Back to Pinar Duygulu's homepage
 
Associating news videos with words
Integration of visual and textual data is proposed to solve the correspondence problem between video frames and associated text in order to annotate video frames with more reliable labels and descriptions.

Publications

What's news, what's not? Associating News videos with words ( .pdf )
          Pinar Duygulu and Alex Hauptmann
          The 3rd International Conference on Image and Video Retrieval (CIVR 2004),
           Ireland, July 21-23, 2004.

  Associating video frames with text ( .pdf )
          Pinar Duygulu and Howard Wactlar
          Multimedia Information Retrieval Workshop,
          in conjuction with the 26th annual SIGIR conference on Information Retrieval,
          August 1, 2003, Toronto, Canada

Linking Visual and Textual Data on Video ( .pdf )
          Pinar Duygulu, Howard Wactlar, Norman Papernick, Dorbin Ng
          Workshop on Multimedia Contents in Digital Libraries , Crete, Greece, June 2-3, 2003