检索结果-内蒙古大学图书馆

6th ACM International Conference on Image and Video Retrieval, CIVR 2007

作者： Liu, Xiaobing Wang, Dong Li, Jianmin Zhang, Bo State Key Lab. of Intelligent Technology and System Department of Computer Science and Technology Tsinghua University Beijing 100084 China

ISBN: (纸本)1595937331

In this paper, we are motivated to augment the holistic histogram representation with implicit spatial constrains. To be more concrete, we aim atending a good match function for the problem of object/scene categorization which considers the spatial constraints against heavy clutter and occlusion. Our solution is a partial match kernel under the histogram representation which varies simultaneously at both the feature and spatial resolutions, named as the Feature and Spatial Covariant (FESCO) kernel. Both the FESCO kernel and its late fusion alternative achieve better match accuracy than Spatial Pyramid Match[13] and Pyramid Match[11]. We also apply the keypoint features to video indexing. And on a large scale TRECVID data sets of over 300 hours videos, to our best knowledge, this approach achieves the state-of-the-art result for a single feature. Copyright 2007 ACM.

关键词： Image matching

来源：评论

学校读者我要写书评

暂无评论

Adaptive multiple subtraction based on constrained independent component analysis 77

Adaptive multiple subtraction based on constrained independe...

引用

77th Society of Exploration Geophysicists International Exposition and Annual Meeting, SEG 2007

作者： Lu, Wen-Kai Liu, Lei Li, Yan-Dong Key State Lab. of Intelligent Technology and System Institute of Information Processing Department of Automation Tsinghua University China

ISBN: (纸本)9781604238976

Adaptive multiple subtraction is a critical and challenging procedure for the widely-used surface-related multiple attenuation (SRMA) techniques. The problem encountered in this field is that a good result is usually hard to obtain when primaries and multiples have overlap. In this paper, we propose a new adaptive multiple subtraction method based on constrained independent component analysis (CICA). In this method, the prediction error obtained by multidimensional prediction error filters (PEFs), which measure the lateral continuity of the primaries, is adopted as a constraint term in the objective function of CICA. The proposed method is demonstrated on two synthetic datasets. © 2007 Society of Exploration Geophysicists. All rights reserved.

关键词： Independent component analysis

来源：评论

学校读者我要写书评

暂无评论

Random noise suppression based on discrete cosine transform 77

Random noise suppression based on discrete cosine transform

引用

77th Society of Exploration Geophysicists International Exposition and Annual Meeting, SEG 2007

作者： Lu, Wen-Kai Liu, Jun Key State Lab. of Intelligent Technology and System Institute of Information Processing Department of Automation Tsinghua University China

ISBN: (纸本)9781604238976

This paper illustrates the advantages of using the Discrete Cosine Transform (DCT) as compared to the standard Discrete Fourier Transform (DFT) for the purpose of removing random noise embedded in seismic data. The prediction filter is adopted in the DCT domain. Comparisons of the results between our method and the prediction filter in f-x domain show that the new method achieved better performance. © 2007 Society of Exploration Geophysicists. All rights reserved.

关键词： Discrete cosine transforms

来源：评论

学校读者我要写书评

暂无评论

Video diver: Generic video indexing with diverse features

Video diver: Generic video indexing with diverse features

引用

International Multimedia Conference, MM'07 - 9th ACM SIG Multimedia International Workshop on Multimedia Information Retrieval, MIR'07

作者： Wang, Dong Liu, Xiaobing Luo, Linjie Li, Jianmin Zhang, Bo State Key Lab. of Intelligent Tech. and System Department of Computer Science and Technology Tsinghua University Beijing 100084 China

ISBN: (纸本)9781595937780

Semantic video indexing is critical for practical video retrieval systems and a generic and scalab.e indexing framework is a must for indexing a large semantic lexicon with over 1000 concepts present. This paper fully explores the idea of incorporating many kinds of diverse features into a single framework, combining them altogether to obtain larger degree of invariance which is absent in any of the component features, and thus achieves genericness and scalab.lity. We scale down the formidable computational expense with a clever design of the classification and fusion schemes. To be specific, ~20 kinds of diverse features are extracted to capture limited yet complementary variance in color, texture and edge with spatial constraints implicitly integrated, and over 100 classifiers are built subsequently and fused to produce a generic detector. The extensive experiments on a total of 310 hours of TRECVID news videos show that the proposed framework yields significantly improved performance over that of the best single feature across a variety of concepts. Moreover, a benchmark comparison demonstrates that this approach is state-of-the-art. Meanwhile, the proposed approach generalizes well over previously unseen programs and stations and scales well to a lexicon of over 300 concepts in the LSCOM [18] ontology. Copyright 2007 ACM.

关键词： Indexing (of information)

来源：评论

学校读者我要写书评

暂无评论

Video search in concept subspace: A text-like paradigm 07

Video search in concept subspace: A text-like paradigm

引用

6th ACM International Conference on Image and Video Retrieval, CIVR 2007

作者： Li, Xirong Wang, Dong Li, Jianmin Zhang, Bo State Key Lab. of Intelligent Tech. and System Department of Computer Science and Technology Tsinghua University Beijing 100084 China

ISBN: (纸本)1595937331

Though both quantity and quality of semantic concept detection in video are continuously improving, it still remains unclear how to exploit these detected concepts as semantic indices in video search, given a specific query. In this paper, we tackle this problem and propose a video search framework which operates like searching text documents. Noteworthy for its adoption of the well-founded text search principles, this framework first selects a few related concepts for a given query, by employing a tf-idf like scheme, called c-tf-idf, to measure the informativeness of the concepts to this query. These selected concepts form a concept subspace. Then search can be conducted in this concept subspace, either by a Vector Model or a Language Model. Further, two algorithms, i.e., Linear Summation and Random Walk through Concept-Link, are explored to combine the concept search results and other baseline search results in a reranking scheme. This framework is both effective and efficient. Using a lexicon of 311 concepts from the LSCOM concept ontology, experiments conducted on the TRECVID 2006 search data set show that: when used solely, search within the concept subspace achieves the state-of-the-art concept search result;when used to rerank the baseline results, it can improve over the top 20 automatic search runs in TRECVID 2006 on average by approx. 20%, on the most significant one by approx. 50%, all within 180 milliseconds on a normal PC. Copyright 2007 ACM.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

The importance of query-concept-mapping for automatic video retrieval

The importance of query-concept-mapping for automatic video ...

引用

15th ACM International Conference on Multimedia, MM'07

作者： Wang, Dong Li, Xirong Li, Jianmin Zhang, Bo State Key Lab. of Intelligent Tech. and System Department of Computer Science and Technology Tsinghua University Beijing 100084 China

ISBN: (纸本)9781595937025

A new video retrieval paradigm of query-by-concept emerges recently. However, it remains unclear how to exploit the detected concepts in retrieval given a multimedia query. In this paper, we point out that it is important to map the query to a few relevant concepts instead of search with all concepts. In addition, we show that solving this problem through both text and image inputs are effective for search, and it is possible to determine the number of related concepts by a language modeling approach. Experimental evidence is obtained on the automatic search task of TRECVID 2006 using a large lexicon of 311 learned semantic concept detectors. Copyright 2007 ACM.

关键词： Image retrieval

来源：评论

学校读者我要写书评

暂无评论

Web page quality estimation based on linear discriminant function

引用

Journal of Computational Information systems 2007年第3期3卷 1117-1126页

作者： Cen, Rongwei Liu, Yiqun Zhang, Min Ru, Liyun Ma, Shaoping State Key Lab. of Intelligent Technology and Systems Tsinghua University Beijing 100084 China Sogou R and D Center Beijing 100000 China

With the exponential growth of Web data, how to estimate Web page quality effectively and rapidly becomes more and more important for Web information retrieval and knowledge discovery. In this paper, we analyze the differences between retrieval target pages and ordinary pages using query-independent features. Using these features, an algorithm called Linear Page Quality Estimation (LPQE) is proposed for Web page quality estimation. Based on the experiments on. GOV corpus and SOGOU corpus involving 26 million pages, about 95% pages can be reduced with more than 90% retrieval target pages retained using LPQE algorithm. Experimental results based on TREC datasets also show that the retrieval performance on collections selected by LPQE can be close to or even better than that on the whole collection.

关键词： Information retrieval

来源：评论

学校读者我要写书评

暂无评论

BDI agents using evolving artificial neural network for intelligent planning in etching tools

引用

Journal of Harbin Institute of technology (New Series) 2007年第SUPPL. 2期14卷 135-138页

作者： Xu, Hua Jia, Peifa State Key Lab. of Intelligent Technology and Systems Tsinghua University Beijing 100084 China Dept. of Computer Science and Technology Tsinghua University Beijing 100084 China

Multi robot cooperation in etching tools is a complex application since dynamic state changes of all the cooperative robots should be considered in making control decisions. So it is difficult for traditional agent-based method (such as belief decision intention (BDI) method) to schedule cooperative etching robots. A dynamic intelligent planning method is required to improve the quality of the decision making process. According to the etching cooperative robot system requirements, this paper proposes a dynamic and intelligent planning method on the base of hybrid BDI agent architecture, which is with evolving artificial neural network (NN) in building the intelligence especially in planning process. As the input of the NN, the working states of every robot can be got easily. And the control decisions for every cooperative robot can be easily made by itself with the evolving neural network. It has been demonstrated effective in actual applications.

关键词： Robot applications

来源：评论

学校读者我要写书评

暂无评论

Frequency recovery of band-limited seismic data based on sparse spike train deconvolution 77

Frequency recovery of band-limited seismic data based on spa...

引用

77th Society of Exploration Geophysicists International Exposition and Annual Meeting, SEG 2007

作者： Lu, Wen-Kai Liu, Dong-Qi Key State Lab. of Intelligent Technology and System Institute of Information Processing Department of Automation Tsinghua University China Institute of Geophysics PetroChina Research Institute of Petroleum Exploration and Development China

ISBN: (纸本)9781604238976

An iterative algorithm is presented for the frequency recovery of the band-limited seismic data based on the sparse spike train deconvolution (SSTD) method using the minimum entropy criterion. In this method, we exploit an upper limit nonlinear function to construct a new entropy measure, which is insensitive to the large value. Furthermore, a parameter of the nonlinear function is adopted to control the sparsity of the deconvolved signal. Synthetic data experiments are provided and the results show that this method performs well at low computation time. © 2007 Society of Exploration Geophysicists. All rights reserved.

关键词： Functions

来源：评论

学校读者我要写书评

暂无评论

Universal approximation for Takagi-Sugeno fuzzy systems using dynamically constructive method-SISO cases

Universal approximation for Takagi-Sugeno fuzzy systems usin...

引用

2007 IEEE 22nd International Symposium on intelligent Control, ISIC 2007

作者： Fuchun, Sun Ni, Zhao IEEE Dept. of Computer Science and Technology State Key Lab. of Intelligent Technology and Systems Tsinghua University Beijing 100084 China

ISBN: (纸本)142440441X

In this paper, a dynamically constructive method is proposed for proving the universal approximation for single input/single output (SISO) Takagi-Sugeno (T-S) fuzzy systems, which is superior to the existing constructive methods only considering the global property of the function to be approximated and also unrelated to the membership functions of fuzzy sets. The dynamically constructive method proposed not only considers the different property of the nonlinear function in different areas, but also the membership functions of fuzzy sets in fuzzy rules. As a result, the number of rules in the constructed T-S model is greatly reduced. Finally some simulation examples confirm that the T-S fuzzy model constructed by our method with small size rule base can approximate the given nonlinear functions at high accuracy as compared with some typical methods. © 2007 IEEE.

关键词： Fuzzy rules

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：