State-of-the-Art in Visual Attention Modeling

TLDR

Visual attention modeling, especially stimulus‑driven saliency‑based approaches, has been a highly active research area for 25 years, producing numerous models that contribute theoretically and find successful applications in computer vision, mobile robotics, and cognitive systems. The authors review the computational concepts underlying attention models. They present a taxonomy of about 65 attention models, compare them using 13 behavioral and computational criteria, and discuss challenges such as biological plausibility, eye‑movement correlation, top‑down/bottom‑up dissociation, and performance metrics. The review identifies current research trends and offers insights for future directions in attention modeling.

Abstract

Modeling visual attention-particularly stimulus-driven, saliency-based attention-has been a very active research area over the past 25 years. Many different models of attention are now available which, aside from lending theoretical contributions to other fields, have demonstrated successful applications in computer vision, mobile robotics, and cognitive systems. Here we review, from a computational perspective, the basic concepts of attention implemented in these models. We present a taxonomy of nearly 65 models, which provides a critical comparison of approaches, their capabilities, and shortcomings. In particular, 13 criteria derived from behavioral and computational studies are formulated for qualitative comparison of attention models. Furthermore, we address several challenging issues with models, including biological plausibility of the computations, correlation with eye movement datasets, bottom-up and top-down dissociation, and constructing meaningful performance measures. Finally, we highlight current research trends in attention modeling and provide insights for future.