BROWSE
Detail
Journal Article
Facial Attribute Recognition by Recurrent Learning With Visual Fixation
Cited 13 time in 
Download 71 time
Share 
Download 71 time
Share
- Authors
- Jinhyeok Jang, Hyunjoong Cho, Jaehong Kim, Jaeyeon Lee, Seungjoon Yang
- Issue Date
- 2019-02
- Citation
- IEEE Transactions on Cybernetics, v.49, no.2, pp.616-625
- ISSN
- 2168-2267
- Publisher
- IEEE
- Language
- English
- Type
- Journal Article
- Project Code
- 17HS6500, Development of Human-care Robot Technology for Aging Society, Lee Jae Yeon
- Abstract
- This paper presents a recurrent learning-based facial attribute recognition method that mimics human observers' visual fixation. The concentrated views of a human observer while focusing and exploring parts of a facial image over time are generated and fed into a recurrent network. The network makes a decision concerning facial attributes based on the features gleaned from the observer's visual fixations. Experiments on facial expression, gender, and age datasets show that applying visual fixation to recurrent networks improves recognition rates significantly. The proposed method not only outperforms state-of-the-art recognition methods based on static facial features, but also those based on dynamic facial features.