检索结果-内蒙古大学图书馆

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Mu Li James T. Kwok Bao-Liang Lu Department of Computer Science and Engineering Shanghai Jiaotong University Shanghai China Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong China MOE-Microsoft Key Laboratory for Intelligent Computing and Intelligent Systems Shanghai Jiaotong University Shanghai China

Multiple instance (MI) learning is a recent learning paradigm that is more flexible than standard supervised learning algorithms in the handling of label ambiguity. It has been used in a wide range of applications including image classification, object detection and object tracking. Typically, MI algorithms are trained in a batch setting in which the whole training set has to be available before training starts. However, in applications such as tracking, the classifier needs to be trained continuously as new frames arrive. Motivated by the empirical success of a batch MI algorithm called MILES, we propose in this paper an online MI learning algorithm that has an efficient online update procedure and also performs joint feature selection and classification as MILES. Besides, while existing online MI algorithms lack theoretical properties, we prove that the proposed online algorithm has a (cumulative) regret of O(√T), where T is the number of iterations. In other words, the average regret goes to zero asymptotically and it thus achieves the same performance as the best solution in hindsight. Experiments on a number of MI classification and object tracking data sets demonstrate encouraging results.

关键词： Layout Image reconstruction Semiconductor device modeling Image segmentation Stereo vision Surface reconstruction Surface texture Surface fitting Stereo image processing Rendering (computer graphics)

来源：评论

学校读者我要写书评

暂无评论

Research of geometric computing and its theory

引用

Shanghai Jiaotong Daxue Xuebao/Journal of Shanghai Jiaotong University 2010年第3期44卷 407-412页

作者： He, Yuan-Jun Department of Computer Science and Engineering MOE-Microsoft Key Laboratory for Intelligent Computing and Intelligent System Shanghai Jiaotong University Shanghai 200240 China

A new geometric computing theory was proposed. On the definition level of geometric elements, using the Cartesian coordinates ideology as reference, 2D and 3D ″geometric algebra elements″ (or ″geometric elements″ for short, which could construct an upper-level element in the solving sequence) were constructed by geometry algebraization methods. On the processing level of geometries, geometric problems were solved with geometry methods, by which a geometric element solving sequence could be constructed. Directional property was introduced into geometries in this theory and geometries were represented in a unified format. They help to simplify the processing of finding the geometric element solving sequence for a geometry problem. The paper also tried to theoretically find out an integrated solution for geometry ambiguity issues, and established a unified, standardized geometry computing architecture. The Leibniz's mind-to process geometric objects with geometric language-was implemented in an indirect way!

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

A Parallel Algorithm for Adaptive Local Refinement of Tetrahedral Meshes Using Bisection

引用

Numerical Mathematics(Theory,Methods and Applications) 2009年第1期2卷 65-89页

作者： Lin-Bo Zhang State Key Laboratory of Scientific and Engineering Computing Institute of Computational Mathematics and Scientific/Engineering Computing Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing 100080 China.

Local mesh refinement is one of the key steps in the implementations of adaptive finite element methods. This paper presents a parallel algorithm for distributed memory parallel computers for adaptive local refinement of tetrahedral meshes using bisection. This algorithm is used in PHG, Parallel Hierarchical Grid Chttp：//lsec. cc. ac. cn/phg/）, a toolbox under active development for parallel adaptive finite element solutions of partial differential equations. The algorithm proposed is characterized by allowing simukaneous refinement of submeshes to arbitrary levels before synchronization between submeshes and without the need of a central coordinator process for managing new vertices. Using the concept of canonical refinement, a simple proof of the independence of the resulting mesh on the mesh partitioning is given, which is useful in better understanding the behaviour of the biseetioning refinement procedure.

关键词： Adaptive refinement bisection tetrahedral mesh parallel algorithm MPI.

来源：评论

学校读者我要写书评

暂无评论

Electric-potential reconstructions of single particles using L2-gradient flows

Electric-potential reconstructions of single particles using...

引用

International Conference on BioMedical engineering and Informatics (BMEI)

作者： Ming Li Guoliang Xu Carlos O. S. Sorzano Roberto Melero Chandrajit Bajaj State Key Laboratory of Scientific and Engineering Computing Institute of Computational Mathematics Academy of Mathematics and System Sciences Chinese Academy and Sciences Beijing China Biocomputing Unit. Centro Nacional de Biotecnologia CSIC Campus University Autonoma Madrid Mexico Austin Department of Computer Sciences and Institute of Computational Engineering & Sciences University of Texas Austin Austin TX USA

In this paper, we present a stable, reliable and robust method for reconstructing a three dimensional density function from a set of two dimensional electron microscopy images. By minimizing an energy functional consisting of a fidelity term and a regularization term, a L 2 -gradient flow is derived. The flow is integrated by a finite element method in the spatial direction and an explicit Euler scheme in temporal direction. The experimental results show that the proposed method is efficient and effective.

关键词： Image reconstruction Spline Three dimensional displays Adenoviruses Microscopy Finite element methods

来源：评论

学校读者我要写书评

暂无评论

Emotion classification based on gamma-band EEG

Emotion classification based on gamma-band EEG

引用

31st Annual International Conference of the IEEE engineering in Medicine and Biology Society: engineering the Future of Biomedicine, EMBC 2009

作者： Li, Mu Lu, Bao-Liang Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai 200240 China MOE-Microsoft Key Laboratory for Intelligent Computing and Intelligent Systems Shanghai Jiao Tong University Shanghai 200240 China

ISBN: (纸本)9781424432967

In this paper, we use EEG signals to classify two emotions-happiness and sadness. These emotions are evoked by showing subjects pictures of smile and cry facial expressions. We propose a frequency band searching method to choose an optimal band into which the recorded EEG signal is filtered. We use common spatial patterns (CSP) and linear-SVM to classify these two emotions. To investigate the time resolution of classification, we explore two kinds of trials with lengths of 3s and 1s. Classification accuracies of 93:5% ± 6:7% and 93:0%±6:2% are achieved on 10 subjects for 3s-trials and 1s-trials, respectively. Our experimental results indicate that the gamma band (roughly 30-100 Hz) is suitable for EEG-based emotion classification. ©2009 IEEE.

关键词： Signal processing

来源：评论

学校读者我要写书评

暂无评论

Emotion classification based on gamma-band EEG

Emotion classification based on gamma-band EEG

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Mu Li Bao-Liang Lu Department of Computer Science and Engineering MOE-Microsoft Key Laboratory of Intelligent Computing and Intelligent Systems Shanghai JiaoTong University Shanghai China

In this paper, we use EEG signals to classify two emotions-happiness and sadness. These emotions are evoked by showing subjects pictures of smile and cry facial expressions. We propose a frequency band searching method to choose an optimal band into which the recorded EEG signal is filtered. We use common spatial patterns (CSP) and linear-SVM to classify these two emotions. To investigate the time resolution of classification, we explore two kinds of trials with lengths of 3s and 1s. Classification accuracies of 93.5% plusmn 6.7% and 93.0%plusmn6.2% are achieved on 10 subjects for 3s-trials and 1s-trials, respectively. Our experimental results indicate that the gamma band (roughly 30-100 Hz) is suitable for EEG-based emotion classification.

关键词： Electroencephalography Frequency Neuroscience Psychology Humans Computer displays Emotion recognition USA Councils Spatial resolution Signal resolution

来源：评论

学校读者我要写书评

暂无评论

Abstraction Strategy of Software Knowledge Reuse for Adaptable Knowledge and Information Systems

Abstraction Strategy of Software Knowledge Reuse for Adaptab...

引用

International Conference on Information and Multimedia Technology (ICIMT)

作者： Yinglin Wang Department of Computer Science and Engineering MOE-Microsoft Key Laboratory for Intelligent Computing and Intelligent Systems Shanghai Jiaotong University Shanghai China

Nowadays enterprise information and knowledge systems provide technical platforms for the integration and collaboration of business processes among multi-organizations of enterprises. However, software systems supporting enterprise business processes are hard to be adapted and deployed to satisfy the ever-changing requirements of enterprises. In this paper we put forward an adaptable enterprise information system framework in which we use four levels of abstractions. At the meta-meta model level, the ontology schema is used which provides the specification language for other more specific levels. At the meta-model level, the extended OSM model is used, and the generic elements obtained from analyzing the commonality of requirements are included. At the model level, the commonalities of sub-domains, such as the patterns of tasks in a specific domain are analyzed and generalized for future reuse. The intermediate specifications of the business processes and work flows are used in this level. At the application level, specific elements and requirements of the applications will be added and customized via the tools developed at the abstracted levels. A case study of knowledge management system based on this four level abstraction is discussed.

关键词： Information systems Knowledge management Management information systems Ontologies Enterprise resource planning ISO standards Online Communities/Technical Collaboration Information management Multimedia systems Computer science

来源：评论

学校读者我要写书评

暂无评论

Improving security of an image encryption algorithm based on chaotic circular shift

Improving security of an image encryption algorithm based on...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Weihai Li Yuan Yuan MOE-Microsoft Key Laboratory of Multimedia Computing and Communication University of Science and Technology Hefei China School of Engineering and Applied Science Aston University Birmingham UK

An image encryption algorithm based on chaotic circular bit shift is proposed recently. This paper analyses the security of this algorithm and point out that the key space is not as large as they alleged and the algorithm can not resist chosen-plaintext attack or difference attack. The amount of chosen-plaintexts to carry out an attack is very few. This paper also introduces two methods to improve its security by changing chaotic sequences generators, altering orders of permutation and substitution, and applying feedback link mode. The improved algorithm has variable key space and has very good avalanche effect to resist chosen-plaintext attacks, chosen-ciphertext attacks, or difference attacks. The computation cost of improved algorithm is very low.

关键词： Security Cryptography Chaos Streaming media Logistics Chaotic communication Resists Space technology Cybernetics USA Councils

来源：评论

学校读者我要写书评

暂无评论

A Compression Algorithm for Multi-streams Based on GEP

A Compression Algorithm for Multi-streams Based on GEP

引用

International Conference on Genetic and Evolutionary computing (WGEC)

作者： Chao Ding Chang-an Yuan Xiao Qin Yu-zhong Peng Computer and Information Engineering College Guangxi Teachers Education University Nanning China Key Laboratory of Scientific Computing & Intelligent Information processing University of Guangxi Nanning Guangxi China Computer and Information Engineering College University of Guangxi Nanning China

This paper applied the Methods which based on GEP in compress multi-streams. The contributions of this paper include: 1) giving an introduction to data function finding based on GEP(DFF-GEP), defining the main conception of Multi-Streams, and revealing the map relation in it; 2) putting forward the Compression Algorithm for Multi-Streams according to map relation lied in data between data streams; and 3)providing an experience with the real data and find that (3.1) the compression ratio of the new methods is 120~150 times as the traditional wavelets method, and 35~70 times as the wavelets and coincidence method; (3.2) the relative error of the new method is about 3%, yet maximum relative error is 0.01 by using the traditional relative error standard, the precision is improved from 7% to 15% as compared with the traditional method.

关键词： Compression algorithms scientific computing Competitive intelligence Information processing Chaos Educational institutions Computer science education Monitoring Genetic engineering Gene expression

来源：评论

学校读者我要写书评

暂无评论

Noether conserved quantities and Lie point symmetries of difference Lagrange-Maxwell equations and lattices

引用

Chinese Physics B 2009年第7期18卷 2634-2641页

作者：傅景礼聂宁明黄健飞 Jiménez Salvador 唐贻发 Vzquez Luis 赵维加 Institute of Mathematical Physics Zhejiang Sci-Tech University State Key Laboratory of Scientific and Engineering Computing ICMSECAcademy of Mathematics and Systems ScienceChinese Academy of Sciences Department of Mathematics Qingdao University Departamento de Matema'tica Aplicada TTII E.T.S.I.Telecomunicacio'nUniversidad Polit'ecnica de Madrid28040-MadridSpain Departamento de Matemática Aplicada Facultad de MatemáticasInstituto de Matemática Interdisciplinar(IMI)Universidad Complutense de Madrid28040-MadridSpain Departamento de Matemática Aplicada Facultad de InformáticaInstituto de Matemática Interdisciplinar(IMI)Universidad Complutense de Madrid28040-MadridSpain

This paper presents a method to find Noether-type conserved quantities and Lie point symmetries for discrete mechanico-electrical dynamical systems,which leave invuriant the set of solutions of the corresponding difference scheme. This approach makes it possible to devise techniques for solving the Lagrange Maxwell equations in differences which correspond to mechanico-electrical systems,by adapting existing differential *** particular,it obtains a new systematic method to determine both the one-parameter Lie groups and the discrete Noether conserved quantities of Lie point symmetries for mechanico-electrical *** an application,it obtains the Lie point symmetries and the conserved quantities for the difference equation of a model that represents a capacitor microphone.

关键词： Lagrange Maxwell equation Lie point symmetry discrete mechanico-electrical system conserved quantity

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：