Fig A1.

Model structure overview (left) and detailed neural network presentation (right). After feeding with the same input of extracted temporal features matrix, the data goes through a block of feature-wise convolution and then goes to one of three branches: A is the Recurrent Neural Network, B is temporal-wise dilated Convolutional Neural Network of two blocks, and C is feature-wise Convolutional Neural Network of two blocks. For all 3 branches, a fully connected layer is attached as the last layer for score classification.