Building a Visual Ontology for Video Retrieval

Building a Visual Ontology for Video Retrieval
L. Hollink, M. Worring, G. Schreiber
In ACM International Conference on Multimedia 2005.
[bibtex] [pdf] [url]
Abstract
To ensure access to growing video collections, annotation is becoming more and more important. Using background knowledge in the form of ontologies or thesauri is a way to facilitate annotation in a broad domain. Current ontologies are not suitable for (semi-) automatic annotation of visual resources as they contain little visual information about the concepts they describe. We investigate how an ontology that does contain visual information can facilitate annotation in a broad domain and identify requirements that a visual ontology has to meet. Based on these requirements, we create a visual ontology out of two existing knowledge corpora (WordNet and MPEG-7) by creating links between visual and general concepts. We test performance of the ontology on 40 shots of news video, and discuss the added value of each visual property.

Bibtex Entry
@InProceedings{HollinkICM2005,
  author       = "Hollink, L. and Worring, M. and Schreiber, G.",
  title        = "Building a Visual Ontology for Video Retrieval",
  booktitle    = "ACM International Conference on Multimedia",
  pages        = "479--482",
  year         = "2005",
  url          = "https://ivi.fnwi.uva.nl/isis/publications/2005/HollinkICM2005",
  pdf          = "https://ivi.fnwi.uva.nl/isis/publications/2005/HollinkICM2005/HollinkICM2005.pdf"
}
Powered by bibtexbrowser