检索结果-内蒙古大学图书馆

3rd International Conference on Internet Multimedia Computing and Service, ICIMCS 2011

作者： Chen, Xinlei Qu, Xinquan Li, Zijian State Key Lab. of CAD and CG College of Computer Science Zhejiang University Hangzhou 310027 China

ISBN: (纸本)9781450309189

In multimedia applications, dimension reduction is essential to the effectiveness and efficiency of an algorithm due to the curse of dimensionality. Recently, its adaptive variants have received considerable attention in unsupervised learning since a single pass without lab.l information often fails to guarantee an optimal representation, especially when the parameters are not set properly. However, most such methods are basically linear, therefore unable to consider the geometrical structure of the data space. In this paper, we propose a novel algorithm called Nonlinear Adaptive Dimension Reduction (NADR), which adaptively learns the optimal low-dimensional coordinates that preserve the intrinsic geometric structure of the original data. Moreover, the incorporation of K-means enables NADR to be a powerful alternative for cluster analysis. Experiments on benchmark image data sets illustrate that NADR outperforms the state-of-the-art adaptive dimension reduction methods. © 2011 ACM.

关键词： Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

A facial expression model for human-like agent

A facial expression model for human-like agent

引用

2006 IEEE Conference on Robotics, Automation and Mechatronics

作者： Bin, Yang Peifa, Jia State Key Lab. of Intelligent Technology and System Department of Computer Science Tsinghua University Beijing China

ISBN: (纸本)1424400244

A major unsolved problem in human-like agent is the construction and application of realistic human facial expression models. Human-like agents should interact with human by recognizing human facial expression and synthesizing facial expressions to show their emotional states. However there is no a uniform model for both recognition and synthesis of facial expression. In this paper, we present a model for solving this challenging task. First, we setup a muscle-based facial model and use muscles' contraction as controlling factors because all the facial actions are driven by the muscles. An orthogonal facial expression space is constructed by regarding each controlling factor as a dimension. Then muscles' contractions are calculated from facial images to construct the facial vector. Thus the facial vector can be used on the facial expression synthesis system of human-like agent. In this paper, we also present a facial function to describe the dynamic procedure of facial expressions. Last, this paper points out the direction of future work. © 2006 IEEE.

关键词： Anthropomorphic robots

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised regression via parallel field regularization

Semi-supervised regression via parallel field regularization

引用

25th Annual Conference on Neural Information Processing Systems 2011, NIPS 2011

作者： Lin, Binbin Zhang, Chiyuan He, Xiaofei State Key Lab. of CAD and CG College of Computer Science Zhejiang University Hangzhou 310058 China

ISBN: (纸本)9781618395993

This paper studies the problem of semi-supervised learning from the vector field perspective. Many of the existing work use the graph Laplacian to ensure the smoothness of the prediction function on the data manifold. However, beyond smoothness, it is suggested by recent theoretical work that we should ensure second order smoothness for achieving faster rates of convergence for semisupervised regression problems. To achieve this goal, we show that the second order smoothness measures the linearity of the function, and the gradient field of a linear function has to be a parallel vector field. Consequently, we propose to find a function which minimizes the empirical error, and simultaneously requires its gradient field to be as parallel as possible. We give a continuous objective function on the manifold and discuss how to discretize it by using random points. The discretized optimization problem turns out to be a sparse linear system which can be solved very efficiently. The experimental results have demonstrated the effectiveness of our proposed approach.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

A new method of interactive marker-driven free form mesh deformation

A new method of interactive marker-driven free form mesh def...

引用

Geometric Modeling and Imaging New Trends, 2006

作者： Difei, Lu Ying, Zhang Xiuzi, Ye College of Computer Science State Key Lab. of CAD and CG Zhejiang University Hangzhou 310027 China

ISBN: (纸本)0769526047

In this paper, we propose a new scheme for marker-driven free form global mesh deformation without manually establishing a skeleton orfreeform deformation domain beforehand. It allows a user to deform a given mesh interactively and intuitively. Firstly markers are placed at existing mesh vertices. Then user moves markers as constrained handles in a free form style. Next a global shape deformation is obtained by reconstructing the shape corresponding to the translated markers. Finally the system smooth the deformed mesh to get desired result. Our approach successfully conveys a sense of rigidity of the mesh, which is difficult in space-warp approaches. We demonstrate that our system can be used to intuitively deform a complex mesh with very little effort. We also show that our approach of the deformation provides a natural way to interpolate between key frames, allowing production of simple key framed animations. © 2006 IEEE.

关键词： Interactive computer graphics

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 CG School of Computer Science Technology Zhejiang University Hangzhou 310027 China Software College Zhejiang University of Technology Hangzhou 310014 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

Drowsy region-based caches: Minimizing both dynamic and static power dissipation

Drowsy region-based caches: Minimizing both dynamic and stat...

引用

2005 Computing Frontiers Conference

作者： Geiger, Michael J. McKee, Sally A. Tyson, Gary S. Advanced Computer Architecture Lab. University of Michigan Ann Arbor MI 48109-2122 Computer Systems Lab. Cornell University Ithaca NY 14853-3801 Department of Computer Science Florida State University Tallahassee FL 32306-4530

ISBN: (纸本)1595930183

Power consumption within the memory hierarchy grows in importance as on-chip data caches occupy increasingly greater die area. Among dynamic power conservation schemes, horizontal partitioning reduces average power per data access by employing multiple smaller structures or using cache subbanks. For instance, region-based caching places small caches dedicated to stack and global accesses next to the LI data cache. With respect to static power dissipation, leakage power may be addressed at both circuit and architectural levels. Drowsy caches reduce leakage power by keeping inactive lines in a low-power mode. Here we merge drowsy and region-based caching to reduce overall cache power consumption, showing that the combination yields more benefits than either alone. Applications from the MiBench suite exhibit power reductions in the cache system of up to 68-71%, depending on memory configuration, with a small increase in execution time. Copyright 2005 ACM.

关键词： Buffer storage

来源：评论

学校读者我要写书评

暂无评论

Beyond basic region caching: Specializing cache structures for high performance and energy conservation

引用

1st International Conference on High Performance Embedded architectures and Compilers, HiPEAC 2005

ISBN: (纸本)3540303170

Increasingly tight energy design goals require processor architects to re-think the organizational structure of microarchitectural resources. In this paper, we examine a new multilateral cache organization that replaces a conventional data cache with a set of smaller region caches that significantly reduces energy consumption with little performance impact. This is achieved by tailoring the cache resources to the specific reference characteristics of each application. © Springer-Verlag Berlin Heidelberg 2005.

关键词： Embedded systems

来源：评论

学校读者我要写书评

暂无评论

FIFAWC:a dataset with detailed annotation and rich semantics for group activity recognition

引用

Frontiers of computer Science 2024年第6期18卷 271-272页

作者： Duoxuan PEI Di HUANG Yunhong WANG State Key Laboratory of Software Development Environment School of Computer Science and EngineeringBeihang UniversityBeijing 100191China Intelligent Recognition and Image Processing Lab. School of Computer Science and EngineeringBeihang UniversityBeijing 100191China

1 *** Activity Recognition(GAR),which aims to identify activities performed collectively in videos,has gained significant attention *** conventional action recognition centered on single individuals,GAR explores the c... 详细信息

关键词： has collective gained

来源：评论

学校读者我要写书评

暂无评论

Automatic Target Segmentation based on Texture for Microscopic Images of Chinese Herbal Powders

Automatic Target Segmentation based on Texture for Microscop...

引用

第25届中国控制与决策会议

作者： Jun Li Yixu Song Yaoli Li Shaoqin Cai Zehong Yang State Key Laboratory of Intelligent Technology and Systems Computer Science and Technology Department Tsinghua University State Key Lab. of Natural and Biological Drugs School of Pharmaceutical Sciences Peking University

ISBN: (纸本)9781467355339

The identification of Chinese herbal powders is usually based on physical or chemical detection, but that is far from enough to identity dozens of herbal species. Microscopic images of these powders contain variety of information, and important evidence for identification. These images usually contain variety of substance, and most of them are noises, which makes the target segmentation become a difficult job. An effective automatic target segmentation algorithm based on texture is proposed in this paper. Our method consists of two steps: "Preliminary Segmentation" and "Further Segmentation". Firstly, feature vector of texture is extracted and clustered into two groups: background and foreground;secondly, taking the continuity of edge and the locality of target into consideration, energy equations are established, and Maximum flow-Minimum cut Algorithm is applied to solve them. Three groups of images are used to test our method: microscopic images of Chinese herbal powders, Brodaze Images, and natural texture images. And the experimental results show that our method achieves a better segmentation compared with Grab-Cut, and additionally user inter-action is not required in our method.

关键词： Chinese herbal powder microscopic images automatic segmentation texture feature

来源：评论

学校读者我要写书评

暂无评论

Gaussian Mixture Model with local consistency

Gaussian Mixture Model with local consistency

引用

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

ISBN: (纸本)9781577354642

Gaussian Mixture Model (GMM) is one of the most popular data clustering methods which can be viewed as a linear combination of different Gaussian components. In GMM, each cluster obeys Gaussian distribution and the task of clustering is to group observations into different components through estimating each cluster's own parameters. The Expectation-Maximization algorithm is always involved in such estimation problem. However, many previous studies have shown naturally occurring data may reside on or close to an underlying submanifold. In this paper, we consider the case where the probability distribution is supported on a sub-manifold of the ambient space. We take into account the smoothness of the conditional probability distribution along the geodesies of data manifold. That is, if two observations are "close" in intrinsic geometry, their distributions over different Gaussian components are similar. Simply speaking, we introduce a novel method based on manifold structure for data clustering, called Locally Consistent Gaussian Mixture Model (LCGMM). Specifically, we construct a nearest neighbor graph and adopt Kullback-Leibler Divergence as the "distance" measurement to regularize the objective function of GMM. Experiments on several data sets demonstrate the effectiveness of such regularization. Copyright © 2010, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Gaussian distribution

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：