Computational models: Bottom-up and top-down aspects

TL;DR

This paper critically reviews recent computational models of visual attention, emphasizing models that process diverse stimuli, incorporate task definitions, and predict behavioral or physiological responses, highlighting their scientific and practical relevance.

Contribution

It provides a focused critique of recent attention models that process any visual stimulus and make testable predictions, distinguishing them from abstract or task-specific models.

Findings

Models make testable predictions for experimental validation

Focus on models that process diverse stimuli and tasks

Highlights relevance for both scientific understanding and technological applications

Abstract

Computational models of visual attention have become popular over the past decade, we believe primarily for two reasons: First, models make testable predictions that can be explored by experimentalists as well as theoreticians, second, models have practical and technological applications of interest to the applied science and engineering communities. In this chapter, we take a critical look at recent attention modeling efforts. We focus on {\em computational models of attention} as defined by Tsotsos \& Rothenstein \shortcite{Tsotsos_Rothenstein11}: Models which can process any visual stimulus (typically, an image or video clip), which can possibly also be given some task definition, and which make predictions that can be compared to human or animal behavioral or physiological responses elicited by the same stimulus and task. Thus, we here place less emphasis on abstract models, phenomenological models, purely data-driven fitting or extrapolation models, or models specifically designed for a single task or for a restricted class of stimuli. For theoretical models, we refer the reader to a number of previous reviews that address attention theories and models more generally \cite{Itti_Koch01nrn,Paletta_etal05,Frintrop_etal10,Rothenstein_Tsotsos08,Gottlieb_Balan10,Toet11,Borji_Itti12pami}.