Xiaoyong Shen

Learn More
Images containmany levels of important structures and edges. Compared to masses of research to make filters edge preserving, finding scale-aware local operations was seldom addressed in a practical way, albeit similarly vital in image processing and computer vision. We propose a new framework to filter images with the complete control of detail smoothing(More)
We propose a fine-grained recognition system that incorporates part localization, alignment, and classification in one deep neural network. This is a nontrivial process, as the input to the classification module should be functions that enable back-propagation in constructing the solver. Our major contribution is to propose a valve linkage function (VLF)(More)
We report the sequencing at 131× coverage, de novo assembly and analyses of the genome of a female Tibetan wild boar. We also resequenced the whole genomes of 30 Tibetan wild boars from six major distributed locations and 18 geographically related pigs in China. We characterized genetic diversity, population structure and patterns of evolution. We searched(More)
Color, infrared, and flash images captured in different fields can be employed to effectively eliminate noise and other visual artifacts. We propose a two-image restoration framework considering input images in different fields, for example, one noisy color image and one dark-flashed near infrared image. The major issue in such a framework is to handle(More)
Images now come in different forms – color, near-infrared, depth, etc. – due to the development of special and powerful cameras in computer vision and computational photography. Their cross-modal correspondence establishment is however left behind. We address this challenging dense matching problem considering structure variation possibly existing in these(More)
Previous joint/guided filters directly transfer structural information from the reference to the target image. In this paper, we analyze the major drawback—that is, there may be completely different edges in the two images. Simply considering all patterns could introduce significant errors. To address this issue, we propose the concept of mutual-structure,(More)
Reliable estimation of visual saliency is helpful to guide many computer graphics tasks including shape matching, simplification, segmentation, etc. Inspired by basic principles induced by psychophysics studies, we propose a novel approach for computing saliency for 3D mesh surface considering both local contrast and global rarity. First, a multi-scale(More)
Color, infrared and flash images captured in different fields can be employed to effectively eliminate noise and other visual artifacts. We propose a two-image restoration framework considering input images from different fields, for example, one noisy color image and one dark-flashed near-infrared image. The major issue in such a framework is to handle all(More)
They can be written in vector forms respectively as E1(s, I) = (s − PxCxI) Ax(s − PxCxI) + (s − PyCyI) Ay(s − PyCyI), (4) E2(I) = (I − I0) B(I − I0), (5) where s, I and I0 are vector representations of s, I and I0. Cx and Cy are discrete backward difference matrices that are used to compute image gradients in the xand ydirections. Px, Py , Ax, Ay and B are(More)
Two hundred and seventy-three CIMMYT bread wheat cultivars and advanced lines grown under irrigated conditions in Mexico during the 2005-06 Yaqui crop cycle were characterized for quality-related genetic traits using gene-specific markers for some high- and low-molecular-weight glutenin subunit (HMW-GS and LMW-GS) genes, polyphenol oxidase (PPO), phytoene(More)