A Hierarchical Static-Dynamic Encoder-Decoder Structure for 3D Human Motion Prediction with Residual CNNs

Table 1

Compare with baselines.

Model	G3D		FNTU
	MSE	MAE	MSE	MAE
PredCNN [19]	0.1882	1.5713	0.1665	1.6394
S-TE [23]	0.1407	1.2095	0.1425	1.3094
PISEP^2 [20]	0.1199	1.1101	0.1210	1.1651
SDnet	0.1106	0.9782	0.1131	1.0675