Publications

Publications

-
Computer Vision and Pattern Recognition (CVPR) (under review), 2018

Recognizing an expression in videos is a challenging problem due to dynamic changes of facial action in the whole video. We propose a novel Cascaded Attention Network(CAN) based on sptiotemporal attention, tailored to the facial expression recognition in videos. The proposed model(CAN) got state-of-the-art result on three common datasets.
IEEE Transaction on Affective Computing (Major Revision), 2018

We propose a novel framework which is built on Generative Adversarial Networks with multiple discriminators, trying to synthesize realistic pedestrian and learn the background context simultaneously, then generate labeled pedestrian data to support the training of pedestrian detectors.
arxiv.preprint:1804.02047, 2018

Contact