Now showing items 1-7 of 7

    • Bilkent University at TRECVID 2005 

      Aksoy, S.; Avci, A.; Balçik, E.; Çavuş Ö.; Duygulu P.; Karaman, Z.; Kavak P.; Kaynak, C.; Küçükayvaz, E.; Öcalan Ç.; Yildiz P. (National Institute of Standards and Technology, 2005)
      We describe our second-time participation, that includes one high-level feature extraction run, and three manual and one interactive search runs, to the TRECVID video retrieval evaluation. All of these runs have used a ...
    • Bilkent university at TRECVID 2006 

      Aksoy, S.; Duygulu P.; Akçay G.; Ataer, E.; Baştan, M.; Can, T.; Cavuş Ö.; Doǧgrusöz, E.; Gökalp, D.; Akaydin, A.; Akoǧlu L.; Angin P.; Cinbiş G.; Gür, T.; Ünlü, M. (National Institute of Standards and Technology, 2006)
      We describe our third participation, that includes one high-level feature extraction run, and two manual and one interactive search runs, to the TRECVID video retrieval evaluation. All of these runs have used a system ...
    • Bilkent University at TRECVID 2007 

      Aksoy, S.; Duygulu P.; Aksoy, C.; Aydin, E.; G̈unaydin, D.; Hadimli, K.; Koç L.; Olgun, Y.; Orhan, C.; Yakin G. (National Institute of Standards and Technology, 2007)
      We describe our fourth participation, that includes two high-level feature extraction runs, and one manual search run, to the TRECVID video retrieval evaluation. All of these runs have used a system trained on the common ...
    • HandVR: a hand-gesture-based interface to a video retrieval system 

      Genç, S.; Baştan M.; Güdükbay U.; Atalay, V.; Ulusoy, Ö. (Springer U K, 2015)
      Using one’s hands in human–computer interaction increases both the effectiveness of computer usage and the speed of interaction. One way of accomplishing this goal is to utilize computer vision techniques to develop ...
    • A relevance feedback technique for multimodal retrieval of news videos 

      Aksoy, S.; Çavuş Ö. (2005)
      Content-based retrieval in news video databases has become an important task with the availability of large quantities of data in both public and proprietary archives. We describe a relevance feedback technique that captures ...
    • Searching for complex human activities with no visual examples 

      Ikizler, N.; Forsyth, D.A. (2008)
      We describe a method of representing human activities that allows a collection of motions to be queried without examples, using a simple and effective query language. Our approach is based on units of activity at segments ...
    • Two-person interaction recognition via spatial multiple instance embedding 

      Sener F.; Ikizler-Cinbis, N. (Academic Press Inc., 2015)
      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 ...