A dynamic appearance descriptor approach to facial actions temporal modeling

Both the configuration and the dynamics of facial expressions are crucial for the interpretation of human facial behavior. Yet to date, the vast majority of reported efforts in the field either do not take the dynamics of facial expressions into account, or focus only on prototypic facial expression...

Full description

Bibliographic Details
Main Authors: Jiang, Bihan, Valstar, Michel, Martinez, Brais, Pantic, Maja
Format: Article
Published: IEEE 2014
Subjects:
Online Access:https://eprints.nottingham.ac.uk/37396/
_version_ 1848795450154418176
author Jiang, Bihan
Valstar, Michel
Martinez, Brais
Pantic, Maja
author_facet Jiang, Bihan
Valstar, Michel
Martinez, Brais
Pantic, Maja
author_sort Jiang, Bihan
building Nottingham Research Data Repository
collection Online Access
description Both the configuration and the dynamics of facial expressions are crucial for the interpretation of human facial behavior. Yet to date, the vast majority of reported efforts in the field either do not take the dynamics of facial expressions into account, or focus only on prototypic facial expressions of six basic emotions. Facial dynamics can be explicitly analyzed by detecting the constituent temporal segments in Facial Action Coding System (FACS) Action Units (AUs)-onset, apex, and offset. In this paper, we present a novel approach to explicit analysis of temporal dynamics of facial actions using the dynamic appearance descriptor Local Phase Quantization from Three Orthogonal Planes (LPQ-TOP). Temporal segments are detected by combining a discriminative classifier for detecting the temporal segments on a frame-by-frame basis with Markov Models that enforce temporal consistency over the whole episode. The system is evaluated in detail over the MMI facial expression database, the UNBC-McMaster pain database, the SAL database, the GEMEP-FERA dataset in database-dependent experiments, in cross-database experiments using the Cohn-Kanade, and the SEMAINE databases. The comparison with other state-of-the-art methods shows that the proposed LPQ-TOP method outperforms the other approaches for the problem of AU temporal segment detection, and that overall AU activation detection benefits from dynamic appearance information.
first_indexed 2025-11-14T19:32:17Z
format Article
id nottingham-37396
institution University of Nottingham Malaysia Campus
institution_category Local University
last_indexed 2025-11-14T19:32:17Z
publishDate 2014
publisher IEEE
recordtype eprints
repository_type Digital Repository
spelling nottingham-373962020-05-04T16:40:52Z https://eprints.nottingham.ac.uk/37396/ A dynamic appearance descriptor approach to facial actions temporal modeling Jiang, Bihan Valstar, Michel Martinez, Brais Pantic, Maja Both the configuration and the dynamics of facial expressions are crucial for the interpretation of human facial behavior. Yet to date, the vast majority of reported efforts in the field either do not take the dynamics of facial expressions into account, or focus only on prototypic facial expressions of six basic emotions. Facial dynamics can be explicitly analyzed by detecting the constituent temporal segments in Facial Action Coding System (FACS) Action Units (AUs)-onset, apex, and offset. In this paper, we present a novel approach to explicit analysis of temporal dynamics of facial actions using the dynamic appearance descriptor Local Phase Quantization from Three Orthogonal Planes (LPQ-TOP). Temporal segments are detected by combining a discriminative classifier for detecting the temporal segments on a frame-by-frame basis with Markov Models that enforce temporal consistency over the whole episode. The system is evaluated in detail over the MMI facial expression database, the UNBC-McMaster pain database, the SAL database, the GEMEP-FERA dataset in database-dependent experiments, in cross-database experiments using the Cohn-Kanade, and the SEMAINE databases. The comparison with other state-of-the-art methods shows that the proposed LPQ-TOP method outperforms the other approaches for the problem of AU temporal segment detection, and that overall AU activation detection benefits from dynamic appearance information. IEEE 2014-02-01 Article PeerReviewed Jiang, Bihan, Valstar, Michel, Martinez, Brais and Pantic, Maja (2014) A dynamic appearance descriptor approach to facial actions temporal modeling. IEEE Transactions on Cybernetics, 44 (2). pp. 161-174. ISSN 2168-2275 Facial dynamics action unit detection dynamic appearance descriptors LPQ-TOP temporal segment detection http://ieeexplore.ieee.org/document/6504484/ doi:10.1109/TCYB.2013.2249063 doi:10.1109/TCYB.2013.2249063
spellingShingle Facial dynamics
action unit detection
dynamic appearance descriptors
LPQ-TOP
temporal segment detection
Jiang, Bihan
Valstar, Michel
Martinez, Brais
Pantic, Maja
A dynamic appearance descriptor approach to facial actions temporal modeling
title A dynamic appearance descriptor approach to facial actions temporal modeling
title_full A dynamic appearance descriptor approach to facial actions temporal modeling
title_fullStr A dynamic appearance descriptor approach to facial actions temporal modeling
title_full_unstemmed A dynamic appearance descriptor approach to facial actions temporal modeling
title_short A dynamic appearance descriptor approach to facial actions temporal modeling
title_sort dynamic appearance descriptor approach to facial actions temporal modeling
topic Facial dynamics
action unit detection
dynamic appearance descriptors
LPQ-TOP
temporal segment detection
url https://eprints.nottingham.ac.uk/37396/
https://eprints.nottingham.ac.uk/37396/
https://eprints.nottingham.ac.uk/37396/