EU IST Network of Excellence "K-Space - The Knowledge Space of Technology to Bridge the Semantic Gap"
Duration: January 2006 - December 2008
funding programmeEU, Information Society Technologies (IST)
When working with audio-visual data, humans utilize komplex and subjective interpretations. In contrast to this rich meaning, computers can only generate simple content descriptions automatically. The gap between low level content descriptions and high level human interpretation is called "the Semantic Gap". The aim of the K-Space project is to narrow this gap, connecting the work of world leading research teams at universities and industry.
The University of Koblenz-Landau contributes to K-Space in the areas of knowledge representation and storage and semi automatic semantic annotation. The Core Ontology of Multi Media COMM allows to express low level descriptions as well as high level context and relations on a well founded logical model, going clearly beyond current state of the art in multimedia description. An extension of the semantic web knowledge representation language RDF allows to define flexible views on annotation. A distributed storage infrastructure is used to access annotation regardless of their physical location. The development of the K-Space Annoation Tool KAT is lead by the University of Koblenz-Landau. KAT integrates automatic feature extraction tools with rich manual annoation of media items and works with variaous media types, such as images, video and audio.
In addition to high quality research, the K-Space network's activities include organisation of the summer school "Multimedia Semantics", a European Masters program and joint publications in the area of semantic multimedia.
- Queen Mary, University of London
- Joanneum Research Forschungsgesellschaft mbH
- Informatics and Telematics Institute
- Dublin City University
- Centrum voor Wiskunde en Informatica
- Groupe des Ecoles des Télécommunications
- Institut National de l'Audiovisuel
- Institut Eurécom
- University of Glasgow
- German Research Centre for Artificial Intelligence
- Technische Universität Berlin
- Ecole Polytechnique Fédérale de Lausanne
- University of Economics, Prague
Further InformationK-Space Brochure