Evaluating the Implicit Feedback Models for Adaptive Video Retrieval

Interactive video retrieval systems are becoming popular. On the one hand, these systems try to reduce the effect of the semantic gap, an issue currently being addressed by the multimedia retrieval community. On the other hand, such systems enhance the quality of information seeking for the user by supporting query formulation and reformulation. Interactive systems are very popular in the textual retrieval domain. However, they are relatively unexplored in the case of multimedia retrieval. The main problem in the development of interactive retrieval systems is the evaluation cost.The traditional evaluation methodology, as used in the information retrieval domain, is not applicable. An alternative is to use a user-centred evaluation methodology. However, such schemes are expensive in terms of effort, cost and are not scalable. This problem gets exacerbated by the use of implicit indicators, which are useful and increasingly used in predicting user intentions. In this paper, we explore the effectiveness of a number of interfaces and feedback mechanisms and compare their relative performance using a simulated evaluation methodology. The results show the relatively better performance of a search interface with the combination of explicit and implicit features