LIVE along with the project BOEMIE will be hosting a special workshop at the SAMT 2007 Conference on knowledge acquisition from multimedia content.

Short description

In recent years significant advances have been made in the area of automatic extraction of low-level features from audiovisual content. However, little progress has been achieved in the identification of high-level semantic features or the effective combination of semantic features derived from different modalities. Knowledge acquisition is becoming a key-enabling factor of the above tasks towards more scalable and reliable solutions, and thus its automation is becoming critical. As the deployment of knowledge enhances the robustness of extraction while on the other hand the continuous extraction of semantic information can enrich this knowledge, synergistic approaches that combine multimedia extraction and knowledge evolution in a bootstrapping common framework to introduce new opportunities in semantic multimedia applications. Integration with additional sources of information, e.g. by using human annotation tools or real-time event services, may further simplify and disambiguate semantic multimedia information systems. Moreover, adaptation to a particular domain, for example to sports events, such as the Olympic games, is essential in order to reduce the complexity of multimedia analysis.

In this context, unified modelling and representation of multimedia and domain-specific knowledge, ontology evolution, and standard and non-standard inference services for multimodal semantic knowledge fusion, form cutting edge technologies. This workshop shall introduce briefly related research activities of two European research projects, BOEMIE and LIVE, which both aim to enhance the automatic understanding of Olympic sports events. Whereas BOEMIE concentrates on ontology evolution and learning, LIVE targets real-time recommender systems for broadcasters able to analyse Olympic sport events and recommend suitable data from a production archive. Any contribution related to these topics is welcome; the workshop shall trigger an open discussion on these topics with all participants.

Call for papers

This workshop invites contributions on all topics related to semantic multimedia information systems. Special emphasis is given in challenging applications, such as the analysis of sports broadcasts. We anticipate some significant discussion owing to differences in opinions about approaches to take in solving the relevant joint problems, and we invite you to join the workshop to give your views on the following, as well as related topics:

1. Knowledge-driven multimedia analysis
   1. Video, image, audio and text semantics extraction
2. Knowledge representation and reasoning for multimedia understanding
   1. Multimedia ontologies
   2. Deductive, abductive, rule-based reasoning
3. Knowledge-based production support systems
4. Knowledge-based systems in real-time environments
5. Ontology evolution
   1. Ontology enrichment, learning, population and coordination
6. Fusion of knowledge extracted from multiple data sources (channels, modalities, streams)
7. Real-time algorithms with or without hardware accelerations
8. Semi-automatic offline or online human annotation
9. Personalised content broadcasting
10. Recommendation systems and collaborative filtering 

To express your interest in participating or contributing a paper to this workshop please send a message to info@ist-live.org. More information will be available soon.