[Retracted] DTFA-Net: Dynamic and Texture Features Fusion Attention Network for Face Antispoofing

Figure 5

The dynamic and texture features fusion attention network (DTFA-Net) architecture. The figure omits the ReLU and pooling layers after the convolution layer, and the id of the convolution is shown on the top. Color code used is as follows: pink = convolution; blue = fusion block; gray = spatial attention; green = fully connected layer.