Multimedia Information Retrieval

At its very core, multimedia information retrieval means the process of searching for and finding multimedia documents. The corresponding research field is concerned with building the best possible multimedia search engines. The intriguing bit about multimedia retrieval is that the query itself can be a multimedia excerpt: For example, when you walk around in an unknown place and stumble across an interesting landmark, would it not be great if you could just take a picture with your mobile phone and send it to a service that matches your picture to their database and tells you more about the building — or where you are for that matter? The common factor of any multimedia IR effort is that documents and queries can consist of various different media (cross-media retrieval). This lecture takes this observation radically forward by examining the full matrix of combining different query modes with document repository types. The text discusses the underlying techniques and common approaches to many of the difficult challenges, points to current literature in the field and gives you the armamentarium to start building your own multimedia search engines. As automation is key we assume throughout that the multimedia objects are either digitally born or have already been digitized.