K-Space Work Package 5

Semantic Multimedia

This task will use and extend semantic web technology in order to respond to the needs of Multimedia Analysis and Knowledge Extraction and, thus, to facilitate the bridging of the semantic gap top down. The rationale behind the approach in this task is that a purely bottom-up approach will not be sufficient to close the semantic gap, because a lot of knowledge around the use and the context of multimedia sources is needed in order to bridge between low level multimedia features and the pragmatics of its use.

Research in this task is structured along four tasks:

Represent semantic metadata as well as experience and needs of users semantically in order to represent bottom-up results and user context.
Investigate how people interact with multimedia in order to derive new semantic characterizations, which may be exploited in the life cycle of the multimedia data.
Extract knowledge from complementary sources (such as subtitles of movies or web sites of similar multimedia data) in order to derive additional semantic characterizations.
Provide a mechanism to handle such additional context-based characterizations, i.e. constructing, representing, querying and using them.

Activity 5.1 - Knowledge Representation for Multimedia

Activity 5.2 - Reference Framework for Distributed Semantic Management of Multimedia Metadata

Activity 5.3 - Semantics-based Interaction with Multimedia

Activity 5.4 - Knowledge Extraction from Complementary Sources

Partners Involved

Koblenz University, (Uni Ko-Ld)

Queen Mary, University of London (QMUL)

Joanneum Research Forschungsgesellschaft mbH, (JRS)

German Research Centre for Artificial Intelligence (DFKI)

Dublin City University, (DCU)

Centrum voor Wiskunde en Informatica, (CWI)

Informatics and Telematics Institute (ITI) & Centre for Research and Technology Hellas (CERTH)