EUVIMEDEUVIMED entdecken
Crossref

Scale-Aware Graph Convolutional Network With Part-Level Refinement for Skeleton-Based Human Action Recognition

Chang Li, Yingchi Mao, Qian Huang, Xiaowei Zhu, Jie Wu

IEEE Transactions on Circuits and Systems for Video Technology · 2024-06 · 34 (6) · 4311-4324

DOI: 10.1109/tcsvt.2023.3334872 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2024-06. Verfasst von Chang Li und 4 weiteren Autor:innen. Die Arbeit wurde bisher 32-mal zitiert (Crossref) und nennt 46 Literaturangaben. Gefördert von: Key Research and Development Program of China, Postgraduate Research & Practice Innovation Program of Jiangsu Province, Fundamental Research Funds for the Central Universities.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Graph Convolutional Networks (GCNs) have been widely used in skeleton-based human action recognition and have achieved promising results. However, current GCN-based methods are limited by their inability to refine semantic-guided joint relations and perform adaptive multi-scale analysis. These limitations impair their performance, particularly for analogical actions involving the interaction of the same body parts (e.g., drinking water and eating) as well as deficient actions with limited spatial-temporal information (e.g., subtle action writing and transient action sneezing). To solve these problems, we propose Part-level Refined Spatial Graph Convolution (PR-SGC) and Scale-aware Temporal Graph Convolution (Sa-TGC) for optimal action representation. The PR-SGC divides the skeleton into body parts and embeds this high-level semantics to refine the physical adjacency matrix. The Sa-TGC leverages the dynamic scale-aware mechanism to extract context-dependent multi-scale features. On this basis, we develop a novel Scale-aware Graph Convolutional Network with Part-level Refinement (SaPR-GCN), which is on par with state-of-the-art benchmarks on NTU RGB+D 60, NTU RGB+D 120, and NW-UCLA datasets.

Förderung

  • Key Research and Development Program of China
  • Postgraduate Research & Practice Innovation Program of Jiangsu Province
  • Fundamental Research Funds for the Central Universities
  • Key Research and Development Program of China, Yunnan Province
  • 14th Five-Year Plan for Educational Science of Jiangsu Province
  • Jiangsu Higher Education Reform Research Project
  • 2022 Undergraduate Practice Teaching Reform Research Project of Hohai University

Zitieren

APA

Li, C., Mao, Y., Huang, Q., Zhu, X., & Wu, J. (2024). Scale-Aware Graph Convolutional Network With Part-Level Refinement for Skeleton-Based Human Action Recognition. IEEE Transactions on Circuits and Systems for Video Technology, 34(6), 4311-4324. https://doi.org/10.1109/tcsvt.2023.3334872

Vancouver

Li C, Mao Y, Huang Q, Zhu X, Wu J. Scale-Aware Graph Convolutional Network With Part-Level Refinement for Skeleton-Based Human Action Recognition. IEEE Transactions on Circuits and Systems for Video Technology. 2024;34(6):4311-4324. doi:10.1109/tcsvt.2023.3334872

BibTeX
@article{Li2024,
  author = {Li, Chang and Mao, Yingchi and Huang, Qian and Zhu, Xiaowei and Wu, Jie},
  title = {Scale-Aware Graph Convolutional Network With Part-Level Refinement for Skeleton-Based Human Action Recognition},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology},
  year = {2024},
  volume = {34},
  number = {6},
  pages = {4311--4324},
  doi = {10.1109/tcsvt.2023.3334872}
}
Kostenlos starten →