View alignment with dynamically updated affine tracking

Fernando de la Torre (Lead / Corresponding author), Shaogang Gong (Lead / Corresponding author), Stephen McKenna (Lead / Corresponding author)

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    6 Citations (Scopus)

    Abstract

    The authors propose a framework for fast view alignment using adaptive affine tracking. They address the issue of modelling both shape and texture information in eigenspace for view alignment. They present an effective bootstrapping process based on colour segmentation and selective attention. They recover affine parameters with dynamic updates to the eigenspace using most recent history and perform predictions in parameter space. Experimental results are given to illustrate their approach
    Original languageEnglish
    Title of host publicationThird IEEE International Conference on Automatic Face and Gesture Recognition
    Subtitle of host publicationProceedings
    Place of PublicationPiscataway, NJ
    PublisherIEEE
    Pages510-515
    Number of pages6
    ISBN (Print)0818683449
    DOIs
    Publication statusPublished - 1998
    Event3rd IEEE International Conference on Automatic Face and Gesture Recognition - New Public Hall, Nara, Japan
    Duration: 14 Apr 199816 Apr 1998

    Conference

    Conference3rd IEEE International Conference on Automatic Face and Gesture Recognition
    Abbreviated titleFG'98
    CountryJapan
    CityNara
    Period14/04/9816/04/98

      Fingerprint

    Cite this

    de la Torre, F., Gong, S., & McKenna, S. (1998). View alignment with dynamically updated affine tracking. In Third IEEE International Conference on Automatic Face and Gesture Recognition : Proceedings (pp. 510-515). IEEE. https://doi.org/10.1109/AFGR.1998.670999