Fig. 1
From: Multiscale wavelet attention convolutional network for facial expression recognition
The structure of CNN,\(\:\:Conv(k,\:s,\:p)\) denotes a convolutional layer with kernel size \(\:k\), stride\(\:\:s\), and padding\(\:\:p\). \(\:Maxpool(k,\:s,\:p)\) represents a max pooling layer with window size \(\:k\), stride \(\:s\), and padding \(\:p\).\(\:\:FC\) denotes a fully connected layer.
