This paper formulates bottom-up visual saliency as center surround conditional entropy and presents a fast and efficient technique for the computation of such a saliency map. It is shown that the new saliency formulation is consistent with self-information based saliency, decision-theoretic saliency and Bayesian definition of surprises but also faces the same significant computational challenge...

The biological plausibility of statistical inference and learning, tuned to the statistics of natural images, is investigated. It is shown that a rich family of statistical decision rules, confidence measures, and risk estimates, can be implemented with the computations attributed to the standard neurophysiological model of V1. In particular, different statistical quantities can be computed thr...

We propose a definition of saliency by considering what the visual system is trying to optimize when directing attention. The resulting model is a Bayesian framework from which bottom-up saliency emerges naturally as the self-information of visual features, and overall saliency (incorporating top-down information with bottom-up saliency) emerges as the pointwise mutual information between the f...

As a newly emerging and significant topic in computer vision community, co-saliency detection aims at discovering the common salient objects in multiple related images. The existing methods often generate the co-saliency map through a direct forward pipeline which is based on the designed cues or initialization, but lack the refinement-cycle scheme. Moreover, they mainly focus on RGB image and ...

In this paper, we present an image saliency detection method by constructing graph model. We extract color, texture and compactness features and segment superpixels from an input image to construct a graph model. Then, saliency for each is measured by calculating random walker probability on the node. Extensive results on MSRA dataset containing 1000 test images with ground truths demonstrate t...

Depth information has been shown to affect identification of visually salient regions in images. In this paper, we investigate the role of depth in saliency detection in the presence of (i) competing saliencies due to appearance, (ii) depth-induced blur and (iii) centre-bias. Having established through experiments that depth continues to be a significant contributor to saliency in the presence ...

In this paper, we propose a new framework to predict visual scanpaths of observers while they freely watch a visual scene. The visual fixations are inferred from bottom-up saliency and several oculomotor biases. Bottom-up saliency is represented by a saliency map whereas the oculomotor biases (saccade amplitudes and saccade orientations) are modeled using public eye tracking datasets. Our exper...

Abstract: Saliency map is an important and very useful representation of visually important parts of the image. It highlights the salient parts of the image by limiting the visual information coming to the human visual system (HVS). Many models have been proposed in the literature for computing the saliency maps. All of them are having their own pros and cons. No model is perfect. But it has be...