Bottom-up Attention, Models of
This is an incremental review for researchers in computational neuroscience, summarizing existing work without presenting new results.
The review examines recent progress in saliency prediction and identifies areas for future research, noting that despite significant efforts, improvements are needed in analysis, evaluation, datasets, and applications.
In this review, we examine the recent progress in saliency prediction and proposed several avenues for future research. In spite of tremendous efforts and huge progress, there is still room for improvement in terms finer-grained analysis of deep saliency models, evaluation measures, datasets, annotation methods, cognitive studies, and new applications. This chapter will appear in Encyclopedia of Computational Neuroscience.