《Attention Modeling for Face Recognition via Deep learning》.pdf

Attention Modeling for Face Recognition via Deep Learning Sheng-hua Zhong (csshzhong@.hk) Department of Computing, Hung Hom, Kowloon Hong Kong, 999077 CHINA Yan Liu (csyliu@.hk) Department of Computing, Hung Hom, Kowloon Hong Kong, 99907 CHINA Yao Zhang (csyaozhang@.hk) Department of Computing, Hung Hom, Kowloon Hong Kong, 99907 CHINA Fu-lai Chung (cskchung@.hk) Department of Computing, Hung Hom, Kowloon Hong Kong, 99907 CHINA Abstract validations have demonstrated that attention models have notable ability in various tasks, such as content aware Face recognition is an important area of research in cognitive science and machine learning. This is the first paper utilizing resizing (Avidan et al., 2007), quality assessment (Zhong et deep learning techniques to model human ’s attention for face al., 2010), and face recognition (Cappelli, et al., 2007) recognition. In our attention model based on bilinear deep (Fang, et al., 2011). belief network (DBDN), the discriminant information is This paper models human’s attention for face recognition maximized in a frame of simulating the human visual cortex