Attention-Guided and Topology-Enhanced Shift Graph Convolutional Network for Skeleton-Based Action Recognition
Electronics · 20.09.2024 · 13 (18) · 3737
DOI: 10.3390/electronics13183737 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 20.09.2024. Verfasst von Chenghong Lu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: JSPS KAKENHI, Young Promising Researchers, JKA.
Abstract (Originalsprache)
Graph Convolutional Networks (GCNs) have emerged as a game-changer in skeleton-based action recognition. However, most previous works are resource-heavy, with large FLoating-number OPerations (FLOPs) limiting the model’s potential. A recent work involving shift operators to GCN (Shift-GCN) has successfully introduced a lightweight GCN, but there is still a performance gap compared to previous results. Inspired by Shift-GCN, we propose an innovative and novel model named attention-guided and topology-enhanced shift graph convolutional network (AT-Shift-GCN), which continues the lightweight benchmark and provides a more powerful performance. We employ a topological transfer operation to aggregate the information flow of different channels and extract spatial information. In addition, to extract temporal information across scales, we apply attention to interacting with shift convolution kernels of different lengths. Furthermore, we integrate an ultralight spatiotemporal attention module to fuse spatiotemporal details and provide robust neighborhood representation. In summary, AT-Shift-GCN is a breakthrough in skeleton-based action recognition that provides a lightweight model with enhanced performance on three datasets.
Förderung
- JSPS KAKENHI
- Young Promising Researchers
- JKA
- KEIRIN RACE
Zitieren
APA
Lu, C., Chen, H., Li, M., & Jing, L. (2024). Attention-Guided and Topology-Enhanced Shift Graph Convolutional Network for Skeleton-Based Action Recognition. Electronics, 13(18), 3737. https://doi.org/10.3390/electronics13183737
Vancouver
Lu C, Chen H, Li M, Jing L. Attention-Guided and Topology-Enhanced Shift Graph Convolutional Network for Skeleton-Based Action Recognition. Electronics. 2024;13(18):3737. doi:10.3390/electronics13183737
BibTeX
@article{Lu2024,
author = {Lu, Chenghong and Chen, Hongbo and Li, Menglei and Jing, Lei},
title = {Attention-Guided and Topology-Enhanced Shift Graph Convolutional Network for Skeleton-Based Action Recognition},
journal = {Electronics},
year = {2024},
volume = {13},
number = {18},
pages = {3737},
doi = {10.3390/electronics13183737}
}
EUVIMED