K-Space: bridging the semantic gap Craig Stewart (QMUL)
Textures Colours Distributions Machines see pixels and numbers Elephant in the African Savannah Textures Colours Distributions Humans see “semantic” objects
Overview of K-Space K-Space -- Knowledge Space of Shared Technology and Integrative Research to Bridge the Semantic Gap (in Multimedia Representation and Processing) A Network of Excellence in the 6 th European R&D Framework (see K-Space is a network of research teams from academia and industry to conduct integrative research and dissemination activities in semantic inference for (semi-)automatic annotation and retrieval of multimedia content. K-Space is aiming at closing the semantic gap between low-level content descriptions that can be computed automatically by machines and the richness and subjectivity of semantics in high-level human interpretations of audiovisual media.
Network Partners 1.Queen Mary, University of London (QMUL)- UK 2.Universitaet Koblenz-Landau (KU)- D 3.Joanneum Research Forschungsgesellschaft mbH (JRS)- AT 4.Centre for Research and Technology Hellas (CERTH)- GR 5.Dublin City University (DCU)- IR 6.Centrum voor Wiskunde en Informatica (CWI)- NL 7.Groupe des Ecoles des Télécommunications (GET)- F 8.Institut National de l’Audiovisuel (INA)- F 9.Institut Eurécom (EURECOM)- F 10.University of Glasgow (GU)- UK 11.German Research Centre for Artificial Intelligence (DFKI)- D 12.Technische Universität Berlin (TUB)- D 13.Ecole Polytechnique Fédérale de Lausanne (EPFL)- CH 14.University of Economics, Prague (UEP)- CZ
K-Space Framework
Summary Creation of an open and expandable framework for collaborative research on knowledge acquisition based on a common distributed system made up of flexible, modular and interconnected technology needed to bridge the semantic gap. Continued in …