DSTGAT: A Spatio-Temporal Dynamic Graph Attention Network for User Activity Recognition
A dynamic graph learning module based on Gumbel-Softmax sampling is proposed to adaptively reconstruct the sensor adjacency matrix and a Talking-Head graph attention mechanism is employed to facilitate cross-head feature interaction, enhancing global semantic fusion.
Jia-Hao Wang, Mao-Quan Wang, Jin-Ming Wu et al.
· Italian National Conference... · 0 citations