Mind the Gap: Another look at the problem of the semantic gap in image retrieval
Mind the Gap: Another look at the problem of the semantic gap in image retrieval
This paper attempts to review and characterise the problem of the semantic gap in image retrieval and the attempts being made to bridge it. In particular, we draw from our own experience in user queries, automatic annotation and ontological techniques. The first section of the paper describes a characterisation of the semantic gap as a hierarchy between the raw media and full semantic understanding of the media's content. The second section discusses real users' queries with respect to the semantic gap. The final sections of the paper describe our own experience in attempting to bridge the semantic gap. In particular we discuss our work on auto-annotation and semantic-space models of image retrieval in order to bridge the gap from the bottom up, and the use of ontologies, which capture more semantics than keyword object labels alone, as a technique for bridging the gap from the top down.
Image retrieval, semantic gap, semantic space, user study, ontology
0-8194-6113-X
607309-1
Hare, Jonathon S.
65ba2cda-eaaf-4767-a325-cd845504e5a9
Lewis, Paul H.
7aa6c6d9-bc69-4e19-b2ac-a6e20558c020
Enser, Peter G. B.
3d0430bb-861f-4d99-a2d7-be7935d5a6c5
Sandom, Christine J.
6637df2a-0204-4e48-951c-6a95e661627d
Chang, Edward Y.
501f4ac0-b61c-4be5-b8c0-ed0bfedb5958
Hanjalic, Alan
deb8622f-10c2-4056-bc91-0bbcbb208530
Sebe, Nicu
972ec0ad-8d21-4b1d-bf2c-beca0c45ec5f
2006
Hare, Jonathon S.
65ba2cda-eaaf-4767-a325-cd845504e5a9
Lewis, Paul H.
7aa6c6d9-bc69-4e19-b2ac-a6e20558c020
Enser, Peter G. B.
3d0430bb-861f-4d99-a2d7-be7935d5a6c5
Sandom, Christine J.
6637df2a-0204-4e48-951c-6a95e661627d
Chang, Edward Y.
501f4ac0-b61c-4be5-b8c0-ed0bfedb5958
Hanjalic, Alan
deb8622f-10c2-4056-bc91-0bbcbb208530
Sebe, Nicu
972ec0ad-8d21-4b1d-bf2c-beca0c45ec5f
Hare, Jonathon S., Lewis, Paul H., Enser, Peter G. B. and Sandom, Christine J.
(2006)
Mind the Gap: Another look at the problem of the semantic gap in image retrieval.
Chang, Edward Y., Hanjalic, Alan and Sebe, Nicu
(eds.)
Multimedia Content Analysis, Management and Retrieval 2006, San Jose, California, United States.
17 - 19 Jan 2006.
.
Record type:
Conference or Workshop Item
(Paper)
Abstract
This paper attempts to review and characterise the problem of the semantic gap in image retrieval and the attempts being made to bridge it. In particular, we draw from our own experience in user queries, automatic annotation and ontological techniques. The first section of the paper describes a characterisation of the semantic gap as a hierarchy between the raw media and full semantic understanding of the media's content. The second section discusses real users' queries with respect to the semantic gap. The final sections of the paper describe our own experience in attempting to bridge the semantic gap. In particular we discuss our work on auto-annotation and semantic-space models of image retrieval in order to bridge the gap from the bottom up, and the use of ontologies, which capture more semantics than keyword object labels alone, as a technique for bridging the gap from the top down.
More information
Published date: 2006
Additional Information:
Event Dates: 17-19 January
Venue - Dates:
Multimedia Content Analysis, Management and Retrieval 2006, San Jose, California, United States, 2006-01-17 - 2006-01-19
Keywords:
Image retrieval, semantic gap, semantic space, user study, ontology
Organisations:
Web & Internet Science
Identifiers
Local EPrints ID: 261887
URI: http://eprints.soton.ac.uk/id/eprint/261887
ISBN: 0-8194-6113-X
PURE UUID: 0f04472b-6a00-47a0-800c-acef81cc8e34
Catalogue record
Date deposited: 01 Feb 2006
Last modified: 15 Mar 2024 03:25
Export record
Contributors
Author:
Jonathon S. Hare
Author:
Paul H. Lewis
Author:
Peter G. B. Enser
Author:
Christine J. Sandom
Editor:
Edward Y. Chang
Editor:
Alan Hanjalic
Editor:
Nicu Sebe
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics