EUVIMEDEUVIMED entdecken
Crossref

Skeleton action recognition via graph convolutional network with self-attention module

Min Li, Ke Chen, Yunqing Bai, Jihong Pei

Electronic Research Archive · 2024 · 32 (4) · 2848-2864

DOI: 10.3934/era.2024129 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronic Research Archive, 2024. Verfasst von Min Li und 3 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 54 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Skeleton-based action recognition is an important but challenging task in the study of video understanding and human-computer interaction. However, existing methods suffer from two deficiencies. On the one hand, most methods usually involve manually designed convolution kernel which cannot capture spatial-temporal joint dependencies of complex regions. On the other hand, some methods just use the self-attention mechanism, ignoring its theoretical explanation. In this paper, we proposed a unified spatio-temporal graph convolutional network with a self-attention mechanism (SA-GCN) for low-quality motion video data with fixed viewing angle. SA-GCN can extract features efficiently by learning weights between joint points of different scales. Specifically, the proposed self-attention mechanism is end-to-end with mapping strategy for different nodes, which not only characterizes the multi-scale dependencies of joints, but also integrates the structural features of the graph and an ability of self-learning fusion features. Moreover, the attention mechanism proposed in this paper can be theoretically explained by GCN to some extent, which is usually not considered in most existing models. Extensive experiments on two widely used datasets, NTU-60 RGB+D and NTU-120 RGB+D, demonstrated that SA-GCN significantly outperforms a series of existing mainstream approaches in terms of accuracy.

Zitieren

APA

Li, M., Chen, K., Bai, Y., & Pei, J. (2024). Skeleton action recognition via graph convolutional network with self-attention module. Electronic Research Archive, 32(4), 2848-2864. https://doi.org/10.3934/era.2024129

Vancouver

Li M, Chen K, Bai Y, Pei J. Skeleton action recognition via graph convolutional network with self-attention module. Electronic Research Archive. 2024;32(4):2848-2864. doi:10.3934/era.2024129

BibTeX
@article{Li2024,
  author = {Li, Min and Chen, Ke and Bai, Yunqing and Pei, Jihong},
  title = {Skeleton action recognition via graph convolutional network with self-attention module},
  journal = {Electronic Research Archive},
  year = {2024},
  volume = {32},
  number = {4},
  pages = {2848--2864},
  doi = {10.3934/era.2024129}
}
Kostenlos starten →