• Submitter Login
    View Item 
    •   Bilkent Repository
    • University Centres and Units
    • Work in Progress
    • Bilkent University - Scopus Publications
    • Research Paper
    • View Item
    •   Bilkent Repository
    • University Centres and Units
    • Work in Progress
    • Bilkent University - Scopus Publications
    • Research Paper
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Two-person interaction recognition via spatial multiple instance embedding

    Thumbnail
    View/Open
    Full printable version (3.175Mb)
    Date Issued
    2015
    Author
    Sener F.
    Ikizler-Cinbis, N.
    Show full item record
    Please cite this item using this persistent URL
    http://hdl.handle.net/11693/20726
    Journal
    Journal of Visual Communication and Image Representation
    Published as
    http://dx.doi.org/10.1016/j.jvcir.2015.07.016
    Collections
    • Research Paper [7145]
    Publisher
    Academic Press Inc.
    Abstract
    Abstract In this work, we look into the problem of recognizing two-person interactions in videos. Our method integrates multiple visual features in a weakly supervised manner by utilizing an embedding-based multiple instance learning framework. In our proposed method, first, several visual features that capture the shape and motion of the interacting people are extracted from each detected person region in a video. Then, two-person visual descriptors are formed. Since the relative spatial locations of interacting people are likely to complement the visual descriptors, we propose to use spatial multiple instance embedding, which implicitly incorporates the distances between people into the multiple instance learning process. Experimental results on two benchmark datasets validate that using two-person visual descriptors together with spatial multiple instance learning offers an effective way for inferring the type of the interaction. © 2015 Elsevier Inc.

    Related items

    Showing items related by title, author, creator and subject.

    • Thumbnail

      A hand gesture recognition technique for human-computer interaction 

      Kiliboz, N.Ç.; Güdükbay, U. (Academic Press Inc., 2015)
      We propose an approach to recognize trajectory-based dynamic hand gestures in real time for human-computer interaction (HCI). We also introduce a fast learning mechanism that does not require extensive training data to ...
    • Thumbnail

      Real time hand gesture recognition for computer interaction 

      Farooq J.; Ali, M.B. (IEEE Computer Society, 2014)
      Hand gesture recognition is a natural and intuitive way to interact with the computer, since interactions with the computer can be increased through multidimensional use of hand gestures as compare to other input methods. ...
    • Thumbnail

      Vision-based continuous Graffiti™-like text entry system 

      Erdem I.A.; Erdem, M.E.; Atalay V.; Çetin, A.E. (2004)
      It is now possible to design real-time, low-cost computer version systems even in personal computers due to the recent advances in electronics and the computer industry. Due to this reason, it is feasible to develop ...

    BİLKENT UNIVERSITY

    Copyright © Bilkent University - Library Technical Services | 06800 Bilkent, Ankara TURKEY
    If you have trouble accessing this page and need to request an alternate format, contact the webmaster. Phone: (312) 290 1771

    Contact Us | Send Feedback | Off-Campus Access
     

    Browse

    All of BilkentCommunities & CollectionsTitleAuthorAdvisorIssue DateSubjectTypeDepartmentThis CollectionTitleAuthorAdvisorIssue DateSubjectTypeDepartment

    My Account

    Submitter Login

    Statistics

    View Usage Statistics

    BİLKENT UNIVERSITY

    Copyright © Bilkent University - Library Technical Services | 06800 Bilkent, Ankara TURKEY
    If you have trouble accessing this page and need to request an alternate format, contact the webmaster. Phone: (312) 290 1771

    Contact Us | Send Feedback | Off-Campus Access