Dynamic Graph Attention Network for Skeleton-Based Action Recognition
Skeleton-based human action recognition has garnered significant attention for its robustness to background noise and illumination variations. However, existing methods relying on Graph Convolutional Networks (GCNs) and Transformers exhibit inherent limitations: GCNs struggle to model interactions b...
Saved in:
| Main Authors: | Zhenhua Li, Fanjia Li, Gang Hua |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-04-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/9/4929 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Cross-Scale Spatial Refinement Graph Convolutional Network for Skeleton-Based Action Recognition
by: Chengyuan Ke, et al.
Published: (2025-04-01) -
Lightweight Multiscale Spatio-Temporal Graph Convolutional Network for Skeleton-Based Action Recognition
by: Zhiyun Zheng, et al.
Published: (2025-04-01) -
GCN-Former: A Method for Action Recognition Using Graph Convolutional Networks and Transformer
by: Xueshen Cui, et al.
Published: (2025-04-01) -
Two-stream spatio-temporal GCN-transformer networks for skeleton-based action recognition
by: Dong Chen, et al.
Published: (2025-02-01) -
Lightweight graph convolutional network with multi-attention mechanisms for intelligent action recognition in online physical education
by: Yuhao You
Published: (2025-07-01)