CORDIS - Resultados de investigaciones de la UE
CORDIS

Knowledge space of semantic inference for automatic annotation and retrieval of multimedia content

Objetivo

K-Space is a network of leading research teams from academia and industry conducting integrative research and dissemination activities in semantic inference for automatic and semi-automatic annotation and retrieval of multimedia content. The aim of K-Space research is to narrow the gap between low-level content descriptions that can be computed automatically by a machine and the richness and subjectivity of semantics in high-level human interpretations of audiovisual media.

K-Space integrative research focus on three key areas:
-Content-based multimedia analysis: Tools and methodologies for low and medium-level signal processing, natural language, audio and speech processing, text analysis, low-level feature fusion and content description.
-Knowledge extraction: Building of a multimedia ontology infrastructure, knowledge-assisted multimedia analysis multimedia reasoning and annotation, context based multimedia mining and intelligent user relevance feedback.
-Semantic multimedia: Adaptation of existing languages, representation of extracted semantic information, knowledge representation for multimedia, semantics-based interaction with multimedia and knowledge extraction from complementary sources.
An important objective of the Network is to implement an open and expandable framework for collaborative research based on a common reference system made up of modular technology: The Knowledge Space of Shared Technology to Bridge the Semantic Gap, "K-Space".

K-Space will integrate complementary expertise, enable resource optimization and sharing, and foster innovative research in semantic inference for semi-automatic annotation and retrieval of multimedia content. Specific dissemination objectives of K-Space are:
-Dissemination of the technical developments of the network across the broad research community
-Influencing and contributing to related knowledge-based multimedia standardisation activities.

Convocatoria de propuestas

Data not available

Régimen de financiación

NoE - Network of Excellence

Coordinador

QUEEN MARY AND WESTFIELD COLLEGE, UNIVERSITY OF LONDON
Aportación de la UE
Sin datos
Dirección
MILE END ROAD
E1 4NS LONDON
Reino Unido

Ver en el mapa

Coste total
Sin datos

Participantes (13)