[Retracted] Recognition of Hitting Action in Cyclic Anaerobic Volleyball by Acute Cooling Based on Improved Spatiotemporal Graph Convolutional Network

Table 2

Comparison of the recognition method in this paper and other methods based on the self-built volleyball hitting action database.

Method	Recognition rate
TSN	60.28%
Attention is all we need	67.21%
ST-GCN (enter the two-dimensional coordinates of the joint point)	69.62%
ST-GCN (enter the three-dimensional coordinates of the joint point)	71.17%
The method of this paper (input the two-dimensional coordinates of the joint point)	84.35%
The method of this paper (input the three-dimensional coordinates of the joint point)	92.89%