Abstract We introduced an algorithm for sequence alignment, based on maximizing local space-time correlations. Our algorithm aligns sequences of the same action performed at different times and places by different people, possibly at different speeds, and wearing different clothes. Moreover, the algorithm offers a unified approach to the problem of sequence alignment for a wide range of scenarios (e.g., sequence pairs taken with stationary or jointly moving cameras, with the same or different photometric properties, with or without moving objects). Our algorithm is applied directly to the dense space-time intensity information of the two sequences (or to filtered versions of them). This is done without prior segmentation of foreground moving objects, and without prior detection of corresponding features across the sequences. Examples of challenging sequences with complex actions are shown, including ballet dancing, actions in the presence of other complex scene dynamics (clutter), as well as multi-sensor sequence pairs.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Aligning Sequences and Actions by Maximizing Space-Time Correlations


    Beteiligte:
    Ukrainitz, Yaron (Autor:in) / Irani, Michal (Autor:in)


    Erscheinungsdatum :

    2006-01-01


    Format / Umfang :

    13 pages





    Medientyp :

    Aufsatz/Kapitel (Buch)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Aligning Sequences and Actions by Maximizing Space-Time Correlations

    Ukrainitz, Y. / Irani, M. | British Library Conference Proceedings | 2006


    Aligning Non-Overlapping Sequences

    Caspi, Y. / Irani, M. | British Library Online Contents | 2002



    Transportation network design for maximizing space–time accessibility

    Tong, Lu / Zhou, Xuesong / Miller, Harvey J. | Elsevier | 2015


    Actions as space-time shapes

    Blank, M. / Gorelick, L. / Shechtman, E. et al. | IEEE | 2005