检索结果-内蒙古大学图书馆

Visual tracking by combining deep learned image representation with particle filter

ICIC Express Letters, Part B: Applications 2015年第9期6卷 2453-2460页

作者： Chen, Shu Liang, Wenzhang School of Information Engineering Xiangda North Road Yuhu District Xiangtan China Key Laboratory of Intelligent Computing and Information Processing Ministry of Education Xiangtan University Xiangda North Road Yuhu District Xiangtan China Guangxi Cast Animation Limited Company No. 4 High-Tech Zone Nanning China

Deep learning has recently shown outstanding performance on feature extraction. In this paper, we go one step further and address the problem of object tracking using a combination of Convolutional Neural Networks and particle filter. We apply Convolutional Neural Networks offline to learn prior image representations that are more robust to appearance variations. These learned visual prior can be transferred for online object tracking. Especially, within a Bayesian inference framework, the learned neural network is used to construct the observation model and a particle filter is used to estimate the tracking result sequentially. Comparison with the state-of-the-art trackers on a variety of challenging sequences shows that the proposed algorithm is more accurate. © 2015 ISSN 2185-2766.

关键词： Image representation

来源：评论

学校读者我要写书评

暂无评论

Determination of multifractal dimensions of complex networks by means of the sandbox algorithm

引用

Chaos 2015年第2期25卷 023103页

作者： Liu, Jin-Long Yu, Zu-Guo Anh, Vo Hunan Key Laboratory for Computation and Simulation in Science and Engineering Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Xiangtan University Xiangtan Hunan 411105 China School of Mathematical Sciences Queensland University of Technology GPO Box 2434 Brisbane Q4001 Australia

Complex networks have attracted much attention in diverse areas of science and technology. Multifractal analysis (MFA) is a useful way to systematically describe the spatial heterogeneity of both theoretical and experimental fractal patterns. In this paper, we employ the sandbox (SB) algorithm proposed by Tél et al. (Physica A 159, 155-166 (1989)), for MFA of complex networks. First, we compare the SB algorithm with two existing algorithms of MFA for complex networks: the compact-box-burning algorithm proposed by Furuya and Yakubo (Phys. Rev. E 84, 036118 (2011)), and the improved box-counting algorithm proposed by Li et al. (J. Stat. Mech.: Theor. Exp. 2014, P02020 (2014)) by calculating the mass exponents ?(q) of some deterministic model networks. We make a detailed comparison between the numerical and theoretical results of these model networks. The comparison results show that the SB algorithm is the most effective and feasible algorithm to calculate the mass exponents ?(q) and to explore the multifractal behavior of complex networks. Then, we apply the SB algorithm to study the multifractal property of some classic model networks, such as scale-free networks, small-world networks, and random networks. Our results show that multifractality exists in scale-free networks, that of small-world networks is not obvious, and it almost does not exist in random networks. © 2015 AIP Publishing LLC.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dense Invariant Feature Based Support Vector Ranking for Person Re-identification

Dense Invariant Feature Based Support Vector Ranking for Per...

引用

IEEE Global Conference on signal and Information processing

作者： Shoubiao Tan Feng Zheng Ling Shao Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education Anhui University Hefei 230039 China Department of Electronic and Electrical Engineering The University of Sheffield Mappin Street Sheffield S1 3JD UK Department of Computer Science and Digital Technologies Northumbria University Newcastle upon Tyne NE1 8ST UK

ISBN: (纸本)9781479975921

Recently, support vector ranking has been adopted to address the challenging person re-identification problem. However, the ranking model based on ordinary global features cannot represent the significant variation of pose and viewpoint across camera views. Thus, a novel ranking method which fuses the dense invariant features is proposed in this paper to model the variation of images across camera views. By maximizing the margin and minimizing the error score for the fused features, an optimal space for ranking has been learned. Due to the invariance of the dense invariant features and the fusion of the bidirectional features, the proposed method significantly outperforms the original support vector ranking algorithm and is competitive with state-of-the-art techniques on two challenging datasets, showing its potential for real-world person re-identification.

关键词： Person Re-identification Dense Invariant Feature Support Vector Ranking Feature Fusion

来源：评论

学校读者我要写书评

暂无评论

Spectral clustering based on the edge betweenness dissimilarity matrix for community detection

引用

Journal of Information and Computational Science 2014年第11期11卷 3929-3939页

作者： Pei, Tingrui Cao, Yuxin Li, Zhetao Choi, Young-June College of Information Engineering Xiangtan University Xiangtan China Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Xiangtan University Xiangtan China Department of Information and Computer Engineering Ajou University Suwon Korea Republic of

As an important global geometric quantity, edge betweennesses can reflect the impact of corresponding edges in the entire network, which have a very strong practical significance. However, edge betweenness ignores the relationship between the vertices which connected indirectly with the edge. This paper first puts forward a dissimilarity matrix based on a novel edge betweenness, and applies it to a spectral clustering algorithm and finally, in order to detect the community structure in complex networks with this improved algorithm, we use a correction step which is based on the gravitation force of the community. This algorithm has been tested on computer-generated networks and typical real world networks. Compared to GN, PBD, GK and DA, the proposed algorithm possesses an apparent advantage. ©2014 Binary Information Press

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Secondary structure element alignment kernel method for prediction of protein structural classes

引用

Current Bioinformatics 2014年第3期9卷 253-257页

作者： Han, Guo-Sheng Yu, Zu-Guo Anh, Vo Hunan Key Laboratory for Computation and Simulation in Science and Engineering Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Xiangtan University Hunan 411105 China School of Mathematical Sciences Queensland University of Technology GPO Box 2434 Brisbane Q 4001 Australia

In this paper, we aim at predicting protein structural classes for low-homology data sets based on predicted secondary structures. We propose a new and simple kernel method, named as SSEAKSVM, to predict protein structural classes. The secondary structures of all protein sequences are obtained by using the tool PSIPRED and then a linear kernel on the basis of secondary structure element alignment scores is constructed for training a support vector machine classifier without parameter adjusting. Our method SSEAKSVM was evaluated on two low-homology datasets 25PDB and 1189 with sequence homology being 25% and 40%, respectively. The jackknife test is used to test and compare our method with other existing methods. The overall accuracies on these two data sets are 86.3% and 84.5%, respectively, which are higher than those obtained by other existing methods. Especially, our method achieves higher accuracies (88.1% and 88.5%) for differentiating the α+ β class and the α/β class compared to other methods. This suggests that our method is valuable to predict protein structural classes particularly for low-homology protein sequences. The source code of the method in this paper can be downloaded at http://***/myphp/math/research/source/SSEAK_source_***. © 2014 Bentham Science Publishers.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

A hybrid artificial fish-school optimization algorithm for solving the quadratic assignment problem 10

A hybrid artificial fish-school optimization algorithm for s...

引用

2014 10th International Conference on Natural Computation, ICNC 2014

作者： Ziqiang, Li Yi, Yang Yang, Qiwei School of Information and Engineering Xiangtan University Xiangtan411105 China Key Laboratory of Intelligent Computing Information Processing of Ministry of Education Xiangtan411105 China

ISBN: (纸本)9781479951505

The quadratic assignment problem (QAP) is a classic combinatorial optimization problem, which is of the NP-hard nature. In this paper, a hybrid artificial fish school optimization algorithm (HAFSOA) is proposed. In HAFSOA, the heuristic information is used in constructing some better initial individuals and its search ability of the global optimal solution is improved by a combination of the modified fish school optimization and differential evolution. In addition, by taking different visual distances for three behaviors: preying, clustering and following, the convergence speed of the proposed HAFSOA is speeded up. Many QAP experimental results show that the proposed HAFSOA can solve QAP better. © 2014 IEEE.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Identity Recognition of Multi-Haptic Pressure Feature based on Sparse Representation

Identity Recognition of Multi-Haptic Pressure Feature based ...

引用

The 6th International Conference on Computer Research and Development

作者： Yan Zhang Dong Liang Ming Zhu Wenxia Bao Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Physics and Materials ScienceAnhui University School of Electronics and Information Engineering Anhui University Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education

Herein,a new identity recognition method of multi-haptic pressure feature based on sparse representation was *** to the common dynamic features,the regional feature and the ratio of length *** of external bounding rectangle(extracted by using the least area method) were *** subset of dynamic feature was optimized by correlation criterion,the sparse representation of haptic pressure was obtained according to the sparse basis(i.e.,wavelet basis),and the sparse feature vector was calculated by the Topelitz measurement *** that,the haptic pressure feature set was created by combining dynamic feature subset and sparse feature subset ***,Support Vector Machine(SVM) classifier identified more than two objects following the one to many rule and output the identification result according to the rule of majority voting,and the stability of features is studied by calculating the intraclass correlation coefficient(ICC) and coefficient of variation(C.V).Overall,the improved acuracy of identity recognition demonstrating the effectiveness and stability of the multihaptic pressure feature.

关键词： dynamic feature sparse representation optimization correlation criterion recognition

来源：评论

学校读者我要写书评

暂无评论

Color analysis of iron surface structure fabricated by circularly polarized femtosecond laser

引用

Guangxue Jingmi Gongcheng/Optics and Precision Engineering 2015年 23卷 52-56页

作者： Su, Ya-Hui Han, Xiao-Hu Fan, Zhen-Zhu Zhang, Hua-Yong Zhong, Hong-Mei School of Electrical Engineering and Automation Anhui University Hefei230601 China School of Electrical and Information Engineering Anhui University Hefei230601 China Key Laboratory of Intelligent Computing and Signal Processing of the Ministry of Education Anhui University Hefei230039 China

A method to induce multi-colors on an iron surface by using Circularly Polarized Femtosecond Laser (CPFL) processing was proposed. The subwavelength ripples were fabricated by CPFL scanning over the iron surface where covered by randomly distributed nanoparticles with diameters from 50 nm to 190 nm. A while light was used to irradiate the treated iron surface, and the relation between surface colors and incident angles was explored. By changing the incident angles of a white light from 0° to 80°, diverse colors were displayed on the laser-treated iron surface. In order to understand the underlying mechanism of the experimental results, a model of spherical nanoparticles spread randomly on ripples of the iron surface was built by Finite-difference Time Domain (FDTD). The experiments show that the surface reflection spectrum is varied from blue to red by increasing the incident angle of white light, which is consistent with the experimental results. Furthermore, it is found that the reflection spectrum shifts towards blue and the peak increases by decreasing the sizes of nanoparticles. This work may find potential applications in the fields of information storage, identifying codes and anti-counterfeiting patterns. © 2015, Chinese Academy of Sciences. All right reserved.

关键词： Femtosecond lasers

来源：评论

学校读者我要写书评

暂无评论

Survey of community structure segmentation in complex networks

Journal of Software

引用

Journal of Software 2014年第1期9卷 89-93页

作者： Pei, Tingrui Zhang, Hongzhi Li, Zhetao Choi, Youngjune College of Information Engineering Xiangtan University Xiangtan China Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Xiangtan University Xiangtan China Department of Information and Computer Engineering Ajou University Suwon Korea Republic of

Community structure analysis is a hot research spot in social networks and complex networks. In order to summarize recent research progress, this paper reviews the background, the motivation, the advantages and disadvantages of existing works related to community structure discovering. A comprehensive outline was obtained by analysis of different clustering algorithms. © 2014 ACADEMY PUBLISHER.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

The 5th International Conference on Biomedical Engineering and Biotechnology (ICBEB 2016) Abstracts

引用

BMC MEDICAL IMAGING 2016年第SUPPL 1期16卷 65-65页

作者： [Anonymous] Department of MRI Shandong Medical Imaging Research Institute Affiliated to Shandong University Jinan Shandong 250021 People’s Republic of China Department of Interventional Radiology Shandong Provincial Hospital Affiliated to Shandong University Jinan Shandong 250021 People’s Republic of China College of Information Science and Technology Engr. Research Center of Digitized Textile & Fashion Tech. for Ministry of Education Donghua University Shanghai 201620 China Intelligent multimedia information processing Lab College of Software Northeastern University Shenyang Liaoning Province 110004 China Institute of Biomedical and Health Engineering Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen 518055 China School of Computer Science and Technology Nanjing Normal University Nanjing China Department of Electrical Engineering The City College of New York CUNY New York USA Jiangsu Key Laboratory of 3D Printing Equipment and Manufacturing Nanjing China School of Electronic Science and Engineering Nanjing University Nanjing Jiangsu 210046 China College of Engineering Nanyang Technological University Singapore 639798 Singapore School of Electronic Information Shanghai Dianji University Shanghai China School of Natural Sciences and Mathematics Shepherd University Shepherdstown WV 25443 USA Davis College of Agriculture Natural Resources and Design West Virginia University Morgantown WV 26505 USA State Key Laboratory of Millimeter Waves Southeast University Nanjing 210096 China Center of Medical Physics and Technology Hefei Institutes of Physical Science Chinese Academy of Sciences Hefei China College of Agricultural and Life Sciences University of Florida Gainesville FL 32611 USA Courant Institute of Mathematical Sciences New York University New York NY 10012 USA Translational Imaging Division & MRI Unit Columbia University and New York State Psychiatric Institute New York NY 10032 USA Guangxi Key Laboratory of Manufacturing System & Adv

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：