Adaptive Visual Information Retrieval by Changing Visual Vocabulary Sizes in Context of User Intentions

The overwhelming availability of visual content on the Internet poses a serious problem: although there are huge resources to tap, users often cannot find the content they actually want. The information need of a user is based on the user´s intention or the goal s/he wants to achieve. In this paper we distinguish between users that have clearly defined, specific information needs and goals and those that have a broader interest and less specific needs. We present a novel approach to retrieval adaptation based on the degree of intentionality. Our tests on two well known data sets demonstrate the potential of our approach.