Today, a person must know where to search, how to query different media, and how to combine information from diverse resources. As Digital Libraries continue to proliferate, in a variety of media, and from a variety of sources, these problems of resource selection and data fusion become major obstacles. The emergence of multimedia, including text, recorded speech and images, only exacerbates current problems and emphasises the need for new solutions. An answer to a query might be in a text document, an audio clip, or a newswire photograph. Effective, reliable information retrieval requires the ability to pose multimedia queries across many Digital Libraries.

The information access environment that we envision requires advances in several different areas. The proposed research is an end-to-end solution, covering how Digital Libraries are described to external parties, how appropriate resources are selected automatically, how text, image and audio (recorded speech) databases are searched, and how multimedia search results are displayed. Solutions deployed on a world-wide scale require a solid theoretical foundation capable of coping with significant heterogeneity, which we will develop. Every aspect of the proposed research will be tested, at the component level, and through a set of user studies covering research and resources produced by several sites around the world.

The results of the proposed research will include:

• a variety of methods and tool for metadata generation for different media;
• methods and tools for resource selection;
• methods and tools for merging ranked lists of items retrieved from the selected collections (data fusion).

These objectives are clearly identified and explained in the project
  Technical Annex (163Kb).