Bottom-up Attention, Models of

TL;DR

This review discusses recent advances in saliency prediction models, highlighting progress and identifying future research directions in evaluation, datasets, cognitive studies, and applications.

Contribution

It provides a comprehensive overview of current saliency models and suggests new avenues for research and improvement.

Findings

Significant progress in saliency prediction models

Identified gaps in evaluation measures and datasets

Proposed future research directions

Abstract

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.