Synthetic Expressions are Better Than Real for Learning to Detect Facial Actions.

ABSTRACT: Critical obstacles in training classifiers to detect facial actions are the limited sizes of annotated video databases and the relatively low frequencies of occurrence of many actions. To address these problems, we propose an approach that makes use of facial expression generation. Our approach reconstructs the 3D shape of the face from each video frame, aligns the 3D mesh to a canonical view, and then trains a GAN-based network to synthesize novel images with facial action units of interest. To evaluate this approach, a deep neural network was trained on two separate datasets: One network was trained on video of synthesized facial expressions generated from FERA17; the other network was trained on unaltered video from the same database. Both networks used the same train and validation par

SUBMITTER: Niinuma K 

PROVIDER: S-EPMC10798354 | biostudies-literature | 2021 Jan

REPOSITORIES: biostudies-literature