A GCN and Transformer complementary network for skeleton-based action recognition

• Published in: Computer vision and image understanding Vol. 249; p. 104213
• Main Authors: Xiang, Xuezhi, Li, Xiaoheng, Liu, Xuzhao, Qiao, Yulong, El Saddik, Abdulmotaleb
• Format: Journal Article
• Language: English
• Published: Elsevier Inc 01.12.2024
• Subjects: Action recogniton; Global and local features; Graph convolution network; Self-attention; Action recogniton; 41A10; Self-attention; 65D05; 65D17; 41A05; Graph convolution network; Global and local features

Graph Convolution Networks (GCNs) have been widely used in skeleton-based action recognition. Although there are significant progress, the inherent limitation still lies in the restricted receptive field of GCN, hindering its ability to extract global dependencies effectively. And the joints that ar...