Supervised super-vector encoding for facial expression recognition

Usman Tariq; Jianchao Yang; Thomas S. Huang

doi:10.1016/j.patrec.2014.05.011

Supervised super-vector encoding for facial expression recognition

Usman Tariq, Jianchao Yang, Thomas S. Huang

Research output: Contribution to journal › Article › peer-review

Abstract

Expression recognition from faces with varying pose and illumination conditions is a challenging research area with growing interest. In this paper, we develop a novel supervised super-vector encoding framework to learn discriminative image feature representations. The framework is then validated on the Multi-PIE and BU3D-FE databases for multi-view facial expression recognition. Extensive experiments show that our supervised framework gives significant improvement over the unsupervised counterpart and outperforms the state-of-the-arts.

Original language	English (US)
Pages (from-to)	89-95
Number of pages	7
Journal	Pattern Recognition Letters
Volume	46
DOIs	https://doi.org/10.1016/j.patrec.2014.05.011
State	Published - Sep 1 2014
Externally published	Yes

Keywords

Face biometrics
Facial expression recognition
GMM learning

ASJC Scopus subject areas

Software
Signal Processing
Computer Vision and Pattern Recognition
Artificial Intelligence

Online availability

10.1016/j.patrec.2014.05.011

Library availability

Discover UIUC Full Text

Cite this

@article{f82c0e8d21e84cd98b8b981ea239ceb6,

title = "Supervised super-vector encoding for facial expression recognition",

abstract = "Expression recognition from faces with varying pose and illumination conditions is a challenging research area with growing interest. In this paper, we develop a novel supervised super-vector encoding framework to learn discriminative image feature representations. The framework is then validated on the Multi-PIE and BU3D-FE databases for multi-view facial expression recognition. Extensive experiments show that our supervised framework gives significant improvement over the unsupervised counterpart and outperforms the state-of-the-arts.",

keywords = "Face biometrics, Facial expression recognition, GMM learning",

author = "Usman Tariq and Jianchao Yang and Huang, {Thomas S.}",

note = "Funding Information: This work was partly supported by Intel under the Avascholar project of the Illinois-Intel Parallelism Center (I2PC) and the ONR Grant NOO0l4-12-1-0122 . This work was done at the University of Illinois at Urbana-Champaign during the PhD dissertation of the first author. Copyright: Copyright 2014 Elsevier B.V., All rights reserved.",

year = "2014",

month = sep,

day = "1",

doi = "10.1016/j.patrec.2014.05.011",

language = "English (US)",

volume = "46",

pages = "89--95",

journal = "Pattern Recognition Letters",

issn = "0167-8655",

publisher = "Elsevier B.V.",

}

TY - JOUR

T1 - Supervised super-vector encoding for facial expression recognition

AU - Tariq, Usman

AU - Yang, Jianchao

AU - Huang, Thomas S.

N1 - Funding Information: This work was partly supported by Intel under the Avascholar project of the Illinois-Intel Parallelism Center (I2PC) and the ONR Grant NOO0l4-12-1-0122 . This work was done at the University of Illinois at Urbana-Champaign during the PhD dissertation of the first author. Copyright: Copyright 2014 Elsevier B.V., All rights reserved.

PY - 2014/9/1

Y1 - 2014/9/1

N2 - Expression recognition from faces with varying pose and illumination conditions is a challenging research area with growing interest. In this paper, we develop a novel supervised super-vector encoding framework to learn discriminative image feature representations. The framework is then validated on the Multi-PIE and BU3D-FE databases for multi-view facial expression recognition. Extensive experiments show that our supervised framework gives significant improvement over the unsupervised counterpart and outperforms the state-of-the-arts.

AB - Expression recognition from faces with varying pose and illumination conditions is a challenging research area with growing interest. In this paper, we develop a novel supervised super-vector encoding framework to learn discriminative image feature representations. The framework is then validated on the Multi-PIE and BU3D-FE databases for multi-view facial expression recognition. Extensive experiments show that our supervised framework gives significant improvement over the unsupervised counterpart and outperforms the state-of-the-arts.

KW - Face biometrics

KW - Facial expression recognition

KW - GMM learning

UR - http://www.scopus.com/inward/record.url?scp=84903153357&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84903153357&partnerID=8YFLogxK

U2 - 10.1016/j.patrec.2014.05.011

DO - 10.1016/j.patrec.2014.05.011

M3 - Article

AN - SCOPUS:84903153357

SN - 0167-8655

VL - 46

SP - 89

EP - 95

JO - Pattern Recognition Letters

JF - Pattern Recognition Letters

ER -

Supervised super-vector encoding for facial expression recognition

Abstract

Keywords

ASJC Scopus subject areas

Online availability

Library availability

Related links

Fingerprint

Cite this