CVOct 24, 2015
Computational models of attention
arXiv:1510.07182v12.55 citations
Originality Synthesis-oriented
AI Analysis
It provides a comprehensive overview for researchers in computer vision and cognitive science, but is incremental as a review.
The paper reviews computational models of visual attention, categorizing them into bottom-up stimulus-driven and top-down goal-oriented approaches.
This chapter reviews recent computational models of visual attention. We begin with models for the bottom-up or stimulus-driven guidance of attention to salient visual items, which we examine in seven different broad categories. We then examine more complex models which address the top-down or goal-oriented guidance of attention towards items that are more relevant to the task at hand.