Research Article
A Hierarchical Static-Dynamic Encoder-Decoder Structure for 3D Human Motion Prediction with Residual CNNs
Figure 7
Jointwise performance of different methods. (a) Jointwise MSE and (b) Jointwise MAE of different methods on G3D. (c) Jointwise MSE and (d) Jointwise MAE of different methods on FNTU.
(a) |
(b) |
(c) |
(d) |