检索结果-内蒙古大学图书馆

New approach to heterogeneous semantic search on the web

Jisuanji Yanjiu yu Fazhan/Computer Research and Development 2008年第8期45卷 1338-1345页

作者： Huang, Rui Shi, Zhongzhi Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China Graduate University Chinese Academy of Sciences Beijing 100049 China

Relevance ranking is a key to Web search in determining how results are retrieved and ordered. As keyword-based search does not guarantee relevance in meanings, semantic search has been put forward as an attractive and promising approach. Recently several kinds of semantic information have been adopted in search respectively, such as thesauruses, ontologies and semantic markups, as well as folksonomies and social annotations. However, although to integrate more semantics would logically generate better search results, search mechanism to fully adopt different kinds of semantic information is still in absence and to be researched. To these ends, an integrated semantic search mechanism is proposed to incorporate textual information and keyword search with heterogeneous semantic information and semantic search. A statistical based measurement of semantic relevance, defined as semantic probabilities, is introduced to integrate both keywords and four kinds of semantic information including thesauruses, categories, ontologies and folksonomies. It is calculated with all textual information and semantic information, and stored in a newly proposed index structure called semantic-keyword dual index. Based on this uniform measurement, the search mechanism is developed that fully utilizes existing keyword and semantic search mechanisms to enhance heterogeneous semantic search. Experiments show that the proposed approach can effectively integrate both keyword-based information and heterogeneous semantic information in search.

关键词： Semantic Web

来源：评论

学校读者我要写书评

暂无评论

Survey of semantic mapping in image retrieval

引用

Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics 2008年第8期20卷 1085-1096页

作者： Li, Zhixin Shi, Zhiping Li, Zhiqing Shi, Zhongzhi Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China Graduate University Chinese Academy of Sciences Beijing 100049 China

Semantic gap has become a bottleneck of content-based image retrieval. In order to bridge the gap and improve retrieval accuracy, a map from lower-level visual features to high-level semantics should be formulated. This paper provides a comprehensive survey on semantic mapping. Firstly, an image retrieval framework integrated with high-level semantics is presented. Secondly, image semantic description is introduced in two aspects: image content level-models and semantic representations. Thirdly, as the emphasis of this paper, semantic mapping approaches and techniques are investigated by classifying them into four main categories in terms of their characteristics. Various ideas and models proposed in these approaches are analyzed. In addition, advantages and limitations of each category are discussed. Finally, based on the state-of-the-art technology and the demand from real-world applications, several important issues related to semantic image retrieval are identified and some promising research directions are suggested.

关键词： Image annotation

来源：评论

学校读者我要写书评

暂无评论

RESEARCH OF PATTERN FEATURE EXTRACTION AND SELECTION

RESEARCH OF PATTERN FEATURE EXTRACTION AND SELECTION

引用

2008 International Conference on Machine Learning and Cybernetics(2008机器学习与控制论国际会议)

作者： SHI-FEI DING WEI-KUAN JIA CHUN-YANG SU ZHONG-ZHI SHI School of Computer Science and Technology China University of Mining and Technology Xuzhou 221008 College of Plant Protection Shandong Agricultural University Taian 271018 China School of Computer Science and Technology China University of Mining and Technology Xuzhou 221008 Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Aca

As an important link of pattern recognition, pattern feature extraction and selection has been paid close attention by lots of scholars, and currently become one of the research hot spot in the field of pattern recognition. Its main purpose is "Low Loss Dimensionality Reduction";it is generally divided into two parts, that is, linear pattern feature extraction and selection and nonlinear pattern feature extraction and selection. This article gives a general discussion of pattern feature extraction and selection, and introduces the frontier methods of this field, at last discusses the development tendency of pattern feature extraction and selection.

关键词： Pattern Feature Eztraction information Theory Neural Network Independent Component Analysis Manifold Learning Optimization Algorithm

来源：评论

学校读者我要写书评

暂无评论

Point based large-scale crowds real-time 3D visualization method

引用

Jisuanji Yanjiu yu Fazhan/Computer Research and Development 2008年第10期45卷 1731-1738页

作者： Shu, Bo Mao, Tianlu Xu, Wenbin Wang, Zhaoqi Virtual Reality Laboratory Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China Graduate University Chinese Academy of Sciences Beijing 100049 China

3D visualization of large-scale virtual crowds is a very important and interesting problem in research fields of virtual reality. For reasons of efficiency and visual realism, it is very difficult to populate, animate and render large-scale virtual crowds with hundreds of thousand individually animated virtual characters in real-time applications;especially for the scene which has more than ten thousands of individuals with different shapes and motions. In this paper, an efficient method to visualize large-scale virtual crowds is presented. Firstly, using model variation technique, many different models can be derived from a small number of model templates. Secondly, the crowds can be animated individually by deforming a small number of elements in motion database. Thirdly, using a developed point sample rendering algorithm, large-scale crowds can be displayed in real-time. This method can be used to visualize different dynamic crowds which require both real-time efficiency and large number of virtual individuals support. Based on this work, an efficient and readily usable 3D visualization system is presented. It can provide very high visual realism for large crowds' visualization in interactive frame rates on a regular PC. The 3D visualization of 60000 people evacuating from a building is also realized in real-time based on the system.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Method of adaptively selecting best LDA model based on density

引用

Jisuanji Xuebao/Chinese Journal of Computers 2008年第10期31卷 1780-1787页

作者： Cao, Juan Zhang, Yong-Dong Li, Jin-Tao Tang, Sheng Virtual Reality Laboratory Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China Graduate University Chinese Academy of Sciences Beijing 100049 China

Topic models have been successfully used to information classification and retrieval. These models can capture word correlations in a collection of textual documents with a low-dimensional set of multinomial distribution, called "topics". It is important but difficult to select an appropriate number of topics for a specific dataset. This paper proposes a theorem that the model reaches optimum as the average similarity among topics reaches minimum, and based on this theorem, proposes a method of adaptively selecting the best LDA model based on density. Experiments show that the proposed method can achieve performance matching the best of LDA without manually tuning the number of topics.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Well limit behaviors of term rewriting systems

引用

中国高等学校学术文摘·计算机科学 2007年第3期1卷 283-296页

作者： MA Shilong SUI Yuefei XU Ke State Key Laboratory of Software Development Environment Beihang UniversityBeijing 100083China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of SciencesBeijing 100080China

The limit behaviors of computations have not been fully *** is necessary to consider such limit behaviors when we consider the properties of infinite objects in computer science,such as infinite logic programs,the symbolic solutions of infinite polynomial ***,we can use finite objects to approximate infinite objects,and we should know what kinds of infinite objects are approximable and how to approximate them effectively.A sequence {Rκ:κω}of term rewriting systems has the well limit behavior if under the condition that the sequence has the Set-theoretic limit or the distance-based limit,the sequence {Th(Rκ):κ∈ω} of corresponding theoretic closures of Rκ has the set-theoretic or distance-based limit,and limκ→∞ Th(Rκ) is equal to the theoretic closure of the limit of {Rκ:κ∈ω).Two kinds of limits of term rewriting systems are considered:one is based on the set-theoretic limit,the other is on the distance-based *** is proved thatgiven a sequence {Rκ:κ∈ω) of term rewriting systems Rκ,if there is a well-founded ordering (-＜) on terms such that every Rκ is (-＜)-well-founded,and the set-theoretic limit of {Rκ:κ∈ω).exists,then {Rκ:κ∈ω).has the well limit behavior;and if (1) there is a well-founded ordering(-＜)on terms such that every Rκ is(-＜-well-founded,(2) there is a distance d on terms which is closed under substitutions and contexts and (3) {Rκ:κ∈ω).is Cauchy under d then {Rκ:κ∈ω).has the well limit *** results are used to approximate the least Herbrand models of infinite Horn logic programs and real Horn logic programs,and the solutions and Cr(o)bner bases of (infinite) sets of real polynomials by sequences of (finite) sets of rational polynomials.

关键词： term rewriting systems limits Gr(o)bner bases well-foundedness

来源：评论

学校读者我要写书评

暂无评论

Fast global motion estimation using threshold method

Fast global motion estimation using threshold method

引用

MIPPR 2007: Medical Imaging, Parallel processing of Images, and Optimization Techniques

作者： Zheng, Jiali Zhang, YongDong Ni, GuangNan Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100080 China

ISBN: (纸本)9780819469533

In this paper, a fast global motion estimation method is proposed for video coding. This method can accommodate not only a translational motion model but also a polynomial motion model. It speeds up the procedure of the global motion estimation (GME) by pre-analyzing the characteristics of the block. At the first stage, the smooth region blocks which contribute less to the GME are filtered by using a threshold method based on image intensity. Next, a threshold method based on the discrepancy of the motion vectors is used to exclude the foreground blocks from the GME. From the experimental results, we can conclude that the proposed fast global motion estimation method manages to speed up the processing of estimating the motion vector field while maintaining the coding performance.

关键词： Motion estimation

来源：评论

学校读者我要写书评

暂无评论

A dependency treelet string correspondence model for statistical machine translation 2

A dependency treelet string correspondence model for statist...

引用

2nd Workshop on Statistical Machine Translation, WMT 2007 at the 45th Annual Meeting of the Association of Computational Linguistics, ACL 2007

作者： Xiong, Deyi Liu, Qun Lin, Shouxun Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100080 China

This paper describes a novel model using dependency structures on the source side for syntax-based statistical machine translation: Dependency Treelet String Correspondence Model (DTSC). The DTSC model maps source dependency structures to target strings. In this model translation pairs of source treelets and target strings with their word alignments are learned automatically from the parsed and aligned corpus. The DTSC model allows source treelets and target strings with variables so that the model can generalize to handle dependency structures with the same head word but with different modifiers and arguments. Additionally, target strings can be also discontinuous by using gaps which are corresponding to the uncovered nodes which are not included in the source treelets. A chart-style decoding algorithm with two basic operations-substituting and attaching-is designed for the DTSC model. We argue that the DTSC model proposed here is capable of lexicalization, generalization, and handling discontinuous phrases which are very desirable for machine translation. We finally evaluate our current implementation of a simplified version of DTSC for statistical machine translation. © 2007 Association for Computational Linguistics

关键词： Machine translation

来源：评论

学校读者我要写书评

暂无评论

Granular computing in the information transformation of patten recognition

Granular computing in the information transformation of patt...

引用

2007 IEEE International Conference on Granular computing, GrC 2007

作者： Hu, Hong Shi, Zhongzhi Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Science Beijing 100080 China

ISBN: (纸本)076953032X

In the past decade, many papers about granular computing(GrC) have been published, but the keypoints about granular computing(GrC) are still unclear. In this paper, we try to find the key points of GrC in the information transformation of the pattern recognition. The information similarity is the main point in the original insight of Granular computing (GrC) proposed by Zadeh(1997[1]). Many GrC researches are based on equivalence relation or more generally tolerance relation, equivalence relation or tolerance relation can be described by some distance functions and GrC can be geometrically defined in a framework of multiscale covering, at other hand, the information transformation in the pattern recognition can be abstracted as a topological transformation in a feature information space, so topological theory can be used to study GrC The key points of GrC are (1) there are two granular computing approaches to change a high dimensional complex distribution domain to a low dimensional and simple domain, (2)these two kind approaches can be used in turn if feature vector itself can be arranged in a granular way. © 2007 IEEE.

关键词： Granular computing

来源：评论

学校读者我要写书评

暂无评论

A Bayesian computational cognitive model

A Bayesian computational cognitive model

引用

3rd International Workshop on Neural-Symbolic Learning and Reasoning, NeSy 2007, Held at IJCAI 2007

作者： Shi, Zhiwei Hu, Hong Shi, Zhongzhi Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS China Kexueyuan Nanlu #6 Beijing 100080 China

Computational cognitive modeling has recently emerged as one of the hottest issues in the AI area. Both symbolic approaches and connectionist approaches present their merits and demerits. Although Bayesian method is suggested to incorporate advantages of the two kinds of approaches above, there is no feasible Bayesian computational model concerning the entire cognitive process by now. In this paper, we propose a variation of traditional Bayesian network, namely Globally Connected and Locally Autonomic Bayesian Network (GCLABN), to formally describe a plausible cognitive model. The model adopts a unique knowledge representation strategy, which enables it to encode both symbolic concepts and their relationships within a graphical structure, and to generate cognition via a dynamic oscillating process rather than a straightforward reasoning process like traditional approaches. Then a simple simulation is employed to illustrate the properties and dynamic behaviors of the model. All these traits of the model are coincident with the recently discovered properties of the human cognitive process.

关键词： Bayesian networks

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：