DocumentCode
420217
Title
Video grammar for locating named people
Author
Yang, Jun ; Hauptmann, Alexander
Author_Institution
Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
fYear
2004
fDate
7-11 June 2004
Firstpage
216
Lastpage
217
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;
fLanguage
English
Publisher
ieee
Conference_Titel
Digital Libraries, 2004. Proceedings of the 2004 Joint ACM/IEEE Conference on
Print_ISBN
1-58113-832-6
Type
conf
DOI
10.1109/JCDL.2004.1336124
Filename
1336124
Link To Document