Multi-Attribute Facial Landmark
MAFL 설명 보기
The MAFL dataset contains manually annotated facial landmark locations for 19,000 training and 1,000 test images. Source: Deforming Autoencoders: Unsupervised Disentangling of Shape and Appearance Image Source: http://mmlab.ie.cuhk.edu.hk/projects/TCDCN.html