Architecture for enhancing video analysis results using complementary resources

  • J. Nemrava
  • , P. Buitelaar
  • , T. Declerck
  • , V. Svátek
  • , J. Petrák
  • , A. Cobet
  • , H. Zeiner
  • , D. Sadlier
  • , N. O'Connor

Research output: Contribution to a Journal (Peer & Non Peer)Conference articlepeer-review

Abstract

In this paper we present different sources of information complementary to audio-visual (A/V) streams and propose their usage for enriching A/V data with semantic concepts in order to bridge the gap between low-level video analysis and high-level analysis. Our aim is to extract crossmedia feature descriptors from semantically enriched and aligned resources so as to detect finer-grained events in video. We introduce an architecture for complementary resources analysis and discuss domain dependency aspects of this approach connected to our initial domain of soccer broadcasts.

Original languageEnglish
Pages (from-to)7-8
Number of pages2
JournalCEUR Workshop Proceedings
Volume300
Publication statusPublished - 2007
Externally publishedYes
Event2nd International Conference on Semantic and Digital Media Technologies, SAMT 2007 - Genoa, Italy
Duration: 5 Dec 20077 Dec 2007

Keywords

  • Multimedia databases
  • Text processing

Fingerprint

Dive into the research topics of 'Architecture for enhancing video analysis results using complementary resources'. Together they form a unique fingerprint.

Cite this