It is a common, well-worn wisdom in multimedia research that the semantics of a multimedia object is not found in the object alone, but it is determined also by the context, in which it has been created, in which it is used and in which it is interpreted. In the past, only few dimensions of context could be defined and for the ones that were defined they went often unused. Semantic Web technologies are radically changing this picture. So far, Semantic Web technologies have mostly been used to define the content of a multimedia object, with Semantic Web technologies being in place right now, we have the possibility of tracing the context of multimedia objects in a comprehensive manner, yielding new possibilities and new challenges for existing multimedia as well as for existing Semantic Web technologies.
Steffen Staab is professor for databases and information systems at the University of Koblenz-Landau, leading the research group on Information Systems and Semantic Web (ISWeb). His interests lie in researching core technology for ontologies and semantic web as well as in applied research for exploiting these technologies for knowledge management, multimedia and software technology. He has participated in numerous national, European and intercontinental research projects on these different subjects and his research has led to over 100 refereed contributions in journals and conferences. Dr. Staab held positions as researcher, project leader and lecturer at the University of Freiburg, the University of Stuttgart/Fraunhofer Institute IAO, and the University of Karlsruhe and he is a co-founder of Ontoprise GmbH. For more information see: http://isweb.uni-koblenz.de/ and http://www.uni-koblenz.de/~staab/
After text retrieval, the next waves in web searching and multimedia retrieval are the search for and delivery of images, music, video, and 3D scenes. Not only the perceptual, cognitive, and semanti aspects, but also many of the algorithmic and performance aspects are still badly understood.
We will discuss a number of perceptual issues in visual and auditory sensing, in particular the Gestalt rules. This is followed by a discussion on multimedia retrieval based on matching of Gestalt, or shape information, within images, notated music, and three-dimensional shapes. One relevant issue is the design of dissimilarity measures (distance functions) that have desired properties. Another aspect is the development of algorithms that can compute or approximate these distances efficiently. Indexing data structures and search algorithms are necessary to make the search more efficient than sequential browsing through large collections.
Apart from provable properties of individual algorithms, the experimental verification of the performance of a complete retrieval system is important to analyse merits and drawbacks of certain approaches, and to compare various techniques. We will discuss a number of performance measures, and look at a number of benchmarks in various multimedia retrieval domains.
Remco Veltkamp obtained his Ph.D. in 1992 from Erasmus University Rotterdam. He is now associate professor at UU, and is group leader of the Multimedia and Geometry Group. He has written over 50 refereed papers on indexing, shape matching, shape reconstruction, geometric constraint management, and variational curve and surface design. He is editor of the International Journal on Shape Modelling, the international journal Pattern Recognition, guest editor of the special issues of Algorithmica, Multimedia Tools & Applications, and Computational Geometry Theory & Applications, was editor of the Eurographics'95 State-of-the-Art proceedings, organised the Dagstuhl Seminars on Content-Based Retrieval of 1999, 2002, 2004, and 2006, and organized the 3D Shape Retieval Contest (SHREC) in 2006 and 2007. He participated in the ESPRIT IV LTR projects CGAL (as the technical manager) GALIA, and SPIRIT, participates in the FP6 Network of Excellence Aim@Shape, and is coordinator of the FP6 project PROFI.