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 proceedingConference contributionAcademicpeer-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 languageUndefined
    Title of host publicationComputer Vision – ECCV 2012 Workshops and Demonstrations
    Place of PublicationBerlin
    PublisherSpringer
    Pages260-269
    Number of pages10
    ISBN (Print)978-3-642-33867-0
    DOIs
    Publication statusPublished - 7 Oct 2012
    EventComputer Vision – ECCV 2012 Workshops and Demonstrations - Florence, Italy
    Duration: 7 Oct 201211 Oct 2012

    Publication series

    NameLecture Notes in Computer Science
    PublisherSpringer Verlag
    Volume7584
    ISSN (Print)0302-9743
    ISSN (Electronic)1611-3349

    Workshop

    WorkshopComputer Vision – ECCV 2012 Workshops and Demonstrations
    Period7/10/1211/10/12
    Other07-11 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

    Cite this