Incremental slow features analysis with indefinite kernel for online temporal video segmentation

Stephan Liwicki, Stefanos Zafeiriou, Maja Pantic

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

    Abstract

    Slow Feature Analysis (SFA) is a subspace learning method inspired by the human visual system, however, it is seldom seen in computer vision. Motivated by its application for unsupervised activity analysis, we develop SFA’s first implementation of online temporal video segmentation to detect episodes of motion changes. We utilize a domainspecific indefinite kernel which takes the data representation into account to introduce robustness. As our kernel is indefinite (i.e. defines instead of a Hilbert, a Krein space), we formulate SFA in Krein space. We propose an incremental kernel SFA framework which utilizes the special properties of our kernel. Finally, we employ our framework to online temporal video segmentation and perform qualitative and quantitative evaluation.
    Original languageUndefined
    Title of host publicationProceedings of the 11th Asian Conference on Computer Vision, ACCV 2012
    Place of PublicationLondon
    PublisherSpringer
    Pages162-176
    Number of pages14
    ISBN (Print)978-3-642-37443-2
    DOIs
    Publication statusPublished - Nov 2012
    Event11th Asian Conference on Computer Vision, ACCV 2012 - Daejeon, Korea, Republic of
    Duration: 5 Nov 20129 Nov 2012
    Conference number: 11

    Publication series

    NameLecture Notes in Computer Science
    PublisherSpringer Verlag
    Volume7725

    Conference

    Conference11th Asian Conference on Computer Vision, ACCV 2012
    Abbreviated titleACCV
    CountryKorea, Republic of
    CityDaejeon
    Period5/11/129/11/12

    Keywords

    • HMI-MI: MULTIMODAL INTERACTIONS
    • METIS-296219
    • IR-84323
    • EWI-22888

    Cite this