Dynamic Bayesian network based interest estimation for visual attentive presentation agents

In this paper, we report on an interactive system and the results ofa formal user study that was carried out with the aim of comparing two approaches to estimating users' interest in a multimodal presentation based on their eye gaze. The scenario consists of a virtual showroom where two 3D agents present product items in an entertaining way, and adapt their performance according to users' (in)attentiveness. In order to infer users' attention and visual interest with regard to interface objects, our system analyzes eye movements in real-time. Interest detection algorithms used in previous research determine an object of interest based on the time that eye gaze dwells on that object. However, this kind of algorithm does not seem to be well suited for dynamic presentations where the goal is to assess the user's focus of attention with regard to a dynamically changing presentation. Here, the current context of the object of interest has to be considered, i.e., whether the visual object is part of (or contributes to) the current presentation content or not. Therefore, we propose to estimate the interest (or non-interest) of a user by means of dynamic Bayesian networks that may take into account the current context of the attention receiving object. In this way, the presentation agents can provide timely and appropriate response. The benefits of our approach will be demonstrated both theoretically and empirically.