Extended multi-stream temporal-attention module for skeleton-based human action recognition (HAR)
arXiv:2411.06553
Abstract
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.
This paper accepted in Computers in Human Behavior Journal