Paper ID: 2411.06553

Extended multi-stream temporal-attention module for skeleton-based human action recognition (HAR)

Faisal Mehmood, Xin Guo, Enqing Chen, Muhammad Azeem Akbar, Arif Ali Khan, Sami Ullah

Graph convolutional networks (GCNs) are an effective skeleton-based human action recognition (HAR) technique. GCNs enable the specification of CNNs to a non-Euclidean frame that is more flexible. The previous GCN-based models still have a lot of issues: (I) The graph structure is the same for all model layers and input data.

Submitted: Nov 10, 2024