A Survey of Recent Graph-Based Methods for Skeleton Based Action Recognition
Journal of Advanced Artificial Intelligence, Engineering and Technology · 01.01.2026 · 02 (01) · 01
DOI: 10.56147/aaiet.2.1.111 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Advanced Artificial Intelligence, Engineering and Technology, online erschienen am 01.01.2026. Verfasst von Abdur Rahman Siam.
Abstract (Originalsprache)
Skeleton-Based Action Recognition (SBAR) leverages 3D joint trajectories to recognize human activities while offering privacy, robustness to illumination/background changes and computational efficiency. Recent progress is dominated by spatio-temporal graph neural networks (ST-GNNs) that model the human body as a graph and learn data-adaptive connectivity, hierarchical structure, compact representations, multimodal supervision and efficient temporal fusion. This survey focuses on five representative methods CTR-GCN, HD-GCN, InfoGCN, Language Supervised Training (LST) and Temporal Channel Aggregation (TCA-GCN) and positions them within the broader SBAR literature. We analyze modeling assumptions, architectural choices, training objectives and empirical results on NTU RGB+D 60/120 and North western UCLA. We additionally contextualize the trajectory from dynamic topology learning to emerging foundation and sequence models reported in 2024-2025. Finally, we summarize open challenges and provide research directions for scalable, robust and semantically grounded SBAR.
Zitieren
APA
Siam, A. R. (2026). A Survey of Recent Graph-Based Methods for Skeleton Based Action Recognition. Journal of Advanced Artificial Intelligence, Engineering and Technology, 02(01), 01. https://doi.org/10.56147/aaiet.2.1.111
Vancouver
Siam AR. A Survey of Recent Graph-Based Methods for Skeleton Based Action Recognition. Journal of Advanced Artificial Intelligence, Engineering and Technology. 2026;02(01):01. doi:10.56147/aaiet.2.1.111
BibTeX
@article{Siam2026,
author = {Siam, Abdur Rahman},
title = {A Survey of Recent Graph-Based Methods for Skeleton Based Action Recognition},
journal = {Journal of Advanced Artificial Intelligence, Engineering and Technology},
year = {2026},
volume = {02},
number = {01},
pages = {01},
doi = {10.56147/aaiet.2.1.111}
}
EUVIMED