Building Detectors to Support Searches on Combined Semantic Concepts

Robin Aly, Djoerd Hiemstra, Roeland J.F. Ordelman

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

66 Downloads (Pure)


Bridging the semantic gap is one of the big challenges in multimedia information retrieval. It exists between the extraction of low-level features of a video and its conceptual contents. In order to understand the conceptual content of a video a common approach is building concept detectors. A problem of this approach is that the number of detectors is impossible to determine. This paper presents a set of 8 methods on how to combine two existing concepts into a new one, which occurs when both concepts appear at the same time. The scores for each shot of a video for the combined concept are computed from the output of the underlying detectors. The findings are evaluated on basis of the output of the 101 detectors including a comparison to the theoretical possibility to train a classifier on each combined concept. The precision gains are significant, specially for methods which also consider the chronological surrounding of a shot promising.
Original languageUndefined
Title of host publicationProceedings of the Multimedia Information Retrieval Workshop
Place of PublicationAmsterdam
PublisherYahoo! Research
Number of pages6
ISBN (Print)not assigned
Publication statusPublished - Aug 2007
EventMultimedia Information Retrieval Workshop 2007 - Amsterdam, Netherlands
Duration: 27 Aug 200727 Aug 2007

Publication series

PublisherYahoo! Research


WorkshopMultimedia Information Retrieval Workshop 2007


  • EWI-10923
  • IR-64301
  • METIS-241850
  • semantic concept
  • concept combination

Cite this