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

Table 1

Comparison of input and output dimensions of spatiotemporal graph convolutional networks.

Number of network layers	Input dimension	Output dimension
First floor	(9,3,300)	(9,64,300)
Second floor	(9,64,300)	(9,64,300)
Third floor	(9,64,300)	(9,64,300)
Fourth floor	(9,64,300)	(9,128,150)
Fifth floor	(9,128,150)	(9,128,150)
Sixth floor	(9,128,150)	(9,256,75)
Seventh floor	(9,256,75)	(9,256,75)
Eighth floor	(9,256,75)	(9,256,75)
Ninth floor	(9,256,75)	(9,256,75)