Volume 4071 of the series Lecture Notes in Computer Science pp 51-60
Query by Semantic Example
- Nikhil RasiwasiaAffiliated withStatistical Visual Computing Lab, University of California
- , Nuno VasconcelosAffiliated withStatistical Visual Computing Lab, University of California
- , Pedro J. MorenoAffiliated withGoogle, Inc.
Abstract
A solution to the problem of image retrieval based on query-by-semantic-example (QBSE) is presented. QBSE extends the idea of query-by-example to the domain of semantic image representations. A semantic vocabulary is first defined, and a semantic retrieval system is trained to label each image with the posterior probability of appearance of each concept in the vocabulary. The resulting vector is interpreted as the projection of the image onto a semantic probability simplex, where a suitable similarity function is defined. Queries are specified by example images, which are projected onto the probability simplex. The database images whose projections on the simplex are closer to that of the query are declared its closest neighbors. Experimental evaluation indicates that 1) QBSE significantly outperforms the traditional query-by-visual-example paradigm when the concepts in the query image are known to the retrieval system, and 2) has equivalent performance even in the worst case scenario of queries composed by unknown concepts.
- Title
- Query by Semantic Example
- Book Title
- Image and Video Retrieval
- Book Subtitle
- 5th International Conference, CIVR 2006, Tempe, AZ, USA, July 13-15, 2006. Proceedings
- Pages
- pp 51-60
- Copyright
- 2006
- DOI
- 10.1007/11788034_6
- Print ISBN
- 978-3-540-36018-6
- Online ISBN
- 978-3-540-36019-3
- Series Title
- Lecture Notes in Computer Science
- Series Volume
- 4071
- Series ISSN
- 0302-9743
- Publisher
- Springer Berlin Heidelberg
- Copyright Holder
- Springer-Verlag Berlin Heidelberg
- Additional Links
- Topics
- Industry Sectors
- eBook Packages
- Editors
-
- Hari Sundaram (16)
- Milind Naphade (17)
- John R. Smith (18)
- Yong Rui (19)
- Editor Affiliations
-
- 16. Arts, Media and Engineering Program, Arizona State University
- 17. Intelligent Information Management Department, IBM T.J. Watson Research Center
- 18. Intelligent Information Management Department, IBM T. J. Watson Research Center
- 19. Microsoft Corporation, Microsoft China R&D Group
- Authors
-
- Nikhil Rasiwasia (20)
- Nuno Vasconcelos (20)
- Pedro J. Moreno (21)
- Author Affiliations
-
- 20. Statistical Visual Computing Lab, University of California, San Diego
- 21. Google, Inc., 1440 Broadway, 21st Floor, New York, NY, USA
Continue reading...
To view the rest of this content please follow the download PDF link above.