Learning deep representation from coarse to fine for face alignment
arXiv preprint arXiv:1608.00207, 2016.
In this paper, we propose a novel face alignment method that trains deep convolutional network from coarse to fine. It divides given landmarks into principal subset and elaborate subset. We firstly keep a large weight for principal subset to make our network primarily predict their locations while slightly take elaborate subset into accou...More
PPT (Upload PPT)