The Effectiveness of Concept Based Search for Video Retrieval

C. Hauff, Robin Aly, Djoerd Hiemstra

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

5 Citations (Scopus)
44 Downloads (Pure)

Abstract

In this paper we investigate how a small number of high-level concepts derived for video shots, such as Sport. Face.Indoor. etc., can be used effectively for ad hoc search in video material. We will answer the following questions: 1) Can we automatically construct concept queries from ordinary text queries? 2) What is the best way to combine evidence from single concept detectors into final search results? We evaluated algorithms for automatic concept query formulation using WordNet based concept extraction, and we evaluated algorithms for fast, on-line combination of concepts. Experimental results on data from the TREC Video 2005 workshop and 25 test users show the following. 1) Automatic query formulation through WordNet based concept extraction can achieve comparable results to user created query concepts and 2) Combination methods that take neighboring shots into account outperform more simple combination methods.
Original languageUndefined
Title of host publicationWorkshop Information Retrieval (FGIR 2007)
Place of PublicationHalle-Wittenberg
PublisherGesellschaft für Informatik
Pages205-212
Number of pages8
ISBN (Print)978-3-86010-907-6
Publication statusPublished - 2007

Publication series

NameLWA 2007 Lernen - Wissen Adaption
PublisherGesellschaft fuer Informatik
NumberLNCS4549
Volume2007

Keywords

  • IR-64302
  • METIS-241851
  • EWI-10924

Cite this