检索结果-内蒙古大学图书馆

Embedding bilateral filter in least squares for efficient edge-preserving image smoothing

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Liu, Wei Zhang, Pingping Chen, Xiaogang Shen, Chunhua Huang, Xiaolin Yang, Jie Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China Dalian University of Technology China University of Shanghai for Science and Technology China University of Adelaide Australia

Edge-preserving smoothing is a fundamental procedure for many computer vision and graphic applications. This can be achieved with either local methods or global methods. In most cases, global methods can yield superior performance over local ones. However, local methods usually run much faster than global ones. In this paper, we propose a new global method that embeds the bilateral filter in the least squares model for efficient edge-preserving smoothing. The proposed method can show comparable performance with the state-of-the-art global method. Meanwhile, since the proposed method can take advantages of the efficiency of the bilateral filter and least squares model, it runs much faster. In addition, we show the flexibility of our method which can be easily extended by replacing the bilateral filter with its variants. They can be further modified to handle more applications. We validate the effectiveness and efficiency of the proposed method through comprehensive experiments in a range of applications. Copyright © 2018, The Authors. All rights reserved.

关键词： Nonlinear filtering

An Application-Oriented Autoscaler Based on Deep Learning

学校读者我要写书评

暂无评论

An Application-Oriented Autoscaler Based on Deep Learning

2018 International Computers, Signals and Systems Conference, ICOMSSC 2018

作者： Cao, Yu Xia, Qianchen Li, Zhaoxi Xu, Liangliang Yang, Jun North China Institute of Computing Technology Fourth Basic Department Beijing China Beihang University School of Computer Science and Engineering Beijing China Beihang University Image Processing Center Beijing China

ISBN: (纸本)9781538667514

In order to meet the performance requirements and reduce resource consumption, researchers have proposed many autoscaling schemes. However, most of them only considered current states of the servers or application that limits the applicability of autoscaler. This paper presents an application-oriented autoscaler based on Long Short Term Memory network and Multi-Layer perceptron. The autoscaler includes a workload prediction model, a response time prediction model and a resource adjusting model. With these models, workload and response time of service are accurately predicted, and mean absolute percentage error of workload prediction is reduced to 3.3 × 10-4. The autoscaler can also provide appropriate adjustment suggestion to server managers. The experiments compared our autoscaler with other models, and results show that our autoscaler had better performance in workload prediction and server adjusting. © 2018 IEEE.

关键词： Long short-term memory

Overview of the CCKS 2019 knowledge graph evaluation track: Entity, relation, event and QA

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Han, Xianpei Wang, Zhichun Zhang, Jiangtao Wen, Qinghua Li, Wenqi Tang, Buzhou Wang, Qi Feng, Zhifan Zhang, Yang Lu, Yajuan Wang, Haitao Chen, Wenliang Shao, Hao Chen, Yubo Liu, Kang Zhao, Jun Wang, Taifeng Zhang, Kezun Wang, Meng Jiang, Yinlin Qi, Guilin Zou, Lei Hu, Sen Zhang, Minhao Lin, Yinnian Chinese Information Processing Laboratory Institute of Software Chinese Academy of Sciences Beijing100190 China School of Artificial Intelligence Beijing Normal University Beijing100875 China 305 Hospital of People’s Liberation Army Beijing100017 China Department of Computer Science and Technology Tsinghua University Beijing100084 China Yidu Cloud Beijing100000 China Harbin Institute of Technology Shenzhen Guangdong518055 China Baidu Beijing100193 China School of Computer Science & Technology Soochow University Suzhou Jiangsu215006 China Gowild Suzhou Jiangsu215002 China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China Ant Financial Hangzhou Zhejiang310000 China School of Computer Science and Engineering Southeast University Nanjing Jiangsu211189 China Key Laboratory of Computer Network Information Integration Southeast University Nanjing Jiangsu211189 China Peking University Beijing100871 China

Knowledge graph models world knowledge as concepts, entities, and the relationships between them, which has been widely used in many real-world tasks. CCKS 2019 held an evaluation track with 6 tasks and attracted more than 1,600 teams. In this paper we give an overview of the knowledge graph evaluation tract at CCKS 2019. By reviewing the task definition, successful methods, useful resources, good strategies and research challenges associated with each task in CCKS 2019, this paper can provide a helpful reference for developing knowledge graph applications and conducting future knowledge graph researches. Copyright © 2020, The Authors. All rights reserved.

关键词： Knowledge graph

Triplet Graph Convolutional Network for Multi-scale Analysis of Functional Connectivity Using Functional MRI 1

学校读者我要写书评

暂无评论

1st International Workshop on Graph Learning in Medical Imaging, GLMI 2019 held in conjunction with the 22nd International Conference on Medical image Computing and Computer-Assisted Intervention, MICCAI 2019

作者： Yao, Dongren Liu, Mingxia Wang, Mingliang Lian, Chunfeng Wei, Jie Sun, Li Sui, Jing Shen, Dinggang Brainnetome Center & National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China Department of Radiology and BRIC University of North Carolina at Chapel Hill Chapel HillNC27599 United States College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing210016 China School of Computer Science Northwestern Polytechnical University Xi’an710072 China National Clinical Research Center for Mental Disorders & Key Laboratory of Mental Health Ministry of Health Peking University Beijing100191 China

ISBN: (数字)9783030358174

ISBN: (纸本)9783030358167

Brain functional connectivity (FC) derived from resting-state functional MRI (rs-fMRI) data has become a powerful approach to measure and map brain activity. Using fMRI data, graph convolutional network (GCN) has recently shown its superiority in learning discriminative representations of brain FC networks. However, existing studies typically utilize one specific template to partition the brain into multiple regions-of-interest (ROIs) for constructing FCs, which may limit the analysis to a single spatial scale (i.e., a fixed graph) determined by the template. Also, previous methods usually ignore the underlying high-order (e.g., triplet) association among subjects. To this end, we propose a multi-scale triplet graph convolutional network (MTGCN) for brain functional connectivity analysis with rs-fMRI data. Specifically, we first employ multi-scale templates for coarse-to-fine ROI parcellation to construct multi-scale FCs for each subject. We then develop a triplet GCN (TGCN) model to learn multi-scale graph representations of brain FC networks, followed by a weighted fusion scheme for classification. Experimental results on 1,218 subjects suggest the efficacy or our method. © 2019, Springer Nature Switzerland AG.

关键词： Brain

Super-resolution reconstruction of color image based on microarray lens

学校读者我要写书评

暂无评论

Super-resolution reconstruction of color image based on micr...

2017 IEEE International Conference on Applied System Innovation, ICASI 2017

作者： Zou, Jiancheng Zhang, Honggen Institute of Image Processing and Pattern Recognition North China University of Technology No. 5 Jinyuanzhuang Road Shijingshan District Beijing China

ISBN: (纸本)9781509048977

In this paper, we propose a novel method which combines with color microarray cameras and super-resolution algorithms. Compared with ordinary cameras, the array camera can capture more details of the image, so better quality low resolution images can be obtained. Array camera has been a great application in depth map extraction and image super-resolution reconstruction [3,4,5]. Pelican and Columbia university present Picam(4 × 4 microarray camera) synthesizes high resolution images along with a range monochrome image[3]. The images produced by most popular camera is color images, so the super resolution algorithm of the Picam can't be applied directly. According to the symmetry of the lens, we use 3 × 3 microarray light field camera which can capture color images. The color images component is extracted for super-resolution reconstruction. The algorithm more efficient compared with the traditional super-resolution algorithm. The advantages of hardware and algorithms can be applied to mobile devices such as mobile phone cameras. © 2017 IEEE.

关键词： Cameras

Sparse Kernel Regression with Coefficient-based `q−regularization

学校读者我要写书评

暂无评论

Journal of Machine Learning Research 2019年 20卷

作者： Shi, Lei Huang, Xiaolin Feng, Yunlong Suykens, Johan A.K. Shanghai Key Laboratory for Contemporary Applied Mathematics School of Mathematical Sciences Fudan University Shanghai China Institute of Image Processing and Pattern Recognition Institute of Medical Robotics Shanghai Jiao Tong University MOE Key Laboratory of System Control and Information Processing Shanghai China Department of Mathematics and Statistics State University of New York at Albany New York United States Department of Electrical Engineering ESAT-STADIUS KU Leuven Kasteelpark Arenberg 10 LeuvenB-3001 Belgium

In this paper, we consider the `q−regularized kernel regression with 0 q−penalty term over a linear span of features generated by a kernel function. We study the asymptotic behavior of the algorithm under the framework of learning theory. The contribution of this paper is two-fold. First, we derive a tight bound on the `2−empirical covering numbers of the related function space involved in the error analysis. Based on this result, we obtain the convergence rates for the `1−regularized kernel regression which is the best so far. Second, for the case 0 ©c 2019 Lei Shi, Xiaolin Huang, Yunlong Feng, and Johan A.K. Suykens.

关键词： Regression analysis

CNN-based invertible wavelet scattering for the investigation of diffusion properties of the in vivo human heart in diffusion tensor imaging

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Deng, Zeyu Wang, Lihui Kuai, Zixiang Chen, Qijian Cheng, Xinyu Yang, Feng Yang, Jie Zhu, Yuemin Key Laboratory of Intelligent Medical Image Analysis and Precise Diagnosis of Guizhou Province College of Computer Science and Technology Guizhou University Guiyang550025 China Imaging Center Harbin Medical University Cancer Hospital Harbin150081 China School of Computer and Information Technology Beijing Jiaotong University Beijing100044 China Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai200240 China University Lyon INSA Lyon CNRS Inserm IRP Metislab CREATIS UMR5220 U1206 LyonF-69621 France

In vivo diffusion tensor imaging (DTI) is a promising technique to investigate noninvasively the fiber structures of the in vivo human heart. However, signal loss due to motions remains a persistent problem in in vivo cardiac DTI. We propose a novel motion-compensation method for investigating in vivo myocardium structures in DTI with free-breathing acquisitions. The method is based on an invertible Wavelet Scattering achieved by means of Convolutional Neural Network (WSCNN). It consists of first extracting translation-invariant wavelet scattering features from DW images acquired at different trigger delays and then mapping the fused scattering features into motion-compensated spatial DW images by performing an inverse wavelet scattering transform achieved using CNN. The results on both simulated and acquired in vivo cardiac DW images showed that the proposed WSCNN method effectively compensates for motion-induced signal loss and produces in vivo cardiac DW images with better quality and more coherent fiber structures with respect to existing methods, which makes it an interesting method for measuring correctly the diffusion properties of the in vivo human heart in DTI under free breathing. Copyright © 2019, The Authors. All rights reserved.

关键词： Diffusion tensor imaging

A generalization theory based on independent and task-identically distributed assumption

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Zheng, Guanhua Sang, Jitao Li, Houqiang Yu, Jian Xu, Changsheng University of Science and Technology of China School of Computer and Information Technology Beijing Key Laboratory of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing100044 China Chinese Academy of Sciences Key Laboratory of Technology in Geo-Spatial Information Processing and Application System Hefei230026 China National Lab of Pattern Recognition Institute of Automation CAS Beijing100190 China University of Chinese Academy of Sciences

—Existing generalization theories analyze the generalization performance mainly based on the model complexity and training process. The ignorance of the task properties, which results from the widely used IID assumption, makes these theories fail to interpret many generalization phenomena or guide practical learning tasks. In this paper, we propose a new Independent and Task-Identically Distributed (ITID) assumption, to consider the task properties into the data generating process. The derived generalization bound based on the ITID assumption identifies the significance of hypothesis invariance in guaranteeing generalization performance. Based on the new bound, we introduce a practical invariance enhancement algorithm from the perspective of modifying data distributions. Finally, we verify the algorithm and theorems in the context of image classification task on both toy and real-world datasets. The experimental results demonstrate the reasonableness of the ITID assumption and the effectiveness of new generalization theory in improving practical generalization performance. Copyright © 2019, The Authors. All rights reserved.

关键词： Classification (of information)

NCEM: Network structural similarity metric-based clustering for noisy cryo-EM single particle images

学校读者我要写书评

暂无评论

NCEM: Network structural similarity metric-based clustering ...

Chinese Automation Congress

作者： Yin Shuo Biao Zhang Hong-Bin Shen Yang Yang Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai China Department of Computer Science Shanghai Jiao Tong University Shanghai China

Cryo-EM single particle image reconstruction is currently a powerful technique for revealing the structure of biomacromolecules. Compared to traditional structural biology techniques like X-Ray, it requires fewer restrictions on specimens and is highly efficient with image processing tools. In this single particle reconstruction protocol, the ultimate goal is to identify different particle projection orientations. Since the picked single particle images are highly noisy, clustering is an important step to refrain noise by dividing images with similar projection angles into groups and averaging these images. The goal of clustering analysis is to assign similar particles into same class, so similarity measurement between particles is an important part in all clustering algorithms. Directly measuring the similarity of two particle images will be unreliable due to their low SNR. In this study, we propose a novel network structural similarity metric-based clustering algorithm NCEM for clustering the single particle images. We first construct a complex network for all particle images, where each node represents a particle. Then calculating the similarity between two nodes using structural similarity. This new network-based single particle image similarity metric has advantages over direct measurement for its noise resistance by using the structural information of the network. Our experiments on both artificial and experimental datasets demonstrate its effectiveness.

关键词： Cryo-EM Single particle image clustering Complex network Structural similarity