View-constrained latent variable model for multi-view facial expression classification

Stefanos Eleftheriadis; Ognjen Rudovic; Maja  Pantic

doi:10.1007/978-3-319-14364-4_28

View-constrained latent variable model for multi-view facial expression classification

Stefanos Eleftheriadis, Ognjen Rudovic, Maja Pantic

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

5 Citations (Scopus)

3 Downloads (Pure)

Abstract

We propose a view-constrained latent variable model for multi-view facial expression classification. In this model, we first learn a discriminative manifold shared by multiple views of facial expressions, followed by the expression classification in the shared manifold. For learning, we use the expression data from multiple views, however, the inference is performed using the data from a single view. Our experiments on data of posed and spontaneously displayed facial expressions show that the proposed approach outperforms the state-of-the-art methods for multi-view facial expression classification, and several state-of-the-art methods for multi-view learning.

Original language	English
Title of host publication	Advances in Visual Computing
Subtitle of host publication	10th International Symposium, ISVC 2014, Las Vegas, NV, USA, December 8-10, 2014, Proceedings
Editors	George Bebis, Richard Boyle, Bahram Parvin, Darko Koracin
Place of Publication	Cham
Publisher	Springer
Pages	292-303
Number of pages	12
Volume	Part II
ISBN (Electronic)	978-3-319-14364-4
ISBN (Print)	978-3-319-14363-7
DOIs	https://doi.org/10.1007/978-3-319-14364-4_28
Publication status	Published - Dec 2014
Event	10th International Symposium on Visual Computing, ISVC 2014 - Las Vegas, United States Duration: 8 Dec 2014 → 10 Dec 2014 Conference number: 10

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer
Volume	8888
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	10th International Symposium on Visual Computing, ISVC 2014
Abbreviated title	ISVC
Country	United States
City	Las Vegas
Period	8/12/14 → 10/12/14

Keywords

HMI-HF: Human Factors
EWI-25810
METIS-309929
EC Grant Agreement nr.: FP7/2007-2013
IR-94677
EC Grant Agreement nr.: FP7/611153

Access to Document

10.1007/978-3-319-14364-4_28

Fingerprint Dive into the research topics of 'View-constrained latent variable model for multi-view facial expression classification'. Together they form a unique fingerprint.

Cite this

Eleftheriadis, S., Rudovic, O., & Pantic, M. (2014). View-constrained latent variable model for multi-view facial expression classification. In G. Bebis, R. Boyle, B. Parvin, & D. Koracin (Eds.), Advances in Visual Computing: 10th International Symposium, ISVC 2014, Las Vegas, NV, USA, December 8-10, 2014, Proceedings (Vol. Part II, pp. 292-303). (Lecture Notes in Computer Science; Vol. 8888). Cham: Springer. https://doi.org/10.1007/978-3-319-14364-4_28

Eleftheriadis, Stefanos ; Rudovic, Ognjen ; Pantic, Maja . / View-constrained latent variable model for multi-view facial expression classification. Advances in Visual Computing: 10th International Symposium, ISVC 2014, Las Vegas, NV, USA, December 8-10, 2014, Proceedings. editor / George Bebis ; Richard Boyle ; Bahram Parvin ; Darko Koracin. Vol. Part II Cham : Springer, 2014. pp. 292-303 (Lecture Notes in Computer Science).

@inproceedings{95ed87b44d0947a2981a0cde2fe1e77b,

title = "View-constrained latent variable model for multi-view facial expression classification",

abstract = "We propose a view-constrained latent variable model for multi-view facial expression classification. In this model, we first learn a discriminative manifold shared by multiple views of facial expressions, followed by the expression classification in the shared manifold. For learning, we use the expression data from multiple views, however, the inference is performed using the data from a single view. Our experiments on data of posed and spontaneously displayed facial expressions show that the proposed approach outperforms the state-of-the-art methods for multi-view facial expression classification, and several state-of-the-art methods for multi-view learning.",

keywords = "HMI-HF: Human Factors, EWI-25810, METIS-309929, EC Grant Agreement nr.: FP7/2007-2013, IR-94677, EC Grant Agreement nr.: FP7/611153",

author = "Stefanos Eleftheriadis and Ognjen Rudovic and Maja Pantic",

note = "eemcs-eprint-25810",

year = "2014",

month = "12",

doi = "10.1007/978-3-319-14364-4_28",

language = "English",

isbn = "978-3-319-14363-7",

volume = "Part II",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "292--303",

editor = "George Bebis and Richard Boyle and Bahram Parvin and Darko Koracin",

booktitle = "Advances in Visual Computing",

}

Eleftheriadis, S, Rudovic, O & Pantic, M 2014, View-constrained latent variable model for multi-view facial expression classification. in G Bebis, R Boyle, B Parvin & D Koracin (eds), Advances in Visual Computing: 10th International Symposium, ISVC 2014, Las Vegas, NV, USA, December 8-10, 2014, Proceedings. vol. Part II, Lecture Notes in Computer Science, vol. 8888, Springer, Cham, pp. 292-303, 10th International Symposium on Visual Computing, ISVC 2014, Las Vegas, United States, 8/12/14. https://doi.org/10.1007/978-3-319-14364-4_28

View-constrained latent variable model for multi-view facial expression classification. / Eleftheriadis, Stefanos; Rudovic, Ognjen; Pantic, Maja .

Advances in Visual Computing: 10th International Symposium, ISVC 2014, Las Vegas, NV, USA, December 8-10, 2014, Proceedings. ed. / George Bebis; Richard Boyle; Bahram Parvin; Darko Koracin. Vol. Part II Cham : Springer, 2014. p. 292-303 (Lecture Notes in Computer Science; Vol. 8888).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - View-constrained latent variable model for multi-view facial expression classification

AU - Eleftheriadis, Stefanos

AU - Rudovic, Ognjen

AU - Pantic, Maja

N1 - eemcs-eprint-25810

PY - 2014/12

Y1 - 2014/12

N2 - We propose a view-constrained latent variable model for multi-view facial expression classification. In this model, we first learn a discriminative manifold shared by multiple views of facial expressions, followed by the expression classification in the shared manifold. For learning, we use the expression data from multiple views, however, the inference is performed using the data from a single view. Our experiments on data of posed and spontaneously displayed facial expressions show that the proposed approach outperforms the state-of-the-art methods for multi-view facial expression classification, and several state-of-the-art methods for multi-view learning.

AB - We propose a view-constrained latent variable model for multi-view facial expression classification. In this model, we first learn a discriminative manifold shared by multiple views of facial expressions, followed by the expression classification in the shared manifold. For learning, we use the expression data from multiple views, however, the inference is performed using the data from a single view. Our experiments on data of posed and spontaneously displayed facial expressions show that the proposed approach outperforms the state-of-the-art methods for multi-view facial expression classification, and several state-of-the-art methods for multi-view learning.

KW - HMI-HF: Human Factors

KW - EWI-25810

KW - METIS-309929

KW - EC Grant Agreement nr.: FP7/2007-2013

KW - IR-94677

KW - EC Grant Agreement nr.: FP7/611153

U2 - 10.1007/978-3-319-14364-4_28

DO - 10.1007/978-3-319-14364-4_28

M3 - Conference contribution

SN - 978-3-319-14363-7

VL - Part II

T3 - Lecture Notes in Computer Science

SP - 292

EP - 303

BT - Advances in Visual Computing

A2 - Bebis, George

A2 - Boyle, Richard

A2 - Parvin, Bahram

A2 - Koracin, Darko

PB - Springer

CY - Cham

ER -

Eleftheriadis S, Rudovic O, Pantic M. View-constrained latent variable model for multi-view facial expression classification. In Bebis G, Boyle R, Parvin B, Koracin D, editors, Advances in Visual Computing: 10th International Symposium, ISVC 2014, Las Vegas, NV, USA, December 8-10, 2014, Proceedings. Vol. Part II. Cham: Springer. 2014. p. 292-303. (Lecture Notes in Computer Science). https://doi.org/10.1007/978-3-319-14364-4_28