Incremental Learning of Target Locations in Visual Search
Michal Dziemianko, Moreno I. Coco, Frank Keller · eScholarship (California Digital Library) · 2011
The top-down guidance of visual attention is one of the main factors allowing humans to effectively process vast amounts of incoming visual information. Nevertheless we still lack a full understanding of the visual, semantic, and memory processes governing visual attention. In this paper, we present a compu-tational model of visual search capable of predicting the most likely positions of target objects. The model does not require a separate training phase, but learns likely target positions in an incremental fashion based on a memory of previous fixations. We evaluate the model on two search tasks and show that it out-performs saliency alone and comes close to the maximal per-formance the Contextual Guidance Model can achieve (CGM, Torralba et al. 2006; Ehinger et al. 2009), even though our model does not perform scene recognition or compute global image statistics.