IAM@ImageCLEFPhotoAnnotation 2009: Naïve application of a linear-algebraic semantic space
IAM@ImageCLEFPhotoAnnotation 2009: Naïve application of a linear-algebraic semantic space
This paper describes Southampton's submissions to the 2009 ImageCLEF photo annotation task. For the task we used an annotation system based on the idea of constructing semantic spaces, which was developed previously at Southampton. To represent the image content, we used a combination of different SIFT and Colour-SIFT features detected using the difference-of-Gaussian and MSER techniques. These features were converted into a visual term representation by applying vector quantisation using a codebook learnt from a hierarchical k-means clustering. In terms of EER and AUC, the annotator performs reasonably well, however, it struggles when evaluated using the hierarchical measure proposed for the task, due to the way the annotation confidences are thresholded.
66-66
Hare, Jonathan
65ba2cda-eaaf-4767-a325-cd845504e5a9
Lewis, Paul
7aa6c6d9-bc69-4e19-b2ac-a6e20558c020
Borri, Francesca
1def688b-d706-466f-a85f-466d319c8878
Nardi, Alessandro
7aeab97c-ec48-4b4b-ad6e-f1176af536e9
Peters, Carol
877980a7-793e-4c02-a03b-846646b154a7
30 September 2009
Hare, Jonathan
65ba2cda-eaaf-4767-a325-cd845504e5a9
Lewis, Paul
7aa6c6d9-bc69-4e19-b2ac-a6e20558c020
Borri, Francesca
1def688b-d706-466f-a85f-466d319c8878
Nardi, Alessandro
7aeab97c-ec48-4b4b-ad6e-f1176af536e9
Peters, Carol
877980a7-793e-4c02-a03b-846646b154a7
Hare, Jonathan and Lewis, Paul
(2009)
IAM@ImageCLEFPhotoAnnotation 2009: Naïve application of a linear-algebraic semantic space.
Borri, Francesca, Nardi, Alessandro and Peters, Carol
(eds.)
CLEF 2009 Workshop, Corfu, Greece.
30 Sep - 02 Oct 2009.
.
Record type:
Conference or Workshop Item
(Paper)
Abstract
This paper describes Southampton's submissions to the 2009 ImageCLEF photo annotation task. For the task we used an annotation system based on the idea of constructing semantic spaces, which was developed previously at Southampton. To represent the image content, we used a combination of different SIFT and Colour-SIFT features detected using the difference-of-Gaussian and MSER techniques. These features were converted into a visual term representation by applying vector quantisation using a codebook learnt from a hierarchical k-means clustering. In terms of EER and AUC, the annotator performs reasonably well, however, it struggles when evaluated using the hierarchical measure proposed for the task, due to the way the annotation confidences are thresholded.
Text
SOTON-ICannotation-WorkingNotes.pdf
- Version of Record
Restricted to Repository staff only
Request a copy
Text
hare-photoannotation-abstractCLEF2009.pdf
- Version of Record
Restricted to Repository staff only
Request a copy
Text
ImageCLEF-poster-sm.pdf
- Other
More information
Published date: 30 September 2009
Additional Information:
Event Dates: 30 September - 2 October 2009
Venue - Dates:
CLEF 2009 Workshop, Corfu, Greece, 2009-09-30 - 2009-10-02
Organisations:
Web & Internet Science
Identifiers
Local EPrints ID: 267992
URI: http://eprints.soton.ac.uk/id/eprint/267992
PURE UUID: 69c0ef8c-b3d8-4279-a7e9-6b339cafbecc
Catalogue record
Date deposited: 05 Oct 2009 11:38
Last modified: 15 Mar 2024 03:25
Export record
Contributors
Author:
Jonathan Hare
Author:
Paul Lewis
Editor:
Francesca Borri
Editor:
Alessandro Nardi
Editor:
Carol Peters
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