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

<div>The representation of skeletal data. We select the yellow-colored joints to represent human motion and transform the 3D joint coordinate to pseudo image.</div>

Mathematical Problems in Engineering

fig2

Figure 2

Figure 2: A Hierarchical Static-Dynamic Encoder-Decoder Structure for 3D Human Motion Prediction with Residual CNNs 