JCDL2010

Multimedia Information Retrieval Tutorial

At its 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 to support digital libraries and a range of resource discovery missions. This tutorial discusses underlying techniques and common approaches to facilitate multimedia search engines:

• metadata driven retrieval;
• piggy-back text retrieval where automated processes create textual representations for multimedia;
• automated image annotation;
• content-based retrieval.

Content-based retrieval is studied in great depth looking at multimedia features and distance calculation methods, and how to effectively combine them for efficient retrieval. Participants should finish with the ingredients and recipe in their hands for building their own multimedia search engines.

Supporting users in their resource discovery missions when hunting for multimedia material is not only a technological indexing problem. We also look at interactive ways of engaging with repositories through browsing and relevance feedback, including geographical context, and providing visual summaries for videos. The tutorial emphasises state-of-the-art research in the area of multimedia information retrieval, which gives an indication of the research and development trends and, thereby, a glimpse of the future world.

This full-day tutorial will be presented by Suzanne Little during the JCDL conference held on Australia's Gold Coast, Monday June 21. Registration for both the conference and the tutorial is available at the JCDL website. Reference material will be from the recently published lecture by Stefan Rueger, Multimedia Information Retrieval. Attendees are highly recommended to bring a laptop computer to participate fully in the interactive exercises.

---

Stefan Rueger joined The Open University's Knowledge Media Institute in 2006 to take up a chair in Knowledge Media. Before that he was a Reader in Multimedia and Information Systems at the Department of Computing, Imperial College London, where he also held an EPSRC Advanced Research Fellowship (1999–2004). Stefan is a theoretical physicist by training (FU Berlin) and received his PhD in Computing in 1996 from TU Berlin for his work on artificial intelligence and, in particular, the theory of neural networks. Since then he has made a continuous journey from theory to its applications in multimedia retrieval. In 2009 he was awarded a Honorary Professorship (until 2014) at the University of Waikato for his work with the Greenstone Digital Library group. During his academic career he and his team have authored over 100 scientific publications in the area of multimedia information retrieval.

Suzanne Little joined KMi in 2008 as a research fellow on the EU-funded PHAROS audiovisual search project in the areas of image analysis, multimedia annotation and content-based search. She completed her PhD at the University of Queensland, Australia in 2006 researching tools for analysing and managing scientific multimedia data. After submitting her thesis, Suzanne held an 18 month postdoctoral fellowship within the European Network of Excellence in multimedia semantic search, MUSCLE, examining hybrid approaches to signal analysis and image annotation, dividing her time between ISTI-CNR in Pisa, Italy and IBaI in Leipzig, Germany. Suzanne has worked with the Greenstone Digital Library project, visiting the University of Waikato, and is working with The Open University library to apply outcomes from the PHAROS research project.

Both Stefan and Suzanne are members of the Multimedia Information Systems research group at KMi.