Title :
Video grammar for locating named people
Author :
Yang, Jun ; Hauptmann, Alexander
Author_Institution :
Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
Abstract :
Finding a named person in broadcast news video is important to video retrieval. Relying on the text information such as video transcript and OCR text, this task suffers from the temporal mismatch between a person´s visual appearance and his/her name occurred in text. By exploring video grammar on the concurrence pattern between faces and names, we propose an extended text-based IR method to overcome this problem and yield superior performance.
Keywords :
broadcasting; grammars; image retrieval; optical character recognition; video signal processing; OCR text; concurrence pattern; text-based information retrieval; video grammar; video retrieval; video transcript; Cellular neural networks; Computer science; Degradation; Digital video broadcasting; Frequency; Information retrieval; Optical character recognition software; Software libraries; Testing; Timing;
Conference_Titel :
Digital Libraries, 2004. Proceedings of the 2004 Joint ACM/IEEE Conference on
Print_ISBN :
1-58113-832-6
DOI :
10.1109/JCDL.2004.1336124
