Multimedia Retrieval by Means of Merge of Results from Textual and Content Based Retrieval Subsystems

García Serrano, Ana and Benavent, Xaro and Granados Muñoz, Rubén and Ves, Esther de and Goñi Menoyo, José Miguel (2010). Multimedia Retrieval by Means of Merge of Results from Textual and Content Based Retrieval Subsystems. In: "Multilingual Information Access Evaluation II - Multimedia Experiments". Lecture Notes in Computer Science (6242). Springer, Berlin, Alemania, pp. 142-149. ISBN 978-3-642-15750-9. https://doi.org/10.1007/978-3-642-15751-6_15.

Description

Title: Multimedia Retrieval by Means of Merge of Results from Textual and Content Based Retrieval Subsystems
Author/s:
  • García Serrano, Ana
  • Benavent, Xaro
  • Granados Muñoz, Rubén
  • Ves, Esther de
  • Goñi Menoyo, José Miguel
Item Type: Book Section
Event Title: 10th Workshop of the Cross-Language Evaluation Forum, CLEF 2009
Event Dates: 30/09/2009-02/10/2009
Event Location: Corfu, Grecia
Title of Book: Multilingual Information Access Evaluation II - Multimedia Experiments
Date: 2010
ISBN: 978-3-642-15750-9
Subjects:
Faculty: E.T.S.I. Telecomunicación (UPM)
Department: Matemática Aplicada a las Tecnologías de la Información [hasta 2014]
UPM's Research Group: Grupo de Sistemas Inteligentes
Creative Commons Licenses: Recognition - No derivative works - Non commercial

Full text

[img]
Preview
PDF - Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (170kB) | Preview

Abstract

The main goal of this paper it is to present our experiments in ImageCLEF 2009 Campaign (photo retrieval task). In 2008 we proved empirically that the Text-based Image Retrieval (TBIR) methods defeats the Content-based Image Retrieval CBIR “quality” of results, so this time we developed several experiments in which the CBIR helps the TBIR. The TBIR System [6] main improvement is the named-entity sub-module. In case of the CBIR system [3] the number of low-level features has been increased from the 68 component used at ImageCLEF 2008 up to 114 components, and only the Mahalanobis distance has been used. We propose an ad-hoc management of the topics delivered, and the generation of XML structures for 0.5 million captions of the photographs (corpus) delivered. Two different merging algorithms were developed and the third one tries to improve our previous cluster level results promoting the diversity. Our best run for precision metrics appeared in position 16th, in the 19th for MAP score, and for diversity value in position 11th, for a total of 84 submitted experiments. Our best and “only textual” experiment was the 6th one over 41.

More information

Item ID: 4745
DC Identifier: http://oa.upm.es/4745/
OAI Identifier: oai:oa.upm.es:4745
DOI: 10.1007/978-3-642-15751-6_15
Official URL: http://www.springerlink.com/content/542r181u253122p7/
Deposited by: Memoria Investigacion
Deposited on: 27 Oct 2010 10:25
Last Modified: 20 Apr 2016 13:50
  • Logo InvestigaM (UPM)
  • Logo GEOUP4
  • Logo Open Access
  • Open Access
  • Logo Sherpa/Romeo
    Check whether the anglo-saxon journal in which you have published an article allows you to also publish it under open access.
  • Logo Dulcinea
    Check whether the spanish journal in which you have published an article allows you to also publish it under open access.
  • Logo de Recolecta
  • Logo del Observatorio I+D+i UPM
  • Logo de OpenCourseWare UPM