Extracting bimodal representations for language-based image text retrieval

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademic

12 Downloads (Pure)

Abstract

This paper explores two approaches to multimedia indexing that might contribute to the advancement of text-based conceptual search for pictorial information. Insights from relatively mature retrieval areas (spoken document retrieval and cross-language retrieval) are taken as a starting point for an investigation of the usefulness of the concept of bimodal dictionaries and of clustering features from multi-modal documents into one semantic space. One of the advantages of the presented techniques is that they are domain independent.
Original languageEnglish
Title of host publicationMultimedia '99
Subtitle of host publicationProceedings of the Eurographics Workshop in Milano, Italy, September 7–8, 1999
EditorsNuno Correia, Teresa Chambel, Glorianna Davenport
Place of PublicationVienna
PublisherSpringer
Pages33-42
Number of pages41
ISBN (Electronic)978-3-7091-6771-7
ISBN (Print)978-3-211-83437-4
Publication statusPublished - 2000
EventEurographics Multimedia Workshop 1999 - Milan, Italy
Duration: 7 Sep 19998 Sep 1999

Publication series

NameEurographics
PublisherSpringer

Workshop

WorkshopEurographics Multimedia Workshop 1999
CountryItaly
CityMilan
Period7/09/998/09/99

Fingerprint Dive into the research topics of 'Extracting bimodal representations for language-based image text retrieval'. Together they form a unique fingerprint.

  • Cite this

    Westerveld, T., Hiemstra, D., & de Jong, F. (2000). Extracting bimodal representations for language-based image text retrieval. In N. Correia, T. Chambel, & G. Davenport (Eds.), Multimedia '99: Proceedings of the Eurographics Workshop in Milano, Italy, September 7–8, 1999 (pp. 33-42). (Eurographics). Vienna: Springer.