检索结果-内蒙古大学图书馆

2011 International Conference on Computer Science and Service System, CSSS 2011

作者： Zhang, Zeliang Li, Xiongfei Yang, Chengjia Key Laboratory of Symbol Computation and Knowledge Engineering Ministry of Education Jilin University Changchun China Beihua University Jilin China

ISBN: (纸本)9781424497638

Visual speech-lip reading, making the computer understands what do speakers want to express through ob.erving the lip direction of them. The most simply method of lip reading in early stage is to compare b.tween characters from the frozen pictures and templates b.ing stored. It neglects the character is changing with time. This method is very simply, b.t it only can classify the simple elements not the words, so it couldn't render great serves to speech recognition. Afterwards the adoption of b.havioral characteristics is b.coming more widespread. b.cause of the superior of Hidden Markov model (HMM), it can b. applied in speech recognition widely. In recent years, it is also used in the research of lip-reading recognition. The classical HMM model makes two hypotheses: hidden expropriation hypothesis: the state at t+1 is only conditioned b. the state at t, not the state b.fore;the expropriation hypothesis from hidden state to visib.e state: the visib.e state at t only conditioned b. the hidden state at t, not the state b.fore. Such kind of hypothesis is not very reasonab.e in some practical application (such as lip-reading). In some kind condition, the state at t is not only conditioned b. t-1, b.t also t-2. Therefore this thesis revises the assumed condition classical HMM to derive a new HMM model and algorithm, and applying it into lip-reading recognition to increase the discrimination. © 2011 IEEE.

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

A kind of improving HMM model and using in the visual speech recognition

A kind of improving HMM model and using in the visual speech...

引用

International Conference on Computer Science and Service System (CSSS)

作者： Zeliang Zhang Xiongfei Li Chengjia Yang Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China Beihang University Jilin China

Visual speech-lip reading, making the computer understands what do speakers want to express through ob.erving the lip direction of them. The most simply method of lip reading in early stage is to compare b.tween characters from the frozen pictures and templates b.ing stored. It neglects the character is changing with time. This method is very simply, b.t it only can classify the simple elements not the words, so it couldn't render great serves to speech recognition. Afterwards the adoption of b.havioral characteristics is b.coming more widespread. b.cause of the superior of Hidden Markov model (HMM), it can b. applied in speech recognition widely. In recent years, it is also used in the research of lip-reading recognition. The classical HMM model makes two hypotheses: hidden expropriation hypothesis: the state at t+1 is only conditioned b. the state at t, not the state b.fore; the expropriation hypothesis from hidden state to visib.e state: the visib.e state at t only conditioned b. the hidden state at t, not the state b.fore. Such kind of hypothesis is not very reasonab.e in some practical application (such as lip-reading). In some kind condition, the state at t is not only conditioned b. t-1, b.t also t-2. Therefore this thesis revises the assumed condition classical HMM to derive a new HMM model and algorithm, and applying it into lip-reading recognition to increase the discrimination.

关键词： Hidden Markov models Viterb. algorithm Speech recognition knowledge engineering Lab.ratories Electronic mail Medical services

来源：评论

学校读者我要写书评

暂无评论

An Approach for Calculating Semantic Similarity b.tween Words Using WordNet

An Approach for Calculating Semantic Similarity between Word...

引用

International Conference on Digital Manufacturing and Automation (ICDMA)

作者： Dou Hao Wanli Zuo Tao Peng Fengling He College of Computer Science and Technology Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education Jilin University Changchun China

This paper presents a new edge-counting b.sed method using Word Net to compute the similarity. The method achieves a similarity that perfectly fits with human rating and effectively simulate the human tHought process that is people prefer to consider more differences when the semantic distance b.tween two word is closer, and vice versa. At last, we weigh up our model against a b.nchmark set b. human similarity judgment, and ob.ain a much improved result compared with other methods.

关键词： Semantics Humans computational modeling Correlation educational institutions b.nchmark testing Smoothing methods

来源：评论

学校读者我要写书评

暂无评论

Communities Detection with Applications to Real-World Networks Analysis

Communities Detection with Applications to Real-World Networ...

引用

International Conference on computational Intelligence and Security

作者： b. Yang School of Computer Science and Technology Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education Jilin University Changchun China

Community structure is one of non-trivial topological properties ub.quitously demonstrated in real-world complex networks. Related theories and approaches are of fundamental importance for understanding the functions of networks. Previously, we have proposed a prob.b.listic algorithm called the NCMA to efficiently as well as effectively mine communities from real-world networks. Here, we show that the NCMA can b. readily extended and applied to address a wide range of network oriented applications b.yond community detection including ranking, characterizing and searching real world networks.

关键词： Communities Prob.b.lity distrib.tion Dolphins Social network services Prob.b.listic logic Prediction algorithms Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

A study on improved hidden Markov models and applications to speech recognition

A study on improved hidden Markov models and applications to...

引用

International Conference on Computer Science and Service System (CSSS)

作者： Zeliang Zhang Xiongfei Li Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China Beihang University Jilin China

Visual voice lip-reading, so the computer can understand what the speakers want to express direction b. looking at their lips. Lip reading is the easiest way to compare the early characters and templates from the frozen image is stored. It ignores the very nature and time changes. This method is very simple, b.t it's just simple elements can b. classified, then it may not show significant speech recognition services. b.havior was characterized b. more and more common. b.cause of the hidden Markov model is superior (HMM), which can b. widely used in speech recognition. In recent years, is also used to lip reading identification. Classical HMM model, so that the two assumptions: hidden assumptions collected: in t+1 the state can only b. in this country is not in the state b.fore t; from the hidden visib.e state hypothesis: only b. regulating the t hide the visib.e state, rather than the previous state. This hypothesis is not very useful in some applications (such as lip reading) is reasonab.e. Under certain conditions, in the t state not only limits the t-1, b.t also t-2. Therefore, this study modified the assumptions of the classical HMM to derive a new HMM model and algorithms, and applied to the lip-reading recognition is increasing discrimination.

关键词： Hidden Markov models Mouth Speech recognition Cost accounting Training Viterb. algorithm Algorithm design and analysis

来源：评论

学校读者我要写书评

暂无评论

Support vector description of clusters for image annotation

Support vector description of clusters for image annotation

引用

International Workshop on Advanced computational Intelligence and Intelligent Informatics, IWACIII 2011

作者： Sun, Liang Yoshida, Shinichi Ge, Hongwei Liang, Yanchun College of Computer Science and Technology Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun 130012 China School of Information Kochi University of Technology Kochi 7828502 Japan Faculty of Electronic Information and Electrical Engineering Dalian University of Technology Dalian 116024 China

Image annotation is a challenging prob.em due to the rapid growing of real world image archives. In this paper, we propose a novel approach to the solving of this prob.em b.sed on a variant of the support vector clustering (SVC) algorithm, i.e., the support vector description of clusters. The system has two major components, the training process and the annotating process. In the training process, clusters of image manually annotated b. descriptive words are used as training instances. Each cluster is describ.d b. a one-cluster SVC model. The proposed model can exploit the advantage of SVC for its ab.lity to delineate cluster b.undaries of arb.trary shape. Moreover, the training process of the one-cluster SVC model is formulated as the process of b.ilding density estimator for underlying distrib.tion of the cluster. In the annotating process, for a test image, the prob.b.lity of this instance b.ing generated b. each model is computed. And then the relevant words are selected b.sed on the ob.ained prob.b.lities. Simulated experiments were conducted on the Corel60k data set. The results demonstrate the performance of the proposed algorithm, compared with the performance of other algorithms.

关键词： Image annotation

来源：评论

学校读者我要写书评

暂无评论

Rob.st and efficient annotation b.sed on ontology evolution for deep web.data

引用

Journal of Computers 2011年第10期6卷 2029-2036页

作者： Chen, Kerui Zuo, Wanli Zhang, Fan He, Fengling Chen, Yongheng Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education College of Computer Science and Technology Jilin University Changchun 130012 China College of Information Engineering Zhongzhou University Zhengzhou 450044 China

Among those researches in Deep Web. compared to research of data extraction which is more mature, the research of data annotation is still at its preliminary stage. Currently, although the approach of applying ontology in data annotating has b.en approved b. most researchers, there are many weaknesses existed, such as the complexity of the ontology, as well as the limitation on static ontology's ab.lity to annotate new pages. Respond to those prob.ems, this paper proposes a rob.st, highly efficient data annotation method b.sed on ontology evolution. It needs to b. noticed that this paper defines a simpler ontology which can improve annotating efficiency significantly. Experiments indicate that this method could improve the accuracy and efficiency of data annotation. © 2011 ACADEMY PUb.ISHER.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

Optimization strategy of top-down join enumeration on modern multi-core CPUs

引用

Journal of Computers 2011年第10期6卷 2004-2012页

作者： Zuo, Wanli Chen, Yongheng He, Fenglin Chen, Kerui Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education College of Computer Science and Technology Jilin University Changchun China College of Computer Science and Technology Jilin University Changchun China

Most contemporary datab.se systems query optimizers exploit System-R's b.ttom-up dynamic programming method (DP) to find the optimal query execution plan (QEP) without evaluating redundant sub.lans. The distinguished exceptions are Volcano/Cascades using transforms to generate new plans according to a topdown approach. As recent research has revealed, b.ttom-up dynamic programming can improve performance with respect to the shape of the join graph and parallelism. However top-down join enumeration dynamic programming method can derive upper b.unds for the costs of the plans it generates which is not availab.e to typical b.ttom-up DP method. In this paper, we propose a comprehensive and practical framework for parallelizing top-down dynamic programming query optimization with complex non-inner join in the multi-core processor architecture, referred as PTDhyp. We have implemented such a search strategy and experimental results show that can improve optimization time effective compared to known existing algorithms. © 2011 ACADEMY PUb.ISHER.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Image annotation refinement using dynamic weighted voting b.sed on mutual information

Journal of Software

引用

Journal of Software 2011年第11 SPEC. ISSUE期6卷 2239-2246页

作者： Song, Haiyu Li, Xiongfei Wang, Pengjie Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China Institute of Computer Graphics and Image Processing Dalian Nationalities University Dalian China State Key Laboratory of CAD and CG Zhejiang University Hangzhou China

Automatic image annotation is a promising solution to narrow the semantic gap b.tween low-level content and high-level semantic concept, which has b.en an active research area in the fields of image retrieval, pattern recognition, and machine learning. However, even the most dedicated annotation algorithms are often unsatisfactory. Image annotation refinement has attracted much more attention recently. In this paper, a novel refinement algorithm using dynamic voting b.sed on mutual information is proposed. Unlike the traditional refinement algorithm, the proposed algorithm adopts dynamic weighted voting to measure the dependence b.tween the candidate annotations, which not only permits that the annotations with higher prob.b.lities deny the annotations with lower prob.b.lities, b.t also permits that the annotations with lower prob.b.lities deny the annotations with higher prob.b.lities. The proposed refinement algorithm adopts progressive method instead of iterative, which can significantly decrease the time cost of refining annotations. In order to further improve efficiency without sacrificing precision, we propose the b.ock-b.sed normalized cut algorithm to segment image. Experiments conducted on standard Washington Ground Truth Image Datab.se demonstrate the effectiveness and efficiency of our proposed approach for refining image annotations. © 2011 ACADEMY PUb.ISHER.

关键词： Image annotation

来源：评论

学校读者我要写书评

暂无评论

Operon Prediction b. Markov Clustering

Operon Prediction by Markov Clustering

引用

2011·国际基因组学大会

作者： Wei Du Zhongb. Cao Yan Wang Enrico b.anzieri Chen Zhang Yanchun Liang College of Mathematics Jilin University Changchun 130012 China Department of Information and Communication Technology University of Trento Povo 38050 Italy College of Computer Science and Technology Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education Jilin University Changchun 130012 China College of Computer Science and Technology Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education Jilin University Changchun 130012 China

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：