检索结果-内蒙古大学图书馆

8th IFIP International Conference on intelligent information Processing, IIP 2014

作者： Zhang, Bo Hao, Jie Ma, Gang Yue, Jinpeng Shi, Zhongzhi Chinese Academy of Sciences Institute of Computing Technology The Key Laboratory of Intelligent Information Processing Beijing China University of Chinese Academy of Sciences Beijing China Xuzhou Medical College School of Medicine Information Xuzhou China China University of Mining and Technology School of Computer Science and Technology Xuzhou China

ISBN: (纸本)9783662449790

CCA is a powerful tool for analyzing paired multi-view data. However, when facing semi-paired multi-view data which widely exist in real-world problems, CCA usually performs poorly due to its requirement of data pairing between different views in nature. To cope with this problem, we propose a semi-paired variant of CCA named SemiPCCA based on the probabilistic model for CCA. Experiments with artificially generated samples demonstrate the effectiveness of the proposed method. © IFIP International Federation for information Processing 2014.

关键词： Correlation methods

来源：评论

学校读者我要写书评

暂无评论

A test data compression scheme based on position information coding 5

A test data compression scheme based on position information...

引用

5th International Conference on computing Communication and Networking Technologies, ICCCNT 2014

作者： Chen, Tian Yang, Bingdong Wang, Wei Hao, Birong Ren, Fuji Liu, Jun Wang, Yixin School of Computer and Information Hefei University of Technology Hefei230009 China AnHui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine Hefei University of Technology Hefei230009 China University of Tokushima 770-8506 Japan

ISBN: (纸本)9781479926961

Under the condition of Built-off Self-test (BOST), a novel test data compression scheme based on position information coding is presented, which is targeting test data and test power consumption. The proposed scheme gets the next test stimuli by reversing some bits of the responses corresponding to the previous test vectors. During the process of bit flip, test power problem should be taken into account;both the shift power and capture power during the test should be limited in the scope of security. For shift power, need to modify the scan chain by adding blocking logic;and the capture power reduction through the test cube filling based on the response. Experimental results justify the efficacy of the proposed method in attaining test-data compression;the average compression ratio is 73.63% on the premise of capture power consumption reduced by 20%. © 2014 IEEE.

关键词： Electric power utilization

来源：评论

学校读者我要写书评

暂无评论

Transfer learning with multiple sources via consensus regularized autoencoders

Transfer learning with multiple sources via consensus regula...

引用

European Conference on Machine Learning and Knowledge Discovery in Databases, ECML PKDD 2014

作者： Zhuang, Fuzhen Cheng, Xiaohu Pan, Sinno Jialin Yu, Wenchao He, Qing Shi, Zhongzhi Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China University of Chinese Academy of Sciences Beijing 100049 China Institute for Infocomm Research Singapore Singapore

ISBN: (纸本)9783662448441

Knowledge transfer from multiple source domains to a target domain is crucial in transfer learning. Most existing methods are focused on learning weights for different domains based on the similarities between each source domain and the target domain or learning more precise classifiers from the source domain data jointly by maximizing their consensus of predictions on the target domain data. However, these methods only consider measuring similarities or building classifiers on the original data space, and fail to discover a more powerful feature representation of the data when transferring knowledge from multiple source domains to the target domain. In this paper, we propose a new framework for transfer learning with multiple source domains. Specifically, in the proposed framework, we adopt autoencoders to construct a feature mapping from an original instance to a hidden representation, and train multiple classifiers from the source domain data jointly by performing an entropy-based consensus regularizer on the predictions on the target domain. Based on the framework, a particular solution is proposed to learn the hidden representation and classifiers simultaneously. Experimental results on image and text real-world datasets demonstrate the effectiveness of our proposed method compared with state-of-the-art methods. © 2014 Springer-Verlag.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Expression image preprocessing based on wavelet transform

Expression image preprocessing based on wavelet transform

引用

2014 IEEE International Conference on Robotics and Biomimetics, IEEE ROBIO 2014

作者： Quan, Changqin Xu, Xiaoming Ren, Fuji Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine School of Computer and Information Hefei University of Technology Hefei230009 China University of Tokushima Shinkura-cho Tokushima770-8501 Japan

ISBN: (纸本)9781479973965

In this paper, we present a new image preprocessing method which is based on Wavelet Transform. Before we extract expression texture information, Wavelet transform will be applied to remove partial high frequency information. And then Gabor Transform will be used to extract expression information. At last we chose the Support Vector Machine to classify facial expressions. Experiments on the Japanese Female Facial Expression (JAFFE) Database illustrate that the Wavelet Transform and Gabor features are effective for facial expression discrimination. Additionally, the experiment results validate the feasibility of this method. © 2014 IEEE.

关键词： Wavelet transforms

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

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

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

How Many Packets Are Most Effective for Early Stage Traffic Identification： An Experimental Study

引用

China Communications 2014年第9期11卷 183-193页

作者： PENG Lizhi YANG Bo CHEN Yuehui WU Tong Shandong Provincial Key Laboratory for Network Based Intelligent Computing University of Jinan Jinan 250022 China School of Computer and Information Technology Beijing Jiaotong University Beijing 100044 China

Accurately identifying network traffics at the early stage is very important for the application of traffic *** years,more and more research works have tried to build effective machine learning models to identify traffics with the few packets at the early ***,a basic and important problem is still unresolved,that is how many packets are most effective in early stage traffic *** this paper,we try to resolve this problem using experimental *** firstly extract the packet size of the first 2-10 packets of 3 traffic data *** then execute crossover identification experiments with different numbers of packets using 11 well-known machine learning ***,statistical tests are applied to find out which number is the best performed *** experimental results show that 5-7are the best packet numbers for early stage traffic identification.

关键词： feature extraction early stagetraffic classification machine learning

来源：评论

学校读者我要写书评

暂无评论

Learning Expressionlets on Spatio-Temporal Manifold for Dynamic Facial Expression Recognition

Learning Expressionlets on Spatio-Temporal Manifold for Dyna...

引用

IEEE Conference on Computer Vision and Pattern Recognition

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

ISBN: (纸本)9781479951192

Facial expression is temporally dynamic event which can be decomposed into a set of muscle motions occurring in different facial regions over various time intervals. For dynamic expression recognition, two key issues, temporal alignment and semantics-aware dynamic representation, must be taken into account. In this paper, we attempt to solve both problems via manifold modeling of videos based on a novel mid-level representation, i.e. expressionlet. Specifically, our method contains three key components: 1) each expression video clip is modeled as a spatiotemporal manifold (STM) formed by dense low-level features;2) a Universal Manifold Model (UMM) is learned over all low-level features and represented as a set of local ST modes to statistically unify all the STMs. 3) the local modes on each STM can be instantiated by fitting to UMM, and the corresponding expressionlet is constructed by modeling the variations in each local ST mode. With above strategy, expression videos are naturally aligned both spatially and temporally. To enhance the discriminative power, the expressionlet-based STM representation is further processed with discriminant embedding. Our method is evaluated on four public expression databases, CK+, MMI, Oulu-CASIA, and AFEW. In all cases, our method reports results better than the known state-of-the-art.

关键词： Databases Manifolds Feature extraction Face recognition Covariance matrices Three-dimensional displays 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

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：