DocumentCode :
3003430
Title :
Learning partially-observed hidden conditional random fields for facial expression recognition
Author :
Kai-Yueh Chang ; Tyng-Luh Liu ; Shang-Hong Lai
Author_Institution :
Inst. of Inf. Sci., Acad. Sinica, Taipei, Taiwan
fYear :
2009
fDate :
20-25 June 2009
Firstpage :
533
Lastpage :
540
Abstract :
This paper describes a novel graphical model approach to seamlessly coupling and simultaneously analyzing facial emotions and the action units. Our method is based on the hidden conditional random fields (HCRFs) where we link the output class label to the underlying emotion of a facial expression sequence, and connect the hidden variables to the image frame-wise action units. As HCRFs are formulated with only the clique constraints, their labeling for hidden variables often lacks a coherent and meaningful configuration. We resolve this matter by introducing a partially-observed HCRF model, and establish an efficient scheme via Bethe energy approximation to overcome the resulting difficulties in training. For real-time applications, we also propose an online implementation to perform incremental inference with satisfactory accuracy.
Keywords :
approximation theory; emotion recognition; face recognition; image sequences; learning (artificial intelligence); random processes; Bethe energy approximation; clique constraint; emotion recognition; facial expression recognition; graphical model; image frame-wise action unit; image sequence; incremental inference; machine learning; partially-observed hidden conditional random field; Computer science; Emotion recognition; Face recognition; Facial features; Graphical models; Image sequences; Independent component analysis; Information analysis; Information science; Labeling;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on
Conference_Location :
Miami, FL
ISSN :
1063-6919
Print_ISBN :
978-1-4244-3992-8
Type :
conf
DOI :
10.1109/CVPR.2009.5206612
Filename :
5206612
Link To Document :
بازگشت