Learning the semantics of multimedia content with application to web image retrieval and classification
Learning the semantics of multimedia content with application to web image retrieval and classification
We use kernel Canonical Correlation Analysis to learn a semantic representation of Web images and their associated text. This representation is used in two applications. In first application we consider classification of images into one of three categories. We use SVM in the semantic space and compare against the SVM on raw data and against previously published results using ICA. In the second application we retrieve images based only on their content from a text query. The semantic space provides a common representation and enables a comparison between the text and image. We compare against a standard cross-representation retrieval technique known as the Generalised Vector Space Model.
KCCA
697-702
Vinokourov, Alexei
a82e6630-b417-4f82-a604-17a544452010
Hardoon, David R.
05549e24-da95-4690-a3e2-3c672d2342b8
Shawe-Taylor, John
b1931d97-fdd0-4bc1-89bc-ec01648e928b
2003
Vinokourov, Alexei
a82e6630-b417-4f82-a604-17a544452010
Hardoon, David R.
05549e24-da95-4690-a3e2-3c672d2342b8
Shawe-Taylor, John
b1931d97-fdd0-4bc1-89bc-ec01648e928b
Vinokourov, Alexei, Hardoon, David R. and Shawe-Taylor, John
(2003)
Learning the semantics of multimedia content with application to web image retrieval and classification.
In Proceedings of the Fourth International Symposium on Independent Component Analysis and Blind Signal Separation.
.
Record type:
Conference or Workshop Item
(Paper)
Abstract
We use kernel Canonical Correlation Analysis to learn a semantic representation of Web images and their associated text. This representation is used in two applications. In first application we consider classification of images into one of three categories. We use SVM in the semantic space and compare against the SVM on raw data and against previously published results using ICA. In the second application we retrieve images based only on their content from a text query. The semantic space provides a common representation and enables a comparison between the text and image. We compare against a standard cross-representation retrieval technique known as the Generalised Vector Space Model.
Text
alexei_ica03.pdf
- Other
More information
Published date: 2003
Venue - Dates:
Fourth International Symposium on Independent Component Analysis and Blind Source Separation, Nara, Japan, 2003-01-01
Keywords:
KCCA
Organisations:
Electronics & Computer Science
Identifiers
Local EPrints ID: 259218
URI: http://eprints.soton.ac.uk/id/eprint/259218
PURE UUID: b315164b-9383-4589-aeb2-1a881dc6d9c0
Catalogue record
Date deposited: 23 Mar 2004
Last modified: 16 Mar 2024 00:39
Export record
Contributors
Author:
Alexei Vinokourov
Author:
David R. Hardoon
Author:
John Shawe-Taylor
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