We study visual attention by detecting a salient object in an input image. We formulate salient object detection as an image segmentation problem, where we separate the salient object from the image background. We propose a set of novel features including multi-scale contrast, centersurround histogram, and color spatial distribution to describe a salient object locally, regionally, and globally. A Conditional Random Field is learned to effectively combine these features for salient object detection. We also constructed a large image database containing tens of thousands of carefully labeled images by multiple users. To our knowledge, it is the first large image database for quantitative evaluation of visual attention algorithms. We validate our approach on this image database, which is public available with this paper.

Abstract-Salient object detection has been attracting a lot of interest, and recently various heuristic computational models have been designed. In this paper, we formulate saliency map computation as a regression problem. Our method, which is based on multi-level image segmentation, utilizes the supervised learning approach to map the regional feature vector to a saliency score. Saliency scores across multiple layers are finally fused to produce the saliency map. The contributions lie in two-fold. One is that we propose a discriminate regional feature integration approach for salient object detection. Compared with existing heuristic models, our proposed method is able to automatically integrate high-dimensional regional saliency features and choose discriminative ones. The other is that by investigating standard generic region properties as well as two widely studied concepts for salient object detection, i.e., regional contrast and backgroundness, our approach significantly outperforms state-of-the-art methods on six benchmark datasets. Meanwhile, we demonstrate that our method runs as fast as most existing algorithms.

We propose a novel automatic salient object segmentation algorithm which integrates both bottom-up salient stimuli and object-level shape prior, i.e., a salient object has a well-defined closed boundary. Our approach is formalized as an iterative energy minimization framework, leading to binary segmentation of the salient object. Such energy minimization is initialized with a saliency map which is computed through context analysis based on multi-scale superpixels. Object-level shape prior is then extracted combining saliency with object boundary information. Both saliency map and shape prior update after each iteration. Experimental results on two public benchmark datasets show that our proposed approach outperforms state-of-the-art methods.

No abstract

The solution structure of Ca(2+)-ligated calmodulin is determined from residual dipolar couplings measured in a liquid crystalline medium and from a large number of heteronuclear J couplings for defining side chains. Although the C-terminal domain solution structure is similar to the X-ray crystal structure, the EF hands of the N-terminal domain are considerably less open. The substantial differences in interhelical angles correspond to negligible changes in short interproton distances and, therefore, cannot be identified by comparison of NOEs and X-ray data. NOE analysis, however, excludes a two-state equilibrium in which the closed apo conformation is partially populated in the Ca(2+)-ligated state. The difference between the crystal and solution structures of Ca(2+)-calmodulin indicates considerable backbone plasticity within the domains of calmodulin, which is key to their ability to bind a wide range of targets. In contrast, the vast majority of side chains making up the target binding surface are locked into the same chi(1) rotameric states as in complexes with target peptide.