Stacked Progressive Auto-Encoders (SPAE) for Face Recognition Across Poses

• Published in: 2014 IEEE Conference on Computer Vision and Pattern Recognition pp. 1883 - 1890
• Main Authors: Kan, Meina, Shan, Shiguang, Chang, Hong, Chen, Xilin
• Format: Conference Proceeding Journal Article
• Language: English
• Published: IEEE 01.06.2014
• Subjects: Computer vision; Conferences; Decoding; Deep network; Face; Face recognition; face recognition across pose; Networks; Nonlinearity; Pattern recognition; Solid modeling; Stacked Progressive Auto-Encoders; Stacking; Tasks; Three-dimensional displays; Training; Transforms

Identifying subjects with variations caused by poses is one of the most challenging tasks in face recognition, since the difference in appearances caused by poses may be even larger than the difference due to identity. Inspired by the observation that pose variations change non-linearly but smoothly...