As shown in Table 1 , when only using the MS-TGCN network, the accuracy of behavior recognition roughly shows a decreasing trend with a continuous increase in K value, which well proves the bias weighting problem caused by using high-order adjacency matrices.
← all excerpts
Research on Multi-Scale Spatio-Temporal Graph Convolutional Human Behavior Recognition Method Incorporating Multi-Granularity Features.
1
—
—