Bilkent-RETINA at retrieving diverse social images task of MediaEval 2014
dc.contributor.author | Saraç, Mustafa İlker | en_US |
dc.contributor.author | Duygulu Pınar | en_US |
dc.coverage.spatial | Barcelona, Spain | |
dc.date.accessioned | 2016-02-08T12:03:11Z | |
dc.date.available | 2016-02-08T12:03:11Z | |
dc.date.issued | 2014-10 | en_US |
dc.department | Department of Computer Engineering | en_US |
dc.description | Date of Conference: 16-17 October, 2014 | |
dc.description | Conference name: MediaEval 2014 Workshop | |
dc.description.abstract | This paper explains the approach proposed by Bilkent - RETINA team for the Retrieving Diverse Social Images task of MediaEval 2014 [1]. We develop a framework which rst removes outliers using one-class support vector machines (SVM) to improve relevance. Second it clusters the eliminated set and retrieves the centroids to diversify the results. We tried to exploit visual only features during our experiments. For the rst run we used the provided visual features and for the second run we used well known visual features like SIFT [2] and GIST [4]. | en_US |
dc.description.provenance | Made available in DSpace on 2016-02-08T12:03:11Z (GMT). No. of bitstreams: 1 bilkent-research-paper.pdf: 70227 bytes, checksum: 26e812c6f5156f83f0e77b261a471b5a (MD5) Previous issue date: 2014 | en |
dc.identifier.uri | http://hdl.handle.net/11693/27859 | |
dc.language.iso | English | en_US |
dc.publisher | CEUR-WS | en_US |
dc.source.title | CEUR Workshop Proceedings | en_US |
dc.subject | One-class support vector machine | en_US |
dc.subject | Social images | en_US |
dc.subject | Visual feature | en_US |
dc.subject | Support vector machines | en_US |
dc.title | Bilkent-RETINA at retrieving diverse social images task of MediaEval 2014 | en_US |
dc.type | Conference Paper | en_US |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- Bilkent-RETINA at Retrieving Diverse Social Images task of MediaEval 2014.pdf
- Size:
- 185.29 KB
- Format:
- Adobe Portable Document Format
- Description:
- Full printable version