no code implementations • 6 Sep 2019 • Zhiwen Shao, Hengliang Zhu, Junshu Tang, Xuequan Lu, Lizhuang Ma
Instead of using an intermediate estimated guidance, we propose to explicitly transfer facial expression by directly mapping two unpaired input images to two synthesized images with swapped expressions.
1 code implementation • 5 Aug 2018 • Zhiwen Shao, Hengliang Zhu, Xin Tan, Yangyang Hao, Lizhuang Ma
Most of the existing deep learning methods only use one fully-connected layer called shape prediction layer to estimate the locations of facial landmarks.
Ranked #3 on
Face Alignment
on AFLW2000
no code implementations • 23 Jul 2018 • Hengliang Zhu, Yangyang Hao, Lizhuang Ma, Ruixing Li, Hua Wang
We participated the Task 1: Lesion Segmentation.