期刊
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
卷 -, 期 -, 页码 3359-3368出版社
IEEE
DOI: 10.1109/CVPR.2018.00354
关键词
-
资金
- National Nature Science Foundation of China [61672267, 61432019, 61532009, 61721004, 61572498, 61472379]
- Key Research Program of Frontier Sciences, CAS [QYZDJ-SSW-JSC039]
- Open Project Program of the National Laboratory of Pattern Recognition [201700022]
- Beijing Natural Science Foundation [4172062]
Facial expression recognition (FER) is a challenging task due to different expressions under arbitrary poses. Most conventional approaches either perform face frontalization on a non frontal facial image or learn separate classifiers for each pose. Different from existing methods, in this paper, we propose an end-to-end deep learning model by exploiting different poses and expressions jointly for simultaneous facial image synthesis and pose-invariant facial expression recognition. The proposed model is based on generative adversarial network (GAN) and enjoys several merits. First, the encoder-decoder structure of the generator can learn a generative and discriminative identity representation for face images. Second, the identity representation is explicitly disentangled from both expression and pose variations through the expression and pose codes. Third, our model can automatically generate face images with different expressions under arbitrary poses to enlarge and enrich the training set for FER. Quantitative and qualitative evaluations on both controlled and in-the-wild datasets demonstrate that the proposed algorithm performs favorably against state-of-the-art methods.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据