Multimedia applications: Beyond similarity searches John R. Smith, David Doermann, Amarnath Gupta, Jonathan Goldstein, Uri Shaft, and Nalini Ratha   View Paper (PDF)   Return to Panel Abstract Relational database systems solve many of the traditional problems for processing of structured data. However, unstructured data in the form of images, video, audio and multimedia is growing at a tremendous rate and introduces new requirements that are not met by today's database engines. One well known example is content-based retrieval that involves similarity searching and indexing in high-dimensional feature spaces. In addition there has been much recent focus on applying machine learning techniques involving semantics modeling, spatio-temporal indexing, multi-modal (audio-, visual-, textual-) integration and relevance feedback searching. Database systems clearly must evolve if they are to support this next generation of multimedia data. The objective of this panel is to examine the emerging data processing requirements for multimedia, discuss promising research directions that will address these requirements, and debate the role that database systems will play in the future with respect to the important and growing class of multimedia data. ©2006 Association for Computing Machinery