期刊
出版社
IEEE
DOI: 10.1109/CVPRW.2016.97
关键词
-
资金
- Natural Science Foundation of Guangdong Province [2014A030313688]
- Shenzhen Research Program [JSGG20150925164740726, JCYJ20150925163005055, CXZZ20150930104115529]
- Guangdong Research Program [2014B050505017, 2015B010129013]
- Key Laboratory of Hman-Machine Intelligence -Synergy Systems through the Chinese Academy of Sciences
- National Natural Science Foundation of China [61103164]
Facial gender and smile classification in unconstrained environment is challenging due to the invertible and large variations of face images. In this paper, we propose a deep model composed of GNet and SNet for these two tasks. We leverage the multi-task learning and the general-to-specific fine-tuning scheme to enhance the performance of our model. Our strategies exploit the inherent correlation between face identity, smile, gender and other face attributes to relieve the problem of over-fitting on small training set and improve the classification performance. We also propose the tasks-aware face cropping scheme to extract attribute-specific regions. The experimental results on the ChaLearn'16 FotW dataset for gender and smile classification demonstrate the effectiveness of our proposed 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