Intelligent browsing for multimedia applications

Abstract

Describes a technique which we term "intelligent browsing"; the software built upon this technique assists the users in their search through a multimedia database. Searching for an item of interest in a large multimedia database is a complex task, even for users who have knowledge about it. An active (intelligent) browser suggests to the user items it estimates to be close to the target of the search. The intelligent part of the active browser consists of a learning module, whose object of study is the profile of the users' search actions. After a target is detected, the intelligent browser brings the item or items of interest on to the screen in a dedicated window, and controls the synchronization of the audio, video or written components of the item. If confirmed by the user, the dedicated window is transformed into a series of windows allocated to the desired item. The novel aspect of intelligent browsing is that it is entirely unobtrusive: it infers its similarity measure from the user's normal browsing actions, without any special input. Use of the browser on a multimedia application is illustrated in this paper.