Joint Unsupervised Deformable Spatio-Temporal Alignment of Sequences

L. Zafeiriou, E. Antonakos, S. Zafeiriou, Maja Pantic

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

    3 Citations (Scopus)
    38 Downloads (Pure)


    Typically, the problems of spatial and temporal alignment of sequences are considered disjoint. That is, in order to align two sequences, a methodology that (non)-rigidly aligns the images is first applied, followed by temporal alignment of the obtained aligned images. In this paper, we propose the first, to the best of our knowledge, methodology that can jointly spatio-temporally align two sequences, which display highly deformable texture-varying objects. We show that by treating the problems of deformable spatial and temporal alignment jointly, we achieve better results than considering the problems independent. Furthermore, we show that deformable spatio-temporal alignment of faces can be performed in an unsupervised manner (i.e., without employing face trackers or building person-specific deformable models).
    Original languageUndefined
    Title of host publicationProceedings of IEEE International Conference on Computer Vision & Pattern Recognition (CVPR 2016)
    Place of PublicationUSA
    PublisherIEEE Computer Vision and Pattern Recognition
    Number of pages9
    ISBN (Print)978-1-4673-8852-8
    Publication statusPublished - Jun 2016
    Event29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016 - Las Vegas, NV, USA, Las Vegas, United States
    Duration: 26 Jun 20161 Jul 2016
    Conference number: 29


    Conference29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016
    Abbreviated titleCVPR 2016
    Country/TerritoryUnited States
    CityLas Vegas
    Other29 June - 1 July 2016


    • deformable spatial and temporal alignment of sequences
    • HMI-HF: Human Factors
    • EWI-27132

    Cite this