Learning a non-linear knowledge transfer model for cross-view action recognition

Hossein Rahmani, Ajmal Mian

    Research output: Chapter in Book/Conference paperConference paper

    78 Citations (Scopus)

    Abstract

    © 2015 IEEE. This paper concerns action recognition from unseen and unknown views. We propose unsupervised learning of a non-linear model that transfers knowledge from multiple views to a canonical view. The proposed Non-linear Knowledge Transfer Model (NKTM) is a deep network, with weight decay and sparsity constraints, which finds a shared high-level virtual path from videos captured from different unknown viewpoints to the same canonical view. The strength of our technique is that we learn a single NKTM for all actions and all camera viewing directions. Thus, NKTM does not require action labels during learning and knowledge of the camera viewpoints during training or testing. NKTM is learned once only from dense trajectories of synthetic points fitted to mocap data and then applied to real video data. Trajectories are coded with a general codebook learned from the same mocap data. NKTM is scalable to new action classes and training data as it does not require re-learning. Experiments on the IXMAS and N-UCLA datasets show that NKTM outperforms existing state-of-the-art methods for cross-view action recognition.
    Original languageEnglish
    Title of host publication2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
    Place of PublicationUSA
    PublisherIEEE, Institute of Electrical and Electronics Engineers
    Pages2458-2466
    Volume7
    ISBN (Print)9781467369640
    DOIs
    Publication statusPublished - 2015
    Event2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) - Boston, MA, USA, Boston, United States
    Duration: 7 Jun 201512 Jun 2015

    Conference

    Conference2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
    CountryUnited States
    CityBoston
    Period7/06/1512/06/15

    Fingerprint Dive into the research topics of 'Learning a non-linear knowledge transfer model for cross-view action recognition'. Together they form a unique fingerprint.

  • Cite this

    Rahmani, H., & Mian, A. (2015). Learning a non-linear knowledge transfer model for cross-view action recognition. In 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (Vol. 7, pp. 2458-2466). IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/CVPR.2015.7298860