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...

Automatic image segmentation is emerging field in image processing research domain. In a visual scene, the objects which are different from their surroundings get more visual importance and get high gaze attention of the viewer. Saliency detection predicts significantly important regions in a scene, which should be considered for further processing according to specific applications. There are ...

Image topic discovery is a challenging task in computer vision, which is important for content understanding, image retrieval, and event detection. In recent years, image categorization by combination of Bagof-Word (BoW) model and latent topic discovery models [1, 2] has gained considerable attention. Instead of reading word by word in a document, human is usually attracted by salient objects i...

Traditional saliency detection can effectively detect possible objects using an attentional mechanism instead of automatic object detection, and thus is widely used in natural scene detection. However, it may fail to extract salient objects accurately from remote sensing images, which have their own characteristics such as large data volumes, multiple resolutions, illumination variation, and co...

We present a time-consistent depth estimation algorithm for 2D-to-3D video conversion. The algorithm exploits variance of image to identify the foreground, and uses modified scene change detection method that exploits a color histogram. In simulations the proposed algorithm did not commit depth-reversal or saliency-instability. Keywords—Saliency, Depth-reversal, Estimation instability

The calculation of salient structures is one of the early and basic ideas of perceptual organization in Computer Vision. Saliency algorithms aim to nd image curves, maximizing some deterministic quality measure which grows with the length of the curve, its smoothness, and its continuity. This note proposes a modiied saliency estimation mechanism, which is based on probabilistically speciied gro...

In this paper we present a definition for visual saliency grounded in information theory. This proposal is shown to relate to a variety of classic research contributions in scale-space theory, interest point detection, bilateral filtering, and to existing models of visual saliency. Based on the proposed definition of visual saliency, we demonstrate results competitive with the state-of-the art ...

The research on computational saliency models has been an active topic in the past decades, due to its broad applications in the fields of multimedia processing, computer vision, cognitive science, robotics, etc. Saliency models mainly target two genres of applications, i.e., human fixation prediction or salient object detection/segmentation. Although recent years have witnessed significant pro...

The detection of salient regions is an important pre-processing step for many 3D shape analysis and understanding tasks. This paper proposes a novel method for saliency detection in 3D free form shapes. Firstly, we smooth the surface normals by a bilateral filter. Such a method is capable of smoothing the surfaces and retaining the local details. Secondly, a novel method is proposed for the est...

Motion saliency detection aims at finding the semantic regions in a video sequence. It is an important pre-processing step in many vision applications. In this paper, we propose a new algorithm, Temporal Spectral Residual, for fast motion saliency detection. Different from conventional motion saliency detection algorithms that use complex mathematical models, our goal is to find a good tradeoff...