检索结果-内蒙古大学图书馆

13th International Conference on Machine Learning and Cybernetics, ICMLC 2014

作者： Liao, Xiangwen Huang, Yichao Wei, Jingjing Yu, Zhiyong Chen, Guolong College of Mathematics and Computer Science Fuzhou University Fuzhou350116 China College of Physics and Information Engineering Fuzhou University Fuzhou350116 China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou350116 China

ISBN: (纸本)9783662456514

Microblogging services, such as Twitter, have become popular for people to share their opinions towards a broad range of topics. It is a great challenge to get an overview of some important topics by reading all tweets every day. Previous researches such as opinion detection and opinion summarization have been studied for this problem. However, these works mainly focus on the content of text without taking the quality of short text and features of social media into consideration. In this paper, we propose a heterogeneous graph model for users’ opinion detection on microblog. We first extract keywords of topics. Then, a three-level microblog graph is constructed by combining user influence, word importance, post significance, and topic periodicity. Microblog posts are ranked from different topics by using the random walk algorithm. Experimental results on real a dataset validate the effectiveness of our approach. In comparison with baseline approaches, the proposed method achieves 8% improvement. © Springer-Verlag Berlin Heidelberg 2014.

关键词： Random processes

来源：评论

学校读者我要写书评

暂无评论

Stacked Progressive Auto-Encoders (SPAE) for Face Recognition Across Poses

Stacked Progressive Auto-Encoders (SPAE) for Face Recognitio...

引用

IEEE Conference on Computer Vision and Pattern Recognition

作者： Meina Kan Shiguang Shan Hong Chang Xilin Chen Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology

ISBN: (纸本)9781479951192

Identifying subjects with variations caused by poses is one of the most challenging tasks in face recognition, since the difference in appearances caused by poses may be even larger than the difference due to identity. Inspired by the observation that pose variations change non-linearly but smoothly, we propose to learn pose-robust features by modeling the complex non-linear transform from the non-frontal face images to frontal ones through a deep network in a progressive way, termed as stacked progressive auto-encoders (SPAE). Specifically, each shallow progressive auto-encoder of the stacked network is designed to map the face images at large poses to a virtual view at smaller ones, and meanwhile keep those images already at smaller poses unchanged. Then, stacking multiple these shallow auto-encoders can convert non-frontal face images to frontal ones progressively, which means the pose variations are narrowed down to zero step by step. As a result, the outputs of the topmost hidden layers of the stacked network contain very small pose variations, which can be used as the pose-robust features for face recognition. An additional attractiveness of the proposed method is that no pose estimation is needed for the test images. The proposed method is evaluated on two datasets with pose variations, i.e., MultiPIE and FERET datasets, and the experimental results demonstrate the superiority of our method to the existing works, especially to those 2D ones.

关键词： Face Three-dimensional displays Transforms Face recognition Solid modeling Decoding Training

来源：评论

学校读者我要写书评

暂无评论

Learning Euclidean-to-Riemannian Metric for Point-to-Set Classification

Learning Euclidean-to-Riemannian Metric for Point-to-Set Cla...

引用

IEEE Conference on Computer Vision and Pattern Recognition

作者： Zhiwu Huang Ruiping Wang Shiguang Shan Xilin Chen Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology

ISBN: (纸本)9781479951192

In this paper, we focus on the problem of point-to-set classification, where single points are matched against sets of correlated points. Since the points commonly lie in Euclidean space while the sets are typically modeled as elements on Riemannian manifold, they can be treated as Euclidean points and Riemannian points respectively. To learn a metric between the heterogeneous points, we propose a novel Euclidean-to-Riemannian metric learning framework. Specifically, by exploiting typical Riemannian metrics, the Riemannian manifold is first embedded into a high dimensional Hilbert space to reduce the gaps between the heterogeneous spaces and meanwhile respect the Riemannian geometry of the manifold. The final distance metric is then learned by pursuing multiple transformations from the Hilbert space and the original Euclidean space (or its corresponding Hilbert space) to a common Euclidean sub-space, where classical Euclidean distances of transformed heterogeneous points can be measured. Extensive experiments clearly demonstrate the superiority of our proposed approach over the state-of-the-art methods.

关键词： Manifolds Hilbert space Kernel Extraterrestrial measurements Geometry

来源：评论

学校读者我要写书评

暂无评论

A database encryption scheme based on the generalized aryabhata remainder theorem

引用

Journal of information Hiding and Multimedia Signal processing 2014年第4期5卷 603-613页

作者： Liu, Yanjun Liu, Yanjun Chang, Chin-Chen Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei230039 China Department of Computer Science and Information Engineering Asia University Taichung413 Taiwan No.26 Hexing Road Xiangfang District Harbin China Department of Information Engineering and Computer Science Feng Chia University Taichung407 Taiwan

Database security prevents the disclosure of confidential data within a database to unauthorized users, and has become an urgent challenge for a tremendous number of database applications. Data encryption is a widely-used cryptographic technique for realizing database security in which the data kept in the database are encrypted into ciphertext. Inspired by Lin et al.’s database encryption system, we propose a record-oriented database encryption scheme based on the Generalized Aryabhata Remainder Theorem (GART). Analysis showed that our proposed scheme is more efficient than Lin et al.’s scheme, while retaining the same security. ©2014.

关键词： Database systems

来源：评论

学校读者我要写书评

暂无评论

A group key distribution system based on the generalized aryabhata remainder theorem for enterprise digital rights management

引用

Journal of information Hiding and Multimedia Signal processing 2015年第1期6卷 140-153页

作者： Liu, Yanjun Chang, Chin-Chen Chang, Shih-Chang Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University No.111 Jiulong Rd Hefei230601 China Department of Computer Science and Information Engineering Asia University No.500 Lioufeng Rd Wufeng Taichung413 Taiwan Department of Information Engineering and Computer Science Feng Chia University No.100 Wenhwa Rd Seatwen Taichung407 Taiwan Department of Computer Science and Information Engineering National Chung Cheng University No.168 Sec.1 University Rd Min-Hsiung Township Chiayi621 Taiwan

Digital Rights Management (DRM) is a type of access-control technology that is used by diverse content providers to restrict the use of digital content. Enterprise Digital Rights Management (E-DRM) is an application of DRM techniques for managing the control of access to sensitive documents in an enterprise. In this paper, we propose a group key distribution system for E-DRM based on the concept of a secret-sharing mechanism and the generalized Aryabhata remainder theorem (GART). To the best of our knowledge, no previous publications related to E-DRM technologies have presented the group key distribution system that we propose. In our system, different groups of enterprise members within the enterprise obtain different digital content in parallel without collision by using their group’s unique session key;all members within each group share a common session key to decrypt the same digital documents to acquire the correct content. We proved that our system achieves the goal of providing high security, which includes preventing inside and outside attacks and offering forward and backward secrecy. © 2015.

关键词： Copyrights

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

Sign language recognition by 3D trajectory matching in frequency domain

引用

Ruan Jian Xue Bao/Journal of Software 2014年 25卷 36-43页

作者： Lin, Yu-Shun Chai, Xiu-Juan Xu, Zhi-Hao Yin, Fang Chen, Xi-Lin Key Laboratory of Intelligent Information Processing Institute of Computing Technology The Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China

For hearing-impaired people, sign language is a common communication means just like spoken language to ordinary people. Because most of ordinary people cannot understand sign language, it's difficult for hearing-impaired community to participate in social activities. This paper proposes an effective method for sign language recognition with simple 3D trajectory information to break down the barriers between hearing-impaired and normal persons. First of all, the 3D trajectory captured from Kinect is preprocessed, and both the trajectories from the probe and galleries is normalized by the size of the signer. Then the trajectories are resampled evenly by a fast, easy, and usable interpolation algorithm. Before matching of two curves, the trajectory of the probe is aligned to the gallery trajectory and both aligned trajectories are transferred into frequency domain by DFT, and vectors linking the real part, imaginary part and amplitude are obtained. Finally, Euclidean distance between two trajectories in frequency domain is calculated to evaluate the dis-similarity of two trajectory vectors according to the minimized distance. The experimental results on a data set of 239 sign words show that the presented approach is effective to recognizing isolated words of Chinese sign language. ©2014 ISCAS.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

A hybrid approach of PTSVM and ELM inspired by samples' geometric distribution structure

A hybrid approach of PTSVM and ELM inspired by samples' geom...

引用

IEEE International Conference on Granular computing (GRC)

作者： Hong Hu Panyi Ouyang Liang Pang Zhongzhi Shi Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China

In this paper, we try to hybrid projection twin support vector machine (PTSVM) and Extreme Learning Machine(ELM). The experiments shows that ELM generally out performs SVM/LS-SVM in various kinds of cases. PTELM tries to use ELM to overcome the shortness of PTSVM, which lacks of flexibility to change nonlinear kernel mapping for complex samples distribution regions. In order to overcome the shortness of ELMs, we try to maintain the geometric structure of the samples distribution in the initial setting of ELM parameters by starting with an auto-encoder ELM, a sufficient condition for such kind auto-encoder ELM to keep the equivalence of topological homology before and after nonlinear mapping is proved by us. For an auto-encoder, in order to do feature abstraction and find the exact manifold in which samples are located, the number of inner layers nodes should be small enough. For this purpose, we prove that the whole samples set can be at least replaced by a small subset which located on the boundary of distribution region. For more, the weights are modified by a ELM approach to make samples of a class move toward this classs hyperplane found by PTSVM. The experimental results on several UCI benchmark data sets show the feasibility and effectiveness of the proposed method.

关键词： Support vector machines Kernel Training Transforms Shape Vectors Manifolds

来源：评论

学校读者我要写书评

暂无评论

A weighted lexicon-based generative model for opinion retrieval

A weighted lexicon-based generative model for opinion retrie...

引用

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： Xiang-Wen Liao Hu Chen Jing-Jing Wei Zhi-Yong Yu Guo-Long Chen Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou China

ISBN: (纸本)9781479942145

In recent years, opinion retrieval attracted a growing research interest as online users' opinions become more and more valuable for market survey, political polls, etc. The goal of opinion retrieval is to find relevant and opinionate documents according to a user's query. Compared with previous lexicon-based generative model for opinion retrieval considering that the sentiment words are equal for a query, which cannot reflect different sentiment words' relevant opinion strength, we propose a graph-based approach by using HITS model to capture the sentiment words' relevant opinion strength. Then the weights are incorporated into the weighted lexicon-based generative model for opinion retrieval. Experimental results on two datasets show the effectiveness of the proposed generative model. Compared with the baseline approach, improvements of 4% and 11% have been obtained on two real datasets.

关键词： Computational modeling Twitter Analytical models Abstracts

来源：评论

学校读者我要写书评

暂无评论

A Gentzen system for the description logic

A Gentzen system for the description logic

引用

International Conference on Computer Science & Education (ICCSE)

作者： Yu Sun Yuefei Sui Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing CN

The Gentzen systems for a sequent Γ⇒Δ have been proposed in the propositional logic, the predicate calculus and other logics. In this paper, based on the Gentzen system for the predicate calculus, we propose the Gentzen system for a sequent Γ⇒Δ in the description logic, where Γ and Δ are two sets of assertions in ALC: Assertions with universal qualification and inclusion assertions are decomposed as those of universal quantification formulas in the Gentzen system for the predicate calculus. It is proved that the Gentzen system for description logic is sound and complete; but it is not decidable.

关键词： Computers Calculus

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：