SelfGCN: Graph Convolution Network With Self-Attention for Skeleton-Based Action Recognition

Graph Convolutional Networks (GCNs) are widely used for skeleton-based action recognition and achieved remarkable performance. Due to the locality of graph convolution, GCNs can only utilize short-range node dependencies but fail to model long-range node relationships. In addition, existing graph co...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on image processing 2024, Vol.33, p.4391-4403
Hauptverfasser:	Wu, Zhize, Sun, Pengpeng, Chen, Xin, Tang, Keke, Xu, Tong, Zou, Le, Wang, Xiaofeng, Tan, Ming, Cheng, Fan, Weise, Thomas
Format:	Artikel
Sprache:	eng
Schlagworte:	action recognition Activity recognition Artificial neural networks Benchmarks Convolution Correlation Feature extraction Graph convolution Machine learning Modules Network topology Recurrent neural networks self-attention Skeleton Topology
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!