of Crete

Predicting visual attention can significantly improve scene design, interactivity and rendering. For example, image synthesis can be accelerated by reducing computation on non-attended scene re-gions; attention can also be used to improve LOD. Most previous attention models are based on low-level image features, as it is com-putationally and conceptually challenging to take into account high-level factors such as scene context, topology or task. As a result, they often fail to predict saccadic targets because scene semantics strongly affect the planning and execution of fixations. In this talk, we present the first automated high level saliency predictor that in-corporates the schema [Bartlett 1932] and singleton [Theeuwes and Godijn 2002] hypotheses into the Differential-Weighting Model (DWM) [Eckstein 1998]. The scene schema effect states that a scene is comprised of objects expected to be found in a specific context as well objects out of context which are salient (Figure 1a)