Visual saliency detection model simulates the human visual system to perceive the scene, and has been widely used in many vision tasks. With the acquisition technology development, more comprehensive information, such as depth cue, inter-image correspondence, or temporal relationship, is available to extend image saliency detection to RGBD saliency detection, co-saliency detection, or video sal...

Co-saliency detection is a newly emerging and rapidly growing research area in computer vision community. As a novel branch of visual saliency, co-saliency detection refers to the discovery of common and salient foregrounds from two or more relevant images, and can be widely used in many computer vision tasks. The existing co-saliency detection algorithms mainly consist of three components: ext...

The success of current deep saliency detection methods heavily depends on the availability of large-scale supervision in the form of per-pixel labeling. Such supervision, while labor-intensive and not always possible, tends to hinder the generalization ability of the learned models. By contrast, traditional handcrafted features based unsupervised saliency detection methods, even though have bee...

—Traditional saliency models usually adopt hand-crafted image features and human-designed mechanisms to calculate local or global contrast. In this paper, we propose a novel computational saliency model, i.e., deep spatial contextual long-term recurrent convolutional network (DSCLRCN) to predict where people looks in natural scenes. DSCLRCN first automatically learns saliency related local feat...

Objective image quality metrics (IQMs) potentially benefit from the addition of visual saliency. However, challenges to optimising the performance of saliency-based IQMs remain. A previous eye-tracking study has shown that gaze is concentrated in fewer places in images with highly salient features than in images lacking salient features. From this, it can be inferred that the former are more li...

We assessed the role of saliency in driving observers to fixate the eyes in social scenes. Saliency maps (Itti & Koch, 2000) were computed for the scenes from three previous studies. Saliency provided a poor account of the data. The saliency values for the first-fixated locations were extremely low and no greater than what would be expected by chance. In addition, the saliency values for the ey...

The validity of using conventional saliency map models to predict human attention was investigated for video captured with an egocentric camera. Since conventional visual saliency models do not take into account visual motion caused by camera motion, high visual saliency may be erroneously assigned to regions that are not actually visually salient. To evaluate the validity of using saliency map...

Saliency Detection is a hot research topic in both biological and computer vision. Salient structures, edges, regions would greatly contribute to high-level semantics understanding of people’s attention and improve retrieval precision, object detection, edge detection and etc. In this paper, based on the biological principle in visual system, we present a saliency detection system which combine...

This paper presents an approach for top-down saliency detection guided by visual classification tasks. We first learn how to compute visual saliency when a specific visual task has to be accomplished, as opposed to most state-of-theart methods which assess saliency merely through bottom-up principles. Afterwards, we investigate if and to what extent visual saliency can support visual classifica...

Saliency detection is useful for many computer vision tasks including content-based image retrieval, segmentation, and object detection. However, methods on saliency detection are usually greatly affected by factors like features and segmentation results. We propose a novel selective segmentation-based saliency detection model to decrease the side effects caused by these factors. After extracti...