Dynamic Graph Attention Network for Skeleton-Based Action Recognition
Applied Sciences · 29.04.2025 · 15 (9) · 4929
DOI: 10.3390/app15094929 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 29.04.2025. Verfasst von Zhenhua Li und 2 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Xuzhou Science and Technology Plan Project.
Abstract (Originalsprache)
Skeleton-based human action recognition has garnered significant attention for its robustness to background noise and illumination variations. However, existing methods relying on Graph Convolutional Networks (GCNs) and Transformers exhibit inherent limitations: GCNs struggle to model interactions between non-adjacent joints due to predefined skeletal topology, while Transformers accumulate noise through unrestricted global dependency modeling. To address these challenges, we propose a Dynamic Graph Attention Network (DGAN) that dynamically integrates local structural features and global spatiotemporal dependencies. DGAN employs a masked attention mechanism to adaptively adjust node connectivity, forming a dynamic adjacency matrix that extends beyond physical skeletal constraints by selectively incorporating highly correlated joints. Additionally, a node-partition bias strategy is introduced to prioritize attention on collaboratively moving body parts, thereby enhancing discriminative feature extraction. Extensive experiments on the NTU RGB+D 60 and NTU RGB+D 120 datasets validate the effectiveness of DGAN, which outperforms state-of-the-art methods by achieving a balance between local topology preservation and global interaction modeling. Our approach provides a robust framework for skeleton-driven action recognition, demonstrating superior generalization across diverse scenarios.
Förderung
- Xuzhou Science and Technology Plan Project
Zitieren
APA
Li, Z., Li, F., & Hua, G. (2025). Dynamic Graph Attention Network for Skeleton-Based Action Recognition. Applied Sciences, 15(9), 4929. https://doi.org/10.3390/app15094929
Vancouver
Li Z, Li F, Hua G. Dynamic Graph Attention Network for Skeleton-Based Action Recognition. Applied Sciences. 2025;15(9):4929. doi:10.3390/app15094929
BibTeX
@article{Li2025,
author = {Li, Zhenhua and Li, Fanjia and Hua, Gang},
title = {Dynamic Graph Attention Network for Skeleton-Based Action Recognition},
journal = {Applied Sciences},
year = {2025},
volume = {15},
number = {9},
pages = {4929},
doi = {10.3390/app15094929}
}
EUVIMED