• Pattern mining based saliency seeds selection method The pattern mining based method is capable of high-level understanding and recognizes discriminative and representative saliency patterns, thus output more accurate saliency seeds. • ERW based seeds propagation method The proposed External Random Walk (ERW) algorithm in one hand ensures the diffusion of seeds information to more distant are...

Topological methods have been successfully used to identify features in scalar fields and to measure their importance. In this paper, we define a notion of topological saliency that captures the relative importance of a topological feature with respect to other features in its local neighborhood. Features are identified by extreme points of an input scalar field, and their importance measured b...

Models of visual attention postulate the existence of a saliency map whose function is to guide attention and gaze to the most conspicuous regions in a visual scene. Although cortical representations of saliency have been reported, there is mounting evidence for a subcortical saliency mechanism, which pre-dates the evolution of neocortex. Here, we conduct a strong test of the saliency hypothesi...

Visual saliency, which distinguishes “interesting” visual content from others, plays an important role in multimedia and computer vision applications. This chapter starts with a brief overview of visual saliency as well as the literature of some popular models to detect salient regions. We describe two methods to model visual saliency – one in images and the other in videos. Specifically, we in...

1) Co-saliency Generation: Appropriate neighboring warped saliency maps are fused with the saliency maps of activators to generate different co-saliency maps. These maps are then similarly fused through averaging for generating eventual co-saliency object prior (O). 2) Bounding-Box Filtering: Co-saliency object prior helps in filtering out noisy bounding box proposals and keep good proposals. 3...

In this study, we investigate whether the aggregation of saliency maps allows to outperform the best saliency models. This paper discusses various aggregation methods; six unsupervised and four supervised learning methods are tested on two existing eye fixation datasets. Results show that a simple average of the TOP 2 saliency maps significantly outperforms the best saliency models. Considering...

This paper proposes a method to obtain more distinct class saliency maps than Simonyan et al. (2014). We made three improvements over their method: (1) using CNN derivatives with respect to feature maps of the intermediate convolutional layers with up-sampling instead of an input image; (2) subtracting saliency maps of the other classes from saliency maps of the target class to differentiate ta...

A low-complexity saliency detection algorithm for perceptual video coding is proposed; low-level encoding information is adopted as the characteristics of visual perception analysis. Firstly, this algorithm employs motion vector (MV) to extract temporal saliency region through fast MV noise filtering and translational MV checking procedure. Secondly, spatial saliency region is detected based on...

Salient parts of a visual scene attract longer and earlier fixations of the eyes. Saliency is driven by bottom-up (image dependent) factors and top-down factors such as behavioral relevance, goals, and expertise. It is currently assumed that a saliency map defining eye fixation priorities is stored in neural structures that remain to be determined. Lesion studies support a role for the amygdala...

The saliency map is a computational model and has been constructed for simulating human saliency processing, e.g. pop-out target detection (e.g. Itti & Koch, 2000). In this study the spatial structure on the saliency map was investigated. It is proposed that the saliency map is structured into processing units whose size is increasing with retinal eccentricity. In two experiments the distance b...