Parametric temporal alignment for the detection of facial action temporal segments

Bihan Jiang, Brais Martinez, Maja Pantic

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    3 Citations (Scopus)
    18 Downloads (Pure)


    In this paper we propose the very first weakly supervised approach for detecting facial action unit temporal segments. This is achieved by means of behaviour similarity matching, where no training of dedicated classifiers is needed and the input facial behaviour episode is compared to a template. The inferred temporal segment boundaries of the test sequence are those transferred from the template sequence. To this end, a parametric temporal alignment algorithm is proposed to align a single exemplar sequence to the test sequence. The proposed strategy can accommodate flexible time warp functions, does not need to exhaustively align all frames in both sequences, and the optimal warp parameters can be found by an efficient Gauss-Newton gradient descent search. We show that our approach produces the best results to date for the problem at hand, and provides a promising opportunity to studying facial actions from a new perspective.
    Original languageEnglish
    Title of host publicationProceedings of the 25th British Machine Vision Conference (BMVC 2014)
    Place of PublicationDurham, UK
    PublisherBMVC Press
    Number of pages11
    Publication statusPublished - Sep 2014
    Event25th British Machine Vision Conference, BMVC 2014 - Nottingham, United Kingdom
    Duration: 1 Sep 20145 Sep 2014
    Conference number: 25


    Conference25th British Machine Vision Conference, BMVC 2014
    Abbreviated titleBMVC
    Country/TerritoryUnited Kingdom


    • EWI-25829
    • HMI-HF: Human Factors
    • IR-95235
    • EC Grant Agreement nr.: FP7/611153
    • METIS-309954
    • EC Grant Agreement nr.: FP7/2007-2013


    Dive into the research topics of 'Parametric temporal alignment for the detection of facial action temporal segments'. Together they form a unique fingerprint.

    Cite this