检索结果-内蒙古大学图书馆

Proceedings of the Second International Conference on Internet Multimedia Computing and Service

作者： Yu, Zhou Cai, Deng He, Xiaofei State Key Lab. of CAD and CG College of Computer Science Zhejiang University China

ISBN: (纸本)9781450304603

Fast similarity search is one of the key techniques in many large scale learning and data mining applications. Recently, hashing-based methods, which create compact and efficient codes that preserve data distribution, have received considerable attention due to their promising theoretical and empirical results. An ideal hashing method 1) can naturally have out-of-sample extension;2) has very low computational complexity;and 3) has significant improvement over linear search in the original space in terms of accuracy. However, most existing hashing methods failed to satisfy all the above three requirements. In this paper, we propose a new method called Error-correcting Output Hashing (ECOH) which meets all the above three requirements. ECOH first groups all the samples into clusters using a conventional clustering algorithm. Each cluster is assigned an Error-Correcting Output Code (ECOC) and the linear mappings from the sample vectors to the ECOC are then learned using linear regression models. In this way, ECOH learns both the binary code for each sample and the function which links the input vector and the output code. Experimental results on real world data sets demonstrate the effectiveness and efficiency of the proposed approach. Copyright 2010 ACM.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Unsupervised feature selection for Multi-Cluster data

Unsupervised feature selection for Multi-Cluster data

引用

16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD-2010

作者： Cai, Deng Zhang, Chiyuan He, Xiaofei State Key Lab. of CAD and CG College of Computer Science Zhejiang University China

ISBN: (纸本)9781450300551

In many data analysis tasks, one is often confronted with very high dimensional data. Feature selection techniques are designed to find the relevant feature subset of the original features which can facilitate clustering, classification and retrieval. In this paper, we consider the feature selection problem in unsupervised learning scenario, which is particularly difficult due to the absence of class lab.ls that would guide the search for relevant information. The feature selection problem is essentially a combinatorial optimization problem which is computationally expensive. Traditional unsuper-vised feature selection methods address this issue by selecting the top ranked features based on certain scores computed independently for each feature. These approaches neglect the possible correlation between different features and thus can not produce an optimal feature subset. Inspired from the recent developments on manifold learning and L1-regularized models for subset selection, we propose in this paper a new approach, called Multi-Cluster Feature Selection (MCFS), for unsupervised feature selection. Specifically, we select those features such that the multi-cluster structure of the data can be best preserved. The corresponding optimization problem can be efficiently solved since it only involves a sparse eigen-problem and a L1-regularized least squares problem. Extensive experimental results over various real-life data sets have demonstrated the superiority of the proposed algorithm. © 2010 ACM.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Large scale spectral clustering with landmark-based representation 25

Large scale spectral clustering with landmark-based represen...

引用

25th AAAI Conference on Artificial Intelligence and the 23rd Innovative Applications of Artificial Intelligence Conference, AAAI-11 / IAAI-11

作者： Chen, Xinlei Cai, Deng State Key Lab. of CAD and CG College of Computer Science Zhejiang University China

ISBN: (纸本)9781577355083

Spectral clustering is one of the most popular clustering approaches. Despite its good performance, it is limited in its applicability to large-scale problems due to its high computational complexity. Recently, many approaches have been proposed to accelerate the spectral clustering. Unfortunately, these methods usually sacrifice quite a lot information of the original data, thus result in a degradation of performance. In this paper, we propose a novel approach, called Landmark-based Spectral Clustering (LSC), for large scale clustering problems. Specifically, we select p( n) representative data points as the landmarks and represent the original data points as the linear combinations of these landmarks. The spectral embedding of the data can then be efficiently computed with the landmark-based representation. The proposed algorithm scales linearly with the problem size. Extensive experiments show the effectiveness and efficiency of our approach comparing to the state-of-the-art methods. Copyright © 2011, Association for the Advancement of Artificial Intelligence. All rights reserved.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Stretch-based tetrahedral mesh manipulation 07

Stretch-based tetrahedral mesh manipulation

引用

graphics Interface 2007

作者： Song, Wenhao Liu, Ligang Computer Graphics Department Max-Planck-Institut Informatik Saarbrücken Germany Department of Mathematics State Key Lab. of CAD and CG Zhejiang University China

ISBN: (纸本)1568813376

We present a novel least scaling distortion metric to measure the deformation distortion for tetrahedral meshes. The stretch-like metric is a combination of Jacobian matrix norm and tetrahedron volume and has the properties of good shape preservation and rotation invariance. Based on our metric, we propose a uniform non-linear optimization solution to a variety of tetrahedral mesh manipulation applications including shape deformation, interpolation, deformation transfer, and deformation learning. Our approach can produce volume preserving and flip free tetrahedral mesh results, which performs much better than the previous tetrahedral manipulation approaches. We also demonstrate an efficient and practical application using free-form deformation technique. The object is embedded in a rough control tetrahedral mesh and deformed by editing the tetrahedral mesh with various constraints. Each vertex of the object can be obtained by its barycentric coordinates according to its embedding tetrahedron of the control tetrahedral mesh.

关键词： Image analysis

来源：评论

学校读者我要写书评

暂无评论

Decreasing accelerated gradient descent method for nonnegative matrix factorization

Decreasing accelerated gradient descent method for nonnegati...

引用

2nd International Conference on Information Engineering and Applications, IEA 2012

作者： Liu, Furui State Key Lab. of CAD and CG College of Computer Science Zhejiang University Hangzhou China

ISBN: (纸本)9781447148555

In this paper, by bringing in a user defined nonnegative control matrix to form a new objective function, I modify the update rules correspondingly and propose a novel decreasing accelerated gradient descent method for nonnegative matrix factorization (DAGDM) which can make the matrix of the decomposition results achieve sparse. The control matrix also contains the weighting information, which puts different weight on different parts of the result matrix to be produced. This will provide a control interface of nonnegative matrix factorization to make a sparse and light basis matrix. Experimental results demonstrate the effectiveness of the proposed method. © 2013 Springer-Verlag.

关键词： Matrix factorization

来源：评论

学校读者我要写书评

暂无评论

Accelerating locality preserving nonnegative matrix factorization 12

Accelerating locality preserving nonnegative matrix factoriz...

引用

21st ACM International Conference on Information and Knowledge Management, CIKM 2012

作者： Yao, Guanhong Deng, Cai State Key Lab. of CAD and CG College of Computer Science Zhejiang University Hangzhou China

ISBN: (纸本)9781450311564

Matrix factorization techniques have been frequently applied in information retrieval, computer vision and pattern recognition. Among them, Non-negative Matrix Factorization (NMF) has received considerable attention due to its psychological and physiological interpretation of naturally occurring data whose representation may be parts-based in the human brain. Locality Preserving Non-negative Matrix Factorization (LPNMF) is a recently proposed graph-based NMF extension which tries to preserves the intrinsic geometric structure of the data. Compared with the original NMF, LPNMF has more discriminating power on data representa- tion thanks to its geometrical interpretation and outstanding ability to discover the hidden topics. However, the computa- tional complexity of LPNMF is O(n3), where n is the number of samples. In this paper, we propose a novel approach called Accelerated LPNMF (A-LPNMF) to solve the com- putational issue of LPNMF. Specifically, A-LPNMF selects p (p j n) landmark points from the data and represents all the samples as the sparse linear combination of these landmarks. The non-negative factors which incorporates the geometric structure can then be efficiently computed. Experimental results on the real data sets demonstrate the effectiveness and efficiency of our proposed method. © 2012 ACM.

关键词： Non-negative matrix factorization

来源：评论

学校读者我要写书评

暂无评论

Interactive point cloud blending by drag-and-drop

引用

Journal of Zhejiang University-Science A(Applied Physics & Engineering) 2007年第10期8卷 1633-1641页

作者： ZOU Wan-hong?1, DING Zhan1, YE Xiu-zi1, CHEN Zhi-yang2 (1state key lab. of cad and CG, School of computer Science and Technology, Zhejiang University, Hangzhou 310027, China) (2Software College, Zhejiang University of Technology, Hangzhou 310014, China) State Key Lab. of CAD and CG School of Computer Science and Technology Zhejiang University Hangzhou China Software College Zhejiang University of Technology Hangzhou China

With the rapid development of 3D digital photography and 3D digital scanning devices, massive amount of point samples can be generated in acquisition of complex, real-world objects, and thus create an urgent need for advanced point-based processing and editing. In this paper, we present an interactive method for blending point-based geometries by dragging-and- dropping one point-based model onto another model’s surface metaphor. We first calculate a blending region based on the polygon of interest when the user drags-and-drops the model. Radial basis function is used to construct an implicit surface which smoothly interpolates with the transition regions. Continuing the drag-and-drop operation will make the system recalculate the blending regions and reconstruct the transition regions. The drag-and-drop operation can be compound in a constructive solid geometry (CSG) manner to interactively construct a complex point-based model from multiple simple ones. Experimental results showed that our method generates good quality transition regions between two raw point clouds and can effectively reduce the rate of overlapping during the blending.

关键词： Drag-and-drop Point cloud model Interactive blending Geometry modeling

来源：评论

学校读者我要写书评

暂无评论

Search web images using objects, backgrounds and conditions

Search web images using objects, backgrounds and conditions

引用

20th ACM International Conference on Multimedia, MM 2012

作者： Zhang, Jiemi Wu, Chenxia Cai, Deng State Key Lab. of CAD and CG College of Computer Science Zhejiang University Hangzhou China

ISBN: (纸本)9781450310895

As the volumes of web images have grown rapidly in the last decade, Content-Based Image Retrieval (CBIR) has attracted substantial interests as an effective tool to manage the images. Most existing CBIR systems focus on the object in the image, while ignoring the conditions (day/night, sunny/rain, etc) and the backgrounds, both of which are very helpful to meet the user's information need. To overcome this shortcoming, in this paper, we present a novel CBIR system depending on a novel query formulation considering three aspects: Object, Background and Condition. Specifically, we design a user-friendly interface to help the user formulate a query. The interface can allow the user to give the percentage, relative position and size of each object in the background. Moreover, a corresponding effective ranking method is proposed to return the desirable search results. Experimental results demonstrate that our proposed system improves the searching performance and the user experience compared with the existing searching systems. © 2012 ACM.

关键词： Content based retrieval

来源：评论

学校读者我要写书评

暂无评论

Collab.ratively modeling buildings from large-scale street-side and remote sensing images

Collaboratively modeling buildings from large-scale street-s...

引用

2nd International Conference on Multimedia Technology, ICMT 2011

作者： Hua, Wei Zhang, Wei State Key Lab. of CAD and CG College of Computer Science Zhejiang University Hangzhou China

ISBN: (纸本)9781612847740

This paper proposed an approach to rapidly generate 3D models for street-side buildings from street-side images, remote sensing images, and GPS information. Traditional modeling methods usually require a single user to fulfill all processes of 3D modeling, and lack efficient management on massive data. Thus, they are unsuitable for large-scale modeling. In order to overcome those drawbacks, we employ the pipeline idea. The modeling processes are divided into several steps, which are further assembled to form a pipeline elab.rately. We allocate computing resources into each step according to their requirements;on the other side, human resources are deployed into the pipeline to achieve team-work modeling. To demonstrate the effectiveness of ur approach, we developed a distributed prototype system for rapid large-scale urban 3D modeling. This system was tested to build an urban scene with more than 500, 000 street-side images. The results show great improvement on modeling efficiency compared with traditional methods, and it reveals a great prospect in applications. © 2011 IEEE.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

Sparse structured probabilistic projections for factorized latent spaces 11

Sparse structured probabilistic projections for factorized l...

引用

20th ACM Conference on Information and Knowledge Management, CIKM'11

作者： Qu, Xinquan Chen, Xinlei State Key Lab. of CAD and CG College of Computer Science Zhejiang University Hangzhou China

ISBN: (纸本)9781450307178

Building a common representation for several related data sets is an important problem in multi-view learning. CCA and its extensions have shown that they are effective in finding the shared variation among all data sets. However, these models generally fail to exploit the common structure of the data when the views are with private information. Recently, methods explicitly modeling the information into shared part and private parts have been proposed, but they presume to know the prior knowledge about the latent space, which is usually impossible to obtain. In this paper, we propose a probabilistic model, which could simultaneously learn the structure of the latent space whilst factorize the information correctly, therefore the prior knowledge of the latent space is unnecessary. Furthermore, as a probabilistic model, our method is able to deal with missing data problem in a natural way. We show that our approach attains the performance of state-of-art methods on the task of human pose estimation when the motion capture view is completely missing, and significantly improves the inference accuracy with only a few observed data. © 2011 ACM.

关键词： factorized latent space multi-view learning sparse structured projections

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：