Fig. 2
From: Multiscale recurrent regression networks for face alignment
The specification of our designed network. Specifically, our network is fed with a set of sampled local patches as input, and then these patches are passed forward onto a series of operations including two small convolutional layers, ReLU rectifier function, and fully connected layers. The output of the network results in a 136-dimension vector, which denotes the coordinates of 68 facial landmarks