Professional repositories and Intranets, like the Internet as a whole, present the problem of how to find precise segments of audiovisual files among a sea of largely un-indexed, heterogeneous data. SEMEDIA aims to create new methods, environments and widely usable tools for media labelling, searching and retrieval from very large collections of heterogeneous data, building on and extending research in media technologies, web semantics, AI, Content Based IR and interface design. SEMEDIA will enable the rapid, semi-automatic annotation of large data populations at greatly reduced cost, and the production of professional and consumer tools for near instantaneous data search and retrieval from very large, distributed stores of mainly un-indexed audiovisual media. SEMEDIA will develop techniques to extract metadata from 'essence' in ways that allow the automatic inference of high-level structural information from new, partly annotated media content. It will create tools for:- navigating intelligently and searching efficiently; - summarising and clustering visually similar content; searching for 'scenes similar to...'; - finding scenes with a given character and all the associated files, geometry, shading, colour model, speech characteristics, motion data etc; - data architectures that support secure content tracking and multiple user access; - user interfaces that allow fast browsing with user defined criteria and adaptive feedback that recognises context and intent, and contributes to the annotation.The research will be guided by user scenarios developed with professionals in the postproduction and broadcast industries, and on-line communities. The results will adopt an open systems approach, which can be combined with existing media and web environments, to provide search tools that meet the needs of producers and consumers of audiovisual media in the digital postproduction, broadcast, advertising and on-line sectors.