High diversity transforms multimedia information retrieval into a cross-cutting field
James Z. Wang, Nozha Boujemaa, Yixin Chen · ACM SIGMOD Record · 2007
Indexing and retrieval of large quantity of multimedia data is a highly challenging and growingly important problem for the computer science research community. Researchers in multimedia, databases, computer vision, machine learning, signal and image processing and statistics have worked on multimedia information retrieval (MIR) for over a decade. A number of significant technological advances have been achieved in this field. Some of the techniques have been applied to application areas such as art image retrieval, biomedical image and video retrieval, education, sensor networks, large-scale online personal and professional photo sharing communities, classification and filtering of images on the Web, scientific content, computer forensics, threat assessment and security applications more generally.