An optimization high-resolution network for human pose recognition based on attention mechanism

To solve the problems of high complex calculation and low recognition precision of similar actions in the high-resolution network (HRNet), we proposed an optimized HRNet based on attention mechanism. Firstly, the dilated convolution (DC) module is introduced into cross-channel sampling to obtain global features, which ensures that the feature map can cover all the information of the original image; Secondly, the channel attention Squeeze-and-Excitation (SE) module is employed in the process of cross-channel feature fusion to learn the correlations, improving the recognition precision without changing the parameter quantity and operation complexity; Finally, the experiment results on KTH dataset show that the proposed algorithm has a better performance.