An enhanced spatial-temporal graph convolution network with high order features for skeleton-based action recognition
PLOS One · 09.10.2025 · 20 (10) · e0332815
DOI: 10.1371/journal.pone.0332815 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 09.10.2025. Verfasst von Mohammed H Al-Hakimi und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, University of Peshawar, Peshawar, Pakistan. Hauptthemen laut MEDLINE: Neural Networks, Computer, Bone and Bones, Skeleton. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Skeleton-based action recognition has emerged as a promising field within computer vision, offering structured representations of human motion. While existing Graph Convolutional Network (GCN)-based approaches primarily rely on raw 3D joint coordinates, these representations fail to capture higher-order spatial and temporal dependencies critical for distinguishing fine-grained actions. In this study, we introduce novel geometric features for joints, bones, and motion streams, including multi-level spatial normalization, higher-order temporal derivatives, and bone-structure encoding through lengths, angles, and anatomical distances. These enriched features explicitly model kinematic and structural relationships, enabling the capture of subtle motion dynamics and discriminative patterns. Building on this, we propose two architectures: (i) an Enhanced Multi-Stream AGCN (EMS-AGCN) that integrates joint, bone, and motion features via a weighted fusion at the final layer, and (ii) a Multi-Branch AGCN (MB-AGCN) where features are processed in independent branches and fused adaptively at an early layer. Comprehensive experiments on the NTU-RGB+D 60 benchmark demonstrate the effectiveness of our approach: EMS-AGCN achieves 96.2% accuracy and MB-AGCN attains 95.5%, both surpassing state-of-the-art methods. These findings confirm that incorporating higher-order geometric features alongside adaptive fusion mechanisms substantially improves skeleton-based action recognition.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Computer Science, University of Peshawar, Peshawar, Pakistan.
- Department of Computer Science, Hodeida University, Hodeida, Yemen.
- School of Computer Science and Informatics, De Montfort University, Leicester, United Kingdom.
- Department of Computer Science, Aden Community College, Aden, Yemen.
ORCID-Profile: Mohammed H Al-Hakimi, Fahmi H Quradaa
Zitieren
APA
Al-Hakimi, M. H., Ahmed, I., Haseeb, M., Rassem, T. H., Quradaa, F. H., & Almoqbily, R. S. (2025). An enhanced spatial-temporal graph convolution network with high order features for skeleton-based action recognition. PLOS One, 20(10), e0332815. https://doi.org/10.1371/journal.pone.0332815
Vancouver
Al-Hakimi MH, Ahmed I, Haseeb M, Rassem TH, Quradaa FH, Almoqbily RS. An enhanced spatial-temporal graph convolution network with high order features for skeleton-based action recognition. PLOS One. 2025;20(10):e0332815. doi:10.1371/journal.pone.0332815
BibTeX
@article{AlHakimi2025,
author = {Al-Hakimi, Mohammed H and Ahmed, Ibrar and Haseeb, Muhammad and Rassem, Taha H and Quradaa, Fahmi H and Almoqbily, Rashad S},
title = {An enhanced spatial-temporal graph convolution network with high order features for skeleton-based action recognition},
journal = {PLOS One},
year = {2025},
volume = {20},
number = {10},
pages = {e0332815},
doi = {10.1371/journal.pone.0332815}
}
EUVIMED