In the area of 3D digital engineering and 3D digital geometry processing, shape simplification is an important task to reduce their requirement of large memory and high time complexity. By incorporating the content-aw...In the area of 3D digital engineering and 3D digital geometry processing, shape simplification is an important task to reduce their requirement of large memory and high time complexity. By incorporating the content-aware visual salience measure of a polygonal mesh into simplification operation, a novel feature-aware shape simplification approach is presented in this paper. Owing to the robust extraction of relief heights on 3D highly detailed meshes, our visual salience measure is defined by a center-surround operator on Gaussian-weighted relief heights in a scale-dependent manner. Guided by our visual salience map, the feature-aware shape simplification algorithm can be performed by weighting the high-dimensional feature space quadric error metric of vertex pair contractions with the weight map derived from our visual salience map. The weighted quadric error metric is calculated in a six-dimensional feature space by combining the position and normal information of mesh vertices. Experimental results demonstrate that our visual salience guided shape simplification scheme can adaptively and effectively re-sample the underlying models in a feature-aware manner, which can account for the visually salient features of the complex shapes and thus yield better visual fidelity.展开更多
Visual cognition,as one of the fundamental aspects of cognitive neuroscience,is generally associated with high-order brain functions in animals and human.Drosophila,as a model organism,shares certain features of visua...Visual cognition,as one of the fundamental aspects of cognitive neuroscience,is generally associated with high-order brain functions in animals and human.Drosophila,as a model organism,shares certain features of visual cognition in common with mammals at the genetic,molecular,cellular,and even higher behavioral levels.From learning and memory to decision making,Drosophila covers a broad spectrum of higher cognitive behaviors beyond what we had expected.Armed with powerful tools of genetic manipulation in Drosophila,an increasing number of studies have been conducted in order to elucidate the neural circuit mechanisms underlying these cognitive behaviors from a genes-brain-behavior perspective.The goal of this review is to integrate the most important studies on visual cognition in Drosophila carried out in China's Mainland during the last decade into a body of knowledge encompassing both the basic neural operations and circuitry of higher brain function in Drosophila.Here,we consider a series of the higher cognitive behaviors beyond learning and memory,such as visual pattern recognition,feature and context generalization,different feature memory traces,salience-based decision,attention-like behavior,and cross-modal leaning and memory.We discuss the possible general gain-gating mechanism implementing by dopamine-mushroom body circuit in fly's visual cognition.We hope that our brief review on this aspect will inspire further study on visual cognition in flies,or even beyond.展开更多
现有基于深度学习的农作物病害识别方法对网络浅层、中层、深层特征中包含的判别信息挖掘不够,且提取的农作物病害图像显著性特征大多不足,为了更加有效地提取农作物病害图像中的判别特征,提高农作物病害识别精度,提出一种基于多层信息...现有基于深度学习的农作物病害识别方法对网络浅层、中层、深层特征中包含的判别信息挖掘不够,且提取的农作物病害图像显著性特征大多不足,为了更加有效地提取农作物病害图像中的判别特征,提高农作物病害识别精度,提出一种基于多层信息融合和显著性特征增强的农作物病害识别网络(Crop disease recognition network based on multi-layer information fusion and saliency feature enhancement,MISF-Net)。MISF-Net主要由ConvNext主干网络、多层信息融合模块、显著性特征增强模块组成。其中,ConvNext主干网络主要用于提取农作物病害图像的特征;多层信息融合模块主要用于提取和融合主干网络浅层、中层、深层特征中的判别信息;显著性特征增强模块主要用于增强农作物病害图像中的显著性判别特征。在农作物病害数据集AI challenger 2018及自制数据集RCP-Crops上的实验结果表明,MISF-Net的农作物病害识别准确率分别达到87.84%、95.41%,F1值分别达到87.72%、95.31%。展开更多
基金Project supported by the National Natural Science Foundation of China(No.61272309)the Key Laboratory of Visual Media Intelligent Process Technology of Zhejiang Province,China(No.2011E10003)
文摘In the area of 3D digital engineering and 3D digital geometry processing, shape simplification is an important task to reduce their requirement of large memory and high time complexity. By incorporating the content-aware visual salience measure of a polygonal mesh into simplification operation, a novel feature-aware shape simplification approach is presented in this paper. Owing to the robust extraction of relief heights on 3D highly detailed meshes, our visual salience measure is defined by a center-surround operator on Gaussian-weighted relief heights in a scale-dependent manner. Guided by our visual salience map, the feature-aware shape simplification algorithm can be performed by weighting the high-dimensional feature space quadric error metric of vertex pair contractions with the weight map derived from our visual salience map. The weighted quadric error metric is calculated in a six-dimensional feature space by combining the position and normal information of mesh vertices. Experimental results demonstrate that our visual salience guided shape simplification scheme can adaptively and effectively re-sample the underlying models in a feature-aware manner, which can account for the visually salient features of the complex shapes and thus yield better visual fidelity.
文摘Visual cognition,as one of the fundamental aspects of cognitive neuroscience,is generally associated with high-order brain functions in animals and human.Drosophila,as a model organism,shares certain features of visual cognition in common with mammals at the genetic,molecular,cellular,and even higher behavioral levels.From learning and memory to decision making,Drosophila covers a broad spectrum of higher cognitive behaviors beyond what we had expected.Armed with powerful tools of genetic manipulation in Drosophila,an increasing number of studies have been conducted in order to elucidate the neural circuit mechanisms underlying these cognitive behaviors from a genes-brain-behavior perspective.The goal of this review is to integrate the most important studies on visual cognition in Drosophila carried out in China's Mainland during the last decade into a body of knowledge encompassing both the basic neural operations and circuitry of higher brain function in Drosophila.Here,we consider a series of the higher cognitive behaviors beyond learning and memory,such as visual pattern recognition,feature and context generalization,different feature memory traces,salience-based decision,attention-like behavior,and cross-modal leaning and memory.We discuss the possible general gain-gating mechanism implementing by dopamine-mushroom body circuit in fly's visual cognition.We hope that our brief review on this aspect will inspire further study on visual cognition in flies,or even beyond.
文摘现有基于深度学习的农作物病害识别方法对网络浅层、中层、深层特征中包含的判别信息挖掘不够,且提取的农作物病害图像显著性特征大多不足,为了更加有效地提取农作物病害图像中的判别特征,提高农作物病害识别精度,提出一种基于多层信息融合和显著性特征增强的农作物病害识别网络(Crop disease recognition network based on multi-layer information fusion and saliency feature enhancement,MISF-Net)。MISF-Net主要由ConvNext主干网络、多层信息融合模块、显著性特征增强模块组成。其中,ConvNext主干网络主要用于提取农作物病害图像的特征;多层信息融合模块主要用于提取和融合主干网络浅层、中层、深层特征中的判别信息;显著性特征增强模块主要用于增强农作物病害图像中的显著性判别特征。在农作物病害数据集AI challenger 2018及自制数据集RCP-Crops上的实验结果表明,MISF-Net的农作物病害识别准确率分别达到87.84%、95.41%,F1值分别达到87.72%、95.31%。
