Our lives are increasingly surrounded by data, information and knowledge
captured in multiple media: text, graphics, imagery, audio, and video.
These media are frequently combined or structured to form complex artifacts
(e.g., hypermedia documents, interactive CD-ROMs) which exploit multiple
perceptual modalities (e.g., auditory, visual, haptic/gestural). This
book focuses on tools and techniques that support efficient and effective
indexing, browsing, retrieval, interaction with and visualization of
multimedia. Multimedia digital libraries which incorporate text, graphics,
audio, and video are central to many applications areas including information
access, training, and decision support. This chapter introduces the
need for intelligent multimedia information retrieval, outlines its
theoretical foundations, outlines the current state of the art, describes
the structure of this collection, and outlines some remaining fundamental
problems.
» Download Paper [PDF, 57KB]
