Learning parts-based representation for face transition

Authors:
Xiong Li;Liwei Wang;Huanxi Liu;Yuncai Liu
Affiliations:
Shanghai Jiao Tong University, Shanghai, China;Shanghai Jiao Tong University, Shanghai, China;Shanghai Jiao Tong University, Shanghai, China;Shanghai Jiao Tong University, Shanghai, China
Venue:
Proceedings of the international conference on Multimedia
Year:
2010

Citing 4
Cited 0

Toward Automatic Simulation of Aging Effects on Face Images

IEEE Transactions on Pattern Analysis and Machine Intelligence
The CMU Pose, Illumination, and Expression (PIE) Database

FGR '02 Proceedings of the Fifth IEEE International Conference on Automatic Face and Gesture Recognition
Learning Parts-Based Representations of Data

The Journal of Machine Learning Research
Age Synthesis and Estimation via Faces: A Survey

IEEE Transactions on Pattern Analysis and Machine Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper proposes to learn parts-based face representation from real face samples and then applies it to face transition. It differs from previous works in two aspects. First, we learn flexible face decomposition from real faces unsupervisedly instead of designing face template manually, for which two simple priors are embedded into learning procedure through constrained EM formulation. Second, both face representation and transition are derived from an unified probabilistic framework. Based on the learned face representation, the face distance measurement could be defined, which enables us to synthesize face via specifying distance with respect to reference faces and depict the full transition trace of two or more given faces with distinct age, gender and race.