The appearance of dynamic scenes is often largely governed by a latent low-dimensional dynamic process. We show how to learn a mapping from video frames to this low-dimensional representation by exploiting the temporal coherence between frames and supervision from a user. This function maps the frames of the video to a low-dimensional sequence that evolves according to Markovian dynamics. This ensures that the recovered low-dimensional sequence represents a physically meaningful process. We relate our algorithm to manifold learning, semi-supervised learning, and system identification, and demonstrate it on the tasks of tracking 3D rigid objects, deformable bodies, and articulated bodies. We also show how to use the inverse of this mapping to manipulate video.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Learning appearance manifolds from video


    Contributors:
    Rahimi, A. (author) / Darrell, T. (author) / Recht, B. (author)


    Publication date :

    2005-01-01


    Size :

    3372712 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Video-based face recognition using probabilistic appearance manifolds

    Kuang-Chih Lee, / Ho, J. / Ming-Hsuan Yang, et al. | IEEE | 2003


    Video-Based Face Recognition Using Probabilistic Appearance Manifolds

    Lee, K.-C. / Ho, J. / Yang, M.-H. et al. | British Library Conference Proceedings | 2003




    Learning Appearance and Transparency Manifolds of Occluded Objects in Layers

    Frey, B. / Jojic, N. / Kannan, A. et al. | British Library Conference Proceedings | 2003