Kernel conditional ordinal random fields for temporal segmentation of facial action units

Ognjen Rudovic; Vladimir Pavlovic; Maja Pantic

doi:10.1007/978-3-642-33868-7_26

Kernel conditional ordinal random fields for temporal segmentation of facial action units

Ognjen Rudovic, Vladimir Pavlovic, Maja Pantic

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

14 Citations (Scopus)

70 Downloads (Pure)

Abstract

We consider the problem of automated recognition of temporal segments (neutral, onset, apex and offset) of Facial Action Units. To this end, we propose the Laplacian-regularized Kernel Conditional Ordinal Random Field model. In contrast to standard modeling approaches to recognition of AUs’ temporal segments, which treat each segment as an independent class, the proposed model takes into account ordinal relations between the segments. The experimental results evidence the effectiveness of such an approach.

Original language	Undefined
Title of host publication	Computer Vision – ECCV 2012 Workshops and Demonstrations
Place of Publication	Berlin
Publisher	Springer
Pages	260-269
Number of pages	10
ISBN (Print)	978-3-642-33867-0
DOIs	https://doi.org/10.1007/978-3-642-33868-7_26
Publication status	Published - 7 Oct 2012
Event	Computer Vision – ECCV 2012 Workshops and Demonstrations - Florence, Italy Duration: 7 Oct 2012 → 11 Oct 2012

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer Verlag
Volume	7584
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Workshop

Workshop	Computer Vision – ECCV 2012 Workshops and Demonstrations
Period	7/10/12 → 11/10/12
Other	07-11 Oct 2012

Keywords

EWI-22968
HMI-MI: MULTIMODAL INTERACTIONS
ordinal regres- sion
conditional random eld
IR-84314
histogram intersection kernel
Action units
METIS-296258
kernel locality preserving projections

Access to Document

10.1007/978-3-642-33868-7_26

Pantic_Kernel_Conditional_Ordinal
open
Pantic12kernel
open

Cite this

@inproceedings{ef6cfc0409d44d789e05e50fdb01c10e,

title = "Kernel conditional ordinal random fields for temporal segmentation of facial action units",

abstract = "We consider the problem of automated recognition of temporal segments (neutral, onset, apex and offset) of Facial Action Units. To this end, we propose the Laplacian-regularized Kernel Conditional Ordinal Random Field model. In contrast to standard modeling approaches to recognition of AUs{\textquoteright} temporal segments, which treat each segment as an independent class, the proposed model takes into account ordinal relations between the segments. The experimental results evidence the effectiveness of such an approach.",

keywords = "EWI-22968, HMI-MI: MULTIMODAL INTERACTIONS, ordinal regres- sion, conditional random eld, IR-84314, histogram intersection kernel, Action units, METIS-296258, kernel locality preserving projections",

author = "Ognjen Rudovic and Vladimir Pavlovic and Maja Pantic",

note = "10.1007/978-3-642-33868-7_26 ; null ; Conference date: 07-10-2012 Through 11-10-2012",

year = "2012",

month = oct,

day = "7",

doi = "10.1007/978-3-642-33868-7_26",

language = "Undefined",

isbn = "978-3-642-33867-0",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "260--269",

booktitle = "Computer Vision – ECCV 2012 Workshops and Demonstrations",

}

Rudovic, O, Pavlovic, V & Pantic, M 2012, Kernel conditional ordinal random fields for temporal segmentation of facial action units. in Computer Vision – ECCV 2012 Workshops and Demonstrations. Lecture Notes in Computer Science, vol. 7584, Springer, Berlin, pp. 260-269, Computer Vision – ECCV 2012 Workshops and Demonstrations, 7/10/12. https://doi.org/10.1007/978-3-642-33868-7_26

Kernel conditional ordinal random fields for temporal segmentation of facial action units. / Rudovic, Ognjen; Pavlovic, Vladimir; Pantic, Maja.

Computer Vision – ECCV 2012 Workshops and Demonstrations. Berlin : Springer, 2012. p. 260-269 (Lecture Notes in Computer Science; Vol. 7584).

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

TY - GEN

T1 - Kernel conditional ordinal random fields for temporal segmentation of facial action units

AU - Rudovic, Ognjen

AU - Pavlovic, Vladimir

AU - Pantic, Maja

N1 - 10.1007/978-3-642-33868-7_26

PY - 2012/10/7

Y1 - 2012/10/7

N2 - We consider the problem of automated recognition of temporal segments (neutral, onset, apex and offset) of Facial Action Units. To this end, we propose the Laplacian-regularized Kernel Conditional Ordinal Random Field model. In contrast to standard modeling approaches to recognition of AUs’ temporal segments, which treat each segment as an independent class, the proposed model takes into account ordinal relations between the segments. The experimental results evidence the effectiveness of such an approach.

AB - We consider the problem of automated recognition of temporal segments (neutral, onset, apex and offset) of Facial Action Units. To this end, we propose the Laplacian-regularized Kernel Conditional Ordinal Random Field model. In contrast to standard modeling approaches to recognition of AUs’ temporal segments, which treat each segment as an independent class, the proposed model takes into account ordinal relations between the segments. The experimental results evidence the effectiveness of such an approach.

KW - EWI-22968

KW - HMI-MI: MULTIMODAL INTERACTIONS

KW - ordinal regres- sion

KW - conditional random eld

KW - IR-84314

KW - histogram intersection kernel

KW - Action units

KW - METIS-296258

KW - kernel locality preserving projections

U2 - 10.1007/978-3-642-33868-7_26

DO - 10.1007/978-3-642-33868-7_26

M3 - Conference contribution

SN - 978-3-642-33867-0

T3 - Lecture Notes in Computer Science

SP - 260

EP - 269

BT - Computer Vision – ECCV 2012 Workshops and Demonstrations

PB - Springer

CY - Berlin

Y2 - 7 October 2012 through 11 October 2012

ER -