The Multidimensional Motion Features of Spatial Depth Feature Maps: An Effective Motion Information Representation Method for Video-Based Action Recognition

<div>MD3DCNN module—3D convolutional layer for multidimensional motion information acquisition.</div>

Mathematical Problems in Engineering

fig3

Figure 3

Figure 3: The Multidimensional Motion Features of Spatial Depth Feature Maps: An Effective Motion Information Representation Method for Video-Based Action Recognition 

Figure 3 | The Multidimensional Motion Features of Spatial Depth Feature Maps: An Effective Motion Information Representation Method for Video-Based Action Recognition 