Skip to content

Detail of publication

Citation

Iyengar, G. and Duygulu, P. and Feng, S. and Ircing, P. and Khudanpur, S. and Klakow, D. and Krause, M. and Manmatha, R. and Nock, H. and Petkova, D. and Pytlik, B. and Virga, P. : Joint visual-text modeling for automatic retrieval of multimedia documents . Proceedings of the 13th ACM international conference on Multimedia, p. 21-30, ACM Press, New York, NY, 2005.

Abstract

The paper describes a novel approach for jointly modeling the text and the visual components of multimedia documents for the purpose of information retrieval(IR). It proposes a novel framework where individual components are developed to model different relationships between documents and queries and then combined into a joint retrieval framework.

Detail of publication

Title: Joint visual-text modeling for automatic retrieval of multimedia documents
Author: Iyengar, G. ; Duygulu, P. ; Feng, S. ; Ircing, P. ; Khudanpur, S. ; Klakow, D. ; Krause, M. ; Manmatha, R. ; Nock, H. ; Petkova, D. ; Pytlik, B. ; Virga, P.
Language: English
Date of publication: 6 Nov 2005
Year: 2005
Type of publication: Papers in proceedings of reviewed conferences
Title of journal or book: Proceedings of the 13th ACM international conference on Multimedia
Page: 21 - 30
ISBN: 1-59593-044-2
Publisher: ACM Press
Address: New York, NY
Date: 6 Nov 2005 - 12 Nov 2005
/ /

Keywords

Joint Visual-Text Models, TRECVID, Multimedia Retrieval Models

BibTeX

@INPROCEEDINGS{IyengarG_2005_Jointvisual-text,
 author = {Iyengar, G. and Duygulu, P. and Feng, S. and Ircing, P. and Khudanpur, S. and Klakow, D. and Krause, M. and Manmatha, R. and Nock, H. and Petkova, D. and Pytlik, B. and Virga, P.},
 title = {Joint visual-text modeling for automatic retrieval of multimedia documents},
 year = {2005},
 publisher = {ACM Press},
 journal = {Proceedings of the 13th ACM international conference on Multimedia},
 address = {New York, NY},
 pages = {21-30},
 ISBN = {1-59593-044-2},
 url = {http://www.kky.zcu.cz/en/publications/IyengarG_2005_Jointvisual-text},
}