MUSCLE E-Team: Integration of structural and semantic models for multimedia metadata management

The management and exchange of multimedia data is challenging due to the variety of formats, standards and intended applications. In addition, production of multimedia data is rapidly increasing due to the availability of off-the-shelf, modern digital devices that can be used by even inexperienced users. It is likely that this volume of information will only increase in the future. A key goal of the MUSCLE network is to develop tools, technologies and standards to facilitate the interoperability of multimedia content and support the exchange of such data.

Keywords: Multimedia metadata descriptors, Semantic Web, Image Indexing, Content-based Analysis, Information Extraction

Scope

Overall, the purpose of the E-Team is to facilitate and promote communication and exchange. Since the partners in this E-Team have different areas of interest and expertise, we plan to discuss the difficulties in extracting and integrating multimedia data and metadata from different modes (text, images, video).

The broad questions that we aim to consider are:

1. What are the different requirements for recording and storing media?
2. What are the outcomes/outputs from analysing different media?
3. What is the analysis process/workflow for your media?
4. What standards are used? What are their limitations or strengths? (e.g. DC, MPEG-7)
5. How are annotations defined and used? Specifically what type of annotations and how are they captured or extracted?

Current Activities

BILKENT University: video database systems.
CEA LIST: text analysis; web searching; extraction of multimedia metadata from text.
IBaI: tagging of multimedia data; machine-learning; data mining and analysis.
ISTI: multimedia metadata standards, integration of multimedia, semantic web technologies,