Visual Attention is Beyond One Single Saliency Map

TL;DR

This paper argues that visual attention should be modeled as a dynamic process rather than a single static saliency map, using a frequency domain model to better predict human fixation behavior over time.

Contribution

It introduces a global inhibition model in the frequency domain to simulate the dynamic nature of visual attention and fixation distribution.

Findings

Model predicts human dynamic fixation distribution effectively.

Dynamic attention process varies over time and is influenced by a key parameter.

Single saliency maps are insufficient to describe human visual attention.

Abstract

Of later years, numerous bottom-up attention models have been proposed on different assumptions. However, the produced saliency maps may be different from each other even from the same input image. We also observe that human fixation map varies across time greatly. When people freely view an image, they tend to allocate attention at salient regions of large scale at first, and then search more and more detailed regions. In this paper, we argue that, for one input image visual attention cannot be described by only one single saliency map, and this mechanism should be modeled as a dynamic process. Under the frequency domain paradigm, we proposed a global inhibition model to mimic this process by suppressing the {\it non-saliency} in the input image; we also show that the dynamic process is influenced by one parameter in the frequency domain. Experiments illustrate that the proposed model is capable of predicting human dynamic fixation distribution.