检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

2,260 篇 会议
1,475 篇 期刊文献
5 册 图书

馆藏范围

3,740 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

2,366 篇 工学
- 1,517 篇 计算机科学与技术...
- 1,233 篇 软件工程
- 595 篇 信息与通信工程
- 383 篇 电子科学与技术（可...
- 319 篇 电气工程
- 300 篇 控制科学与工程
- 193 篇 生物工程
- 182 篇 机械工程
- 171 篇 光学工程
- 129 篇 生物医学工程（可授...
- 122 篇 化学工程与技术
- 115 篇 仪器科学与技术
- 84 篇 动力工程及工程热...
- 67 篇 材料科学与工程（可...
- 58 篇 网络空间安全
- 53 篇 建筑学
- 46 篇 土木工程
1,415 篇 理学
- 902 篇 数学
- 411 篇 物理学
- 225 篇 生物学
- 216 篇 统计学（可授理学、...
- 134 篇 化学
- 124 篇 系统科学
565 篇 管理学
- 299 篇 管理科学与工程(可...
- 283 篇 图书情报与档案管...
- 100 篇 工商管理
97 篇 医学
- 81 篇 临床医学
- 63 篇 基础医学(可授医学...
- 42 篇 药学(可授医学、理...
58 篇 法学
- 45 篇 社会学
49 篇 农学
33 篇 经济学
21 篇 教育学
11 篇 军事学
10 篇 艺术学
9 篇 哲学
8 篇 文学

主题

142 篇 feature extracti...
105 篇 semantics
87 篇 training
78 篇 laboratories
68 篇 information proc...
65 篇 image segmentati...
65 篇 computational mo...
55 篇 optimization
55 篇 data mining
53 篇 computers
50 篇 face recognition
49 篇 signal processin...
49 篇 accuracy
48 篇 visualization
47 篇 robustness
46 篇 signal processin...
44 篇 deep learning
42 篇 support vector m...
42 篇 humans
41 篇 machine learning

机构

439 篇 key laboratory o...
224 篇 university of ch...
210 篇 key laboratory o...
102 篇 key laboratory o...
83 篇 key laboratory o...
65 篇 school of comput...
65 篇 peng cheng labor...
64 篇 college of compu...
62 篇 key laboratory o...
53 篇 anhui university...
53 篇 college of mathe...
53 篇 key laboratory o...
49 篇 key laboratory o...
46 篇 key laboratory o...
46 篇 hunan provincial...
45 篇 the key laborato...
44 篇 school of comput...
43 篇 graduate univers...
41 篇 college of infor...
39 篇 fujian provincia...

作者

91 篇 zhongzhi shi
86 篇 huang zhixiang
85 篇 shi zhongzhi
74 篇 li yingsong
73 篇 shiguang shan
73 篇 xilin chen
69 篇 zhixiang huang
62 篇 liu qun
62 篇 huang qingming
57 篇 yingsong li
56 篇 xianliang wu
51 篇 shi minjia
43 篇 xu qianqian
41 篇 wu xianliang
39 篇 wu xian-liang
39 篇 feng yang
36 篇 he qing
35 篇 luo bin
33 篇 bin luo
32 篇 wen gao

语言

3,445 篇 英文
200 篇 其他
106 篇 中文

检索条件"机构=The Key Laboratory of Intelligent Computing and Signal Processing"

共 3740 条记录，以下是3331-3340 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Learning long term face aging patterns from partially dense aging databases

Learning long term face aging patterns from partially dense ...

引用

International Conference on Computer Vision (ICCV)

作者： Jinli Suo Xilin Chen Shiguang Shan Wen Gao Key Laboratory of Intelligent Information Processing of CAS Institute for Computing Technology Beijing China Chinese Academy and Sciences China School of Electronic Engineering and Computer Science Peking University China

Studies on face aging are handicapped by lack of long term dense aging sequences for model training. To handle this problem, we propose a new face aging model, which learns long term face aging patterns from partially dense aging databases. The learning strategy is based on two assumptions: (i) short term face aging pattern is relatively simple and is possible to be learned from currently available databases; (ii) long term face aging is a continuous and smooth Markov process. Adopting a compositional face representation, our aging algorithm learns a function-based short term aging model from real aging sequences to infer facial parameters within a short age span. Based on the predefined smoothness criteria between two overlapping short term aging patterns, we concatenate these learned short term aging patterns to build the long term aging patterns. Both the subjective assessment and objective evaluations of synthetic aging sequences validate the effectiveness of the proposed model.

关键词： Aging Databases Biological system modeling Prototypes Face detection Skin Content addressable storage Computer vision Muscles Deformable models

来源：评论

学校读者我要写书评

暂无评论

Modeling latent aspects for automatic image annotation

Modeling latent aspects for automatic image annotation

引用

IEEE International Conference on Image processing

作者： Zhixin Li Zhiping Shi Zhiqing Li Zhongzhi Shi Chinese Academy and Sciences Beijing China The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy and Sciences Beijing China Chinese Academy of Sciences Beijing Beijing CN

In this paper, we present an approach based on probabilistic latent semantic analysis (PLSA) to accomplish the tasks of automatic image annotation. In order to model training data precisely, we represent an image as a bag of visual words and employ two PLSA models to capture semantic information from visual and textual modalities respectively. Furthermore, an adaptive learning approach is proposed to combine the aspects learned from both modalities. For each image document, distribution over aspects is fused by different weight in terms of the entropy of its feature distribution. Consequently, the two models are linked with the same distribution over aspects. This structure can predict semantic annotation for an unseen image because it associates visual and textual modalities properly. We compare our approach with several previous approaches on a standard Corel dataset. The experiment results show that our approach performs more effectively and accurately.

关键词： Image retrieval Hidden Markov models Laboratories Information processing Computers Image analysis Information analysis Training data Entropy Content based retrieval

来源：评论

学校读者我要写书评

暂无评论

Automatic sports genre categorization and view-type classification over large-scale dataset 09

Automatic sports genre categorization and view-type classifi...

引用

17th ACM International Conference on Multimedia, MM'09, with Co-located Workshops and Symposiums

作者： Li, Lingfang Zhang, Ning Duan, Ling-Yu Huang, Qingming Du, Jun Guan, Ling Key Lab. of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100080 China Ryerson Multimedia Research Laboratory Ryerson University Toronto ON Canada Institute of Digital Media Peking University Beijing 100871 China Graduate University of Chinese Academy of Sciences Beijing 100190 China NEC Research Labs. China Beijing 100084 China

ISBN: (纸本)9781605586083

This paper presents a framework with two automatic tasks targeting large-scale and low quality sports video archives collected from online video streams. The framework is based on the bag of visual-words model using speeded-up robust features (SURF). The first task is sports genre categorization based on hierarchical structure. Following on the second task which is based on automatically obtained genre, views are classified using support vector machines (SVMs). As a consequence, the views classification result can be used in video parsing and highlight extraction. As compared with state-of-the-art methods, our approach is fully automatic as well as domain knowledge free and thus provides a better extensibility. Furthermore, our dataset consists of 14 sport genres with 6850 minutes in total. Both sport genre categorization and view type classification have more than 80% accuracy rates, which validate this framework's robustness and potential in web-based applications. Copyright 2009 ACM.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Image Reconstruction by Sparse Coding and Selective Attention

Image Reconstruction by Sparse Coding and Selective Attentio...

引用

Congress on Image and signal processing, CISP

作者： Zhiqing Li Zhiping Shi Zhixin Li Zhongzhi Shi College of Information Engineering Xiangtan University Xiangtan China Chinese Academy and Sciences Beijing China The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy and Sciences Beijing China

Sparse coding theory demonstrates that the neurons in primary visual cortex form a sparse representation of natural scenes in the viewpoint of statistics. In this paper, inspired by the research of selective attention in psychology, we propose a novel self-adaptive algorithm to further reduce the activated variables. The experimental results show that the quality of reconstructed images obtained by our method is satisfying. Moreover, combining selective attention and sparse coding our method evidently decreases the number of coefficients which may be activated and preserves the main information at the same time.

关键词： Image reconstruction Image coding Neurons Information processing Layout Vectors Laboratories Computers Codes Statistics

来源：评论

学校读者我要写书评

暂无评论

A Point Pattern Matching Algorithm Based on Minimize Spanning Tree and Fiedler Vector

A Point Pattern Matching Algorithm Based on Minimize Spannin...

引用

International Conference on Information Science and Engineering (ICISE)

作者： Shan-li Xuan Dong Liang Ming Zhu Yi zheng Fan Nian Wang School of Computer & Information HeFei University of Technology Hefei China Key Laboratory Intelligent Computing & Signal Ministry of Education Anhui University Hefei China School of Mathematical Sciences Anhui University Hefei China

ISBN: (纸本)9781424449095

Based on the minimize spanning tree and Fiedler vector, a new feature matching algorithm is proposed in this paper. Firstly, a weighted complete graph is constructed with the feature points of each image respectively, then search the minimal spanning tree in each complete graph. Secondly, perform spectral decomposition on the Gaussian-weighted Laplace matrix of the minimize spanning tree respectively, and divide the feature points into several different sets based on the vector (Fiedler vector) corresponding to the second smallest eigenvalue of Laplace matrix, then the corresponding relation between sets is obtained. And construct Gaussian-weighted Laplace matrices between the corresponding sets, then submit the matrices to spectral decomposition. Finally, complete the feature matching by constructing matching matrix with eigenvalues and eigenvectors. Experiment results indicate that the algorithm has a high accuracy.

关键词： Pattern matching Matrix decomposition Tree graphs Eigenvalues and eigenfunctions Gaussian processes Laplace equations Information science Computer science education Educational technology Computer vision

来源：评论

学校读者我要写书评

暂无评论

Maximizing intra-individual correlations for face recognition across pose differences

Maximizing intra-individual correlations for face recognitio...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Annan Li Shiguang Shan Xilin Chen Wen Gao Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing of CAS Institute of Computing Technology Chinese Academy and Sciences Beijing China Institute of Digital Media Peking University Beijing China

The variations of pose lead to significant performance decline in face recognition systems, which is a bottleneck in face recognition. A key problem is how to measure the similarity between two image vectors of unequal length that viewed from different pose. In this paper, we propose a novel approach for pose robust face recognition, in which the similarity is measured by correlations in a media subspace between different poses on patch level. The media subspace is constructed by canonical correlation analysis, such that the intra-individual correlations are maximized. Based on the media subspace two recognition approaches are developed. In the first, we transform non-frontal face into frontal for recognition. And in the second, we perform recognition in the media subspace with probabilistic modeling. The experimental results on FERET database demonstrate the efficiency of our approach.

关键词： Face recognition Shape Content addressable storage Robustness Ellipsoids Geometry Information processing Computers Length measurement Databases

来源：评论

学校读者我要写书评

暂无评论

An Approach for Diagnosing Unexpected Faults in Web Service Flows

An Approach for Diagnosing Unexpected Faults in Web Service ...

引用

International Conference on Grid and Cooperative computing (GCC)

作者： Xu Han Zhongzhi Shi Wenjia Niu Fen Lin Donglei Zhang Key Lab. of Intell. Inf. Process. Chinese Acad. of Sci. Beijing Beijing China The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy and Sciences Beijing China

Potential faults have greatly reduced the dependability of business processes, so fault diagnosis is becoming an important issue which aims at supporting self-healing service flow execution. The existing fault handling mechanism provided by BPEL can only identify the faults which have been pre-defined in standards or by users. However, unexpected faults are also the main cause of failures in service flow execution. Therefore an effective diagnosis approach is needed to solve this problem. In this paper, we propose a logic-based approach for diagnosing unexpected faults in Web service flows. This approach uses dynamic description logic (DDL) to model business processes, and diagnoses faults based on DDL reasoning. We provide the DDL-based diagnosing algorithm, which takes process description and runtime information as inputs, and returns the related information of possible faults as the result. Moreover, to improve the efficiency of online diagnosis, the incremental DDL-based diagnosing algorithm is presented. Experimental results on a demo system show the effectiveness of this approach.

关键词： Web services Fault diagnosis Logic Grid computing Laboratories Information processing Computers Testing Runtime Engines

来源：评论

学校读者我要写书评

暂无评论

A novel Hebbian rules based method for computation of sparse coding basis vectors

A novel Hebbian rules based method for computation of sparse...

引用

5th International Conference on Natural Computation, ICNC 2009

作者： Zou, Baixian Miao, Jun Yang, Xiaoling Duan, Lijuan Qiao, Yuanhua Department of Information Science and Technology College of Arts and Science of Beijing Union University Beijing 100083 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China Tianjin Academy of Agricultural Science Tianjin 300192 China College of Computer Science and Technology Beijing University of Technology Beijing 100022 China College of Applied Science Beijing University of Technology Beijing 100022 China

ISBN: (纸本)9780769537368

Sparse coding has high-performance encoding and ability to express images, sparse encoding basis vector plays a crucial role. The computational complexity of the most existing sparse coding basis vectors of is relatively large. In order to reduce the computational complexity and save the time to train basis vectors. A new Hebbian rules based method for computation of sparse coding basis vectors is proposed in this paper. A two-layer neural network is constructed to implement the task. The main idea of our work is to learn basis vectors by removing the redundancy of all initial vectors using Hebbian rules. The experiments on natural images prove that the proposed method is effective for sparse coding basis learning. It has the smaller computational complexity compared with the previous work. © 2009 IEEE.

关键词： Computational complexity

来源：评论

学校读者我要写书评

暂无评论

Tolerance Granular computing based on incomplete information system

Tolerance Granular Computing based on incomplete information...

引用

IEEE International Conference on Granular computing (GRC)

作者： Zhongzhi Shi Zuqiang Meng Yuan Lu The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China College of Computer Electronics and Information Guangxi University Nanning 530004 China College of Computer Guangxi University Nanning China

At present GrC mainly is divided into three categories: computing with words (CW), rough set (RS) and quotient space (QS). From the perspective of essential characteristic of GrC, this demarcation is not comprehensive and accurate. In fact, CW is based on fuzzy granules (fuzzy subset) and both RS and QS are based on disjoint granules, which essentially are equivalence classes, either equal to each other or with empty overlap. In practical application, intersecting granules however need to be handled. Therefore there is another kind of GrC which is based on intersecting granules. This kind of GrC is referred to as tolerance GrC (TGrC) in our work. By constructing a Boolean algebra on super-granular space and a decision algebraic system, this paper will present an incomplete information system-based TGrC. With the TGrC, an example about extracting rules incomplete information is given, so as to show its basic principle.

关键词： Information systems Information processing Data mining Artificial intelligence Humans Problem-solving Arithmetic Laboratories Computers Educational institutions

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

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共374页 << < 330 331 332 333 334 335 336 337 338 339 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：