Active visual information systems

Abstract

To accomplish the discovery, fusion and retrieval of visual/multimedia information from diversified sources, active visual information systems capable of processing and filtering visual/multimedia information, checking for semantic consistency, and structuring the relevant information for distribution are needed. We describe a framework for the human- and system-directed discovery and fusion of visual/multimedia information, which is based upon the observation that a significant event often manifests itself in different media over time. Therefore if we can index such manifestations and dynamically link them, then we can check for consistency and discover important and relevant visual/multimedia information. This dynamic indexing technique is based upon the theory of active index. An approach for rapid prototyping of active visual information systems using Tele-Action Objects, TAO_HTML Interpretor and active index system is then presented.