A probabilistic tour of visual attention and gaze shift computational models

TL;DR

This paper reviews probabilistic models of eye guidance and visual attention, highlighting current limitations and emphasizing the need to integrate attention, emotion, and control within an active perception framework for real-world tasks.

Contribution

It provides a comprehensive probabilistic perspective on visual attention models and discusses the importance of incorporating neurobiological insights into computational models.

Findings

Current models are far from achieving active, goal-directed eye guidance in real-world scenarios.

A principled integration of attention, emotion, and executive control is necessary for progress.

Neurobiological findings suggest complex links between attention, emotion, and control in gaze behavior.

Abstract

In this paper a number of problems are considered which are related to the modelling of eye guidance under visual attention in a natural setting. From a crude discussion of a variety of available models spelled in probabilistic terms, it appears that current approaches in computational vision are hitherto far from achieving the goal of an active observer relying upon eye guidance to accomplish real-world tasks. We argue that this challenging goal not only requires to embody, in a principled way, the problem of eye guidance within the action/perception loop, but to face the inextricable link tying up visual attention, emotion and executive control, in so far as recent neurobiological findings are weighed up.