Julien Ah-Pine, Jean-Michel Renders, Marie-Luce Viaud
AMR 2009 (International Conference on Adaptive Multimedia Retrieval), Madrid, Spain, 24-25 September, 2009
This paper deals with information seeking in a multimedia database. In such a context, we assume that the search process is complex, dynamic and multi-faceted. We suppose moreover, that the information need with respect to a topic, can change during a same search session, going from a simple lookup search to a thorough discovery of connected subtopics. We propose a system that aims at addressing these challenges. It couples serendipitous browsing and query-based search in a smooth manner. The main features of our proposal that we want to underline are the following ones. The system offers two levels, global and local, of visualizing the context of the information seeking task and it also allows to view and search the data using either monomodal or cross-modal similarities. Furthermore, the system integrates a new relevance feedback model that takes into account the multimodal nature
of the data in a flexible way and a combination of two parameters, the locality and forgetting factors, that allows to design adaptive metrics in
the interactive search process. These functionalities are aimed at offering
tools to the user in order to solve information seeking tasks efficiently. A
preliminary user-centered evaluation of our system, that we also present in this paper, gives encouraging results.
Report number: