95.7%), demonstrating the effectiveness of our GCN module, TCN module, and overall architecture.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Wang, L., Zhang, X., & Zhang, C. (2025). Graph Convolutional Network with Multi-View Topology for Lightweight Skeleton-Based Action Recognition. Symmetry, 17(8), 1235. https://doi.org/10.3390/sym17081235

Vancouver

Wang L, Zhang X, Zhang C. Graph Convolutional Network with Multi-View Topology for Lightweight Skeleton-Based Action Recognition. Symmetry. 2025;17(8):1235. doi:10.3390/sym17081235

BibTeX
@article{Wang2025,
  author = {Wang, Liangliang and Zhang, Xu and Zhang, Chuang},
  title = {Graph Convolutional Network with Multi-View Topology for Lightweight Skeleton-Based Action Recognition},
  journal = {Symmetry},
  year = {2025},
  volume = {17},
  number = {8},
  pages = {1235},
  doi = {10.3390/sym17081235}
}
Kostenlos starten →