Abstract

V. Navalpakkam, L. Itti, Bottom-up and top-down influences on visual scanpaths, In: Proc. SPIE Human Vision and Electronic Imaging XI (HVEI06), San Jose, CA, (B. Rogowitz, T. N. Pappas, S. Daly Ed.), Vol. 6057, Bellingham, WA:SPIE Press, Jan 2006. (Cited by 8)

Abstract: Visual attention to salient and relevant scene regions is crucial for an animal's survival in the natural world. It is guided by a complex interplay of at least two factors - image-driven, bottom-up salience and knowledge-driven, top-down guidance. For instance, a ripe red fruit among green leaves captures visual attention due to its bottom-up salience, while a non-salient camouflaged predator is detected through top-down guidance to known predator locations and features. Although both bottom-up and top-down factors are important for guiding visual attention, most existing models and theories are either purely top-down or bottom-up. Here, we present a combined model of bottom-up and top-down visual attention.

Themes: Computational Modeling, Model of Bottom-Up Saliency-Based Visual Attention, Model of Top-Down Attentional Modulation