An Attribute-Assisted Reranking Model for Web Image Search

An Attribute-Assisted Reranking Model for Web Image Search Abstract Image search reranking is an effective approach to refine the text-based image search result. Most existing reranking approaches are based on low-level visual features. In this paper, we propose to exploit semantic attributes for image search reranking. Based on the classifiers for all the predefined attributes, each image is represented by an attribute feature consisting of the responses from these classifiers. […]


Single Image Super-Resolution Based on Gradient Profile Sharpness

Single Image Super-Resolution Based on Gradient Profile Sharpness Abstract Single image super resolution is a classic and active image processing problem, which aims to generate a high-resolution (HR) image from a low-resolution input image. Due to the severely under-determined nature of this problem, an effective image prior is necessary to make the problem solvable, and […]