检索结果-内蒙古大学图书馆

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

Facilitating dynamic web service composition with fine-granularity context management

Facilitating dynamic web service composition with fine-granu...

引用

IEEE International Conference on Granular computing (GRC)

作者： Wenjia Niu Gang Li Xinghua Yang Xu Han Zhongzhi Shi Chinese Academy of Sciences Beijing Beijing CN School of Information Technology Deakin University VIC Australia Chinese Academy and Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy and Sciences Beijing China

Context is an important factor for the success of dynamic service composition. Although many context-based AI or workflow approaches have been proposed to support dynamic service composition, there is still an unaddressed issue of the support of fine-granularity context management. In this paper, we propose a granularity-based context model together with an approach to supporting the intelligent context-aware service composing problem. The corresponding case study is provided to show the validity of our approach.

关键词： Web services Context-aware services Artificial intelligence Simple object access protocol Concrete Road transportation technology management Laboratories information processing Computers

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

Sigma Set: A small second order statistical region descriptor

Sigma Set: A small second order statistical region descripto...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Xiaopeng Hong Hong Chang Shiguang Shan Xilin Chen Wen Gao School of Computer Science and Technology Harbin Institute of Technology China Institute of Computing Technology Chinese Academy and Sciences China Key Laboratory of Intelligent Information Processing Chinese Academy and Sciences China Institute of Computing Technology Chinese Academy of Sciences China Institute for Digital Media Peking University China

Given an image region of pixels, second order statistics can be used to construct a descriptor for object representation. One example is the covariance matrix descriptor, which shows high discriminative power and good robustness in many computer vision applications. However, operations for the covariance matrix on Riemannian manifolds are usually computationally demanding. This paper proposes a novel second order statistics based region descriptor, named “Sigma Set”, in the form of a small set of vectors, which can be uniquely constructed through Cholesky decomposition on the covariance matrix. Sigma Set is of low dimension, powerful and robust. Moreover, compared with the covariance matrix, Sigma Set is not only more efficient in distance evaluation and average calculation, but also easier to be enriched with first order statistics. Experimental results in texture classification and object tracking verify the effectiveness and efficiency of this novel object descriptor.

关键词： Robustness Histograms Fractals Lighting Statistics Solids Computer science Power engineering and energy Mathematics Power engineering computing

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

Single vs. population cell coding: Gaze movement control in target search

Single vs. population cell coding: Gaze movement control in ...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Jun Miao Laiyun Qing Lijuan Duan Baixian Zou Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy and Sciences Beijing China School of Information Science and Engineering Chinese Academy of Sciences Beijing China College of Computer Science and Technology University of Technology Beijing China Department of Information Science and Technology College of Art and Science Beijing Union Technology Beijing China

Gaze movement plays an important role in human visual search system. In literature, the winner-take-all method is wildly used to simulate the controlling of the gaze movement. The winner-take-all is a type of single-cell coding method, which uses one cell (grandmother cell) or one response to represent an object. However, eye movement is affected by the visual context which includes more than one object in images, especially in target search. Therefore, we propose to use the population coding with more than one response rather than the single-cell coding on gaze movement control. The proposed method is supported by the theoretical analysis and experiments on a real image database which show the population-cell-coding improves the target locating accuracy by 44.4% only at the cost of coding 22.4% more information than that of single-cell-coding.

关键词： Humans Image coding Image databases Costs information science Educational institutions Biological neural networks Control systems Image analysis information analysis

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

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

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

Boid particle swarm optimisation

引用

International Journal of Innovative computing and Applications 2009年第2期2卷 78-85页

作者： Cui, Zhihua Shi, Zhongzhi Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences No. 6 Kexueyuan South Rd. Zhongguancun Haidian District Beijing 100190 China Complex System and Computational Intelligence Laboratory Taiyuan University of Science and Technology No. 66 Waliu Rd. Wanbailin District Taiyuan Shanxi 030024 China

Particle swarm optimisation (PSO) is a novel population-based stochastic optimisation algorithm inspired by the Reynolds' boid model. The original biological background of boid obeys three basic simple steering rules: separation, alignment and cohesion. However, to promote a simple update equation, none of these rules of boid model is employed by PSO methodology. Due to the weakness of biological background of PSO, in this paper, a new variant of PSO, boid particle swarm optimisation (BPSO), is designed in which cohesion rule and alignment rule are both employed to improve the performance. In BPSO, each particle has two motions: divergent motion and convergent motion. For divergent motion, each particle adjusts its moving direction according to the alignment direction and the cohesion direction, as well as in convergent motion, the original update equation of the standard version of PSO is used. To make a motion transition, a threshold is introduced to make the divergent motion is employed in the first period, whereas the convergent motion is used in the final stage. To testify the efficiency, several unconstrained benchmarks are used to compare. Simulation results show the proposed variant is more effective and efficient than other two variants of PSO when solving multi-modal high-dimensional numerical problems. Copyright © 2009 Inderscience Enterprises Ltd.

关键词： Alignment

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：