
The proposed MSST-GCN model effectively improves the modeling ability of skeleton-based action recognition by utilizing spatial self-attention with adaptive topology and temporal self-attention, followed by multi-scale convolution networks to capture long-range spatial and temporal dependencies.


coremsg

multi-scale-spatial-temporal-self-attention-graph-convolutional-networks-for-achieving-state-of-the-art-results-in-skeleton-based-action-recognition


Multi-Scale Spatial-Temporal Self-Attention Graph Convolutional Networks for Achieving State-of-the-Art Results in Skeleton-based Action Recognition
