检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

457 篇 会议
6 篇 期刊文献
4 册 图书

馆藏范围

467 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

73 篇 工学
- 65 篇 计算机科学与技术...
- 43 篇 软件工程
- 18 篇 光学工程
- 12 篇 控制科学与工程
- 9 篇 信息与通信工程
- 4 篇 化学工程与技术
- 3 篇 生物医学工程（可授...
- 2 篇 机械工程
- 2 篇 电气工程
- 2 篇 电子科学与技术（可...
- 1 篇 生物工程
31 篇 理学
- 18 篇 物理学
- 15 篇 数学
- 7 篇 统计学（可授理学、...
- 3 篇 系统科学
- 2 篇 化学
- 2 篇 生物学
7 篇 管理学
- 7 篇 图书情报与档案管...
2 篇 医学
- 2 篇 基础医学(可授医学...
- 2 篇 临床医学
- 2 篇 药学(可授医学、理...

主题

219 篇 computer vision
95 篇 pattern recognit...
83 篇 conferences
79 篇 cameras
66 篇 computer science
59 篇 humans
57 篇 layout
56 篇 robustness
54 篇 image segmentati...
50 篇 shape
39 篇 application soft...
35 篇 face recognition
34 篇 object detection
34 篇 pixel
31 篇 face detection
26 篇 lighting
25 篇 bayesian methods
24 篇 training
23 篇 testing
22 篇 tracking

机构

5 篇 institute for ro...
4 篇 department of co...
4 篇 computer vision ...
4 篇 department of co...
3 篇 school of comput...
3 篇 computer vision ...
3 篇 department of co...
3 篇 computer laborat...
3 篇 department of el...
3 篇 microsoft resear...
3 篇 department of co...
3 篇 chinese acad sci...
3 篇 carnegie mellon ...
3 篇 department of co...
3 篇 computer science...
3 篇 computer vision ...
3 篇 research and dev...
3 篇 department of co...
3 篇 rensselaer polyt...
2 篇 department of co...

作者

11 篇 timofte radu
6 篇 l. van gool
5 篇 g. medioni
4 篇 zhigang zhu
4 篇 m. turk
4 篇 b.s. manjunath
4 篇 jiebo luo
4 篇 j.w. davis
4 篇 d. metaxas
3 篇 vasluianu florin...
3 篇 rafael e. rivade...
3 篇 fan haoqiang
3 篇 busch christoph
3 篇 angel d. sappa
3 篇 r. pless
3 篇 hao tang
3 篇 c. vogler
3 篇 rivadeneira rafa...
3 篇 zhang zhao
3 篇 liu shuaicheng

语言

467 篇 英文

检索条件"任意字段=Conference on Computer Vision and Pattern Recognition Workshop, CVPRW 2003"

共 467 条记录，以下是271-280 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Learning a Synchronous MAP for Improved Face recognition

Learning a Synchronous MAP for Improved Face Recognition

引用

IEEE computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： P.S. Penev Seelicon Research Princeton NJ USA

Maximum A posteriori Probability (MAP) is a machine-learning method for classification of objects by their visual representations, such as humans by the images of their faces. Multiple-class recognition can be rendered in a two-class problem, through the attempt to categorize image differences as more likely under either the between- or the within-class hypotheses. When Gaussian models are learned for these two probability densities, Principal Component Analysis (PCA) is used to estimate them. This procedure leaves open the choice for the dimensionalities at which the two models are estimated-a 2-parameter learning problem. Synchronous MAP (sMAP) is proposed here to reduce the complexity to a single dimension by learning a synchronization between the models on the basis of their power spectra. Experiments are reported on the standard, publicly available FERET fafb Sep96 test protocol that demonstrate sMAP results which are almost twice better than the previously reported (non-synchronous) MAP results, and also improve significantly over the previous state of the art-another subspace approach, based on Linear Discriminant Analysis (LDA).

关键词： Face recognition Principal component analysis Level set Support vector machines Independent component analysis Rendering (computer graphics) Linear discriminant analysis Prototypes Maximum likelihood estimation Humans

来源：评论

学校读者我要写书评

暂无评论

Visual Object Categorization using Distance-Based Discriminant Analysis

Visual Object Categorization using Distance-Based Discrimina...

引用

IEEE computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： S. Kosinov S. Marchand-Maillet T. Pun Computer Vision and Multimedia Laboratory University of Genova Geneva Switzerland

This paper formulates the problem of object categorization in the discriminant analysis framework focusing on transforming visual feature data so as to make it conform to the compactness hypothesis in order to improve categorization accuracy. The sought transformation, in turn, is found as a solution to an optimization problem formulated in terms of inter-observation distances only, using the technique of iterative majorization. The proposed approach is suitable for both binary and multiple-class categorization problems, and can be applied as a dimensionality reduction technique. In the latter case, the number of discriminative features is determined automatically since the process of feature extraction is fully embedded in the optimization procedure. Performance tests validate our method on a number of benchmark data sets from the UCI repository, while the experiments in the application of visual object and content-based image categorization demonstrate very competitive results, asserting the method's capability of producing semantically relevant matches that share the same or synonymous vocabulary with the query category and allowing multiple pertinent category assignment.

关键词： Feature extraction computer vision Data mining Neural networks Benchmark testing Application software Vocabulary Focusing Object detection Linear discriminant analysis

来源：评论

学校读者我要写书评

暂无评论

Challenges in Segmentation of Human Forms in Outdoor Video

Challenges in Segmentation of Human Forms in Outdoor Video

引用

IEEE computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： Zongyi Liu S. Sarkar Computer Science and Engineering University of South Florida Tampa FL USA

Most gait and activity recognition algorithms rely on the use of silhouettes as the low-level representation. However, the detection of good silhouettes is still an open problem, particularly for sequences that are taken outdoors. Illumination conditions, compression artifacts, and low number of pixels on the subject, contribute to the difficulty. Presently, these issues are either ignored by using indoor data or addressed, on a case by case basis, by employing, essentially, a "bag of tricks" based approach. We argue for a more formal approach, based on generic shape and motion models to handle a variety of these problems, under the umbrella of one formalism. We present an HMM-based Eigen Stance model, built based on manually created silhouettes from 71 individuals. The population HMM helps map a frame in any given sequence to a stance and the appearance based Eigen-Stance model is used to reconstruct the computed silhouette in that frame. We quantify the performance in terms of signal based criteria of missed detection and false positive prediction rate. We also show results on three different databases.

关键词： Humans Hidden Markov models computer vision Image segmentation Lighting Shape Motion segmentation Cameras computer science Databases

来源：评论

学校读者我要写书评

暂无评论

Learning Chance Probability Functions for Shape Retrieval or Classification

Learning Chance Probability Functions for Shape Retrieval or...

引用

IEEE computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： B.J. Super Computer Science Department University of Illinois Chicago USA

Several example-based systems for shape retrieval and shape classification directly match input shapes to stored shapes, without using class membership information to perform the matching. We propose a method for improving the accuracy of this type of system. First, the system learns a set of chance probability functions (CPFs). The CPFs estimate the probabilities of obtaining a query shape with particular distances from each training example by chance. The learned CPFs are used at runtime to rapidly estimate the chance probabilities of the observed distances between the actual query shape and the database shapes. These estimated probabilities are then used as a dissimilarity measure for shape retrieval and/or nearest-neighbor classification. The CPF learning method is parameter-free. Experimental evaluation demonstrates that: (1) chance probabilities yield higher accuracy than Euclidean distances; (2) the learned CPFs support fast matching; and (3) the CPF-based system outperforms prior systems on a standard benchmark test of retrieval accuracy.

关键词： Shape measurement Information retrieval Runtime Databases Impedance matching Benchmark testing System testing MPEG 7 Standard computer science Learning systems

来源：评论

学校读者我要写书评

暂无评论

Precise Image Segmentation by Iterative EM-Based Approximation of Empirical Grey Level Distributions with Linear Combinations of Gaussians

Precise Image Segmentation by Iterative EM-Based Approximati...

引用

IEEE computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： A.A. Farag A. El-Baz G. Gimel'farb CVIP Laboratory Department of Electrical and Computer Engineering University of Louisville Louisville KY USA CITR Department of Computer Science University of Auckland Auckland New Zealand

A new algorithm for segmenting a multi-modal grey-scale image is proposed. The image is described as a sample of a joint Gibbs random field of region labels and grey values. To initialize the model, a multi-modal mixed empirical grey level density distribution is approximated with several linear combinations of Gaussians, one linear combination per region. Bayesian decisions involving Expectation-Maximization and genetic optimization techniques are used to sequentially estimate and refine parameters of the model, including the number of Gaussians for each region. The final estimates are more accurate than with conventional normal mixture models and result in more adequate region borders in the image. Experiments with simulated and real medical CT images confirm the accuracy of our approach.

关键词： Image segmentation Gaussian approximation Gaussian distribution Iterative algorithms Linear approximation Bayesian methods Genetics Parameter estimation Gaussian processes Medical simulation

来源：评论

学校读者我要写书评

暂无评论

Object Class recognition with Many Local Features

Object Class Recognition with Many Local Features

引用

IEEE computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： S. Helmer D.G. Lowe Department of Computer Science University of British Columbia Vancouver BC Canada

In this paper we present a method to recognize an object class by learning a statistical model of the class. The probabilistic model decomposes the appearance of an object class into a set of local parts and models the appearance, relative location, co-occurrence, and scale of these parts. However, in many object classification approaches that use local features, learning the parameters is exponential in the number of parts because of the problem of matching local features in the image to parts in the model. In this paper we present a learning method that overcomes this difficulty by adding new parts to the model incrementally, using the Maximum-Likelihood framework. When we add a part to the model, a set of candidate parts are selected and the part that increases the likelihood of the data the most is added to the model. Once this part is added to the model, the parameters for all parts up to this point are updated using EM. The learning and recognition in this approach are translation and scale invariant, robust to background clutter, and has less restriction on the number of parts in the model. The validity of the approach is demonstrated on a real world dataset, where the approach is competitive with others, and where the learning for a rich model is much faster than previous approaches.

关键词： Robustness Face recognition Image recognition Space exploration computer science Learning systems computer vision Motorcycles Shape

来源：评论

学校读者我要写书评

暂无评论

Significance of Elastic Properties in Physics-Based Nonrigid Motion Modeling, A Numerical Sensitivity Analysis

Significance of Elastic Properties in Physics-Based Nonrigid...

引用

IEEE computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： Yong Zhang D.B. Goldgof S. Sarkar Department of Computer Science & Engineering University of South Florida Tampa FL USA

Parameters used in the physical models for nonrigid motion simulation are often not known with high precision. It has been recognized that the commonly used assumptions about the parameters may have adverse effects on the modeling quality. We present an efficient sensitivity analysis method to assess the impact of those assumptions by examining the model’s response to the parameter perturbation. Numerical experiments with both synthetic and real models show that (1) the normalized sensitivity distribution can help determine the relative importance of different parameters; (2) the dimensional sensitivity is useful in the assessment of a particular parameter assumption; (3) the model is more sensitive at the property discontinuity (heterogeneity). The proposed sensitivity analysis method is general and can also be applied to the assessment of other types of assumptions such as nonlinearity and anisotropy.

关键词： Motion analysis Numerical models Sensitivity analysis Biological system modeling Computational modeling Anisotropic magnetoresistance Medical simulation Solid modeling Material properties Biological materials

来源：评论

学校读者我要写书评

暂无评论

Slightly Supervised Learning of Part-Based Appearance Models

Slightly Supervised Learning of Part-Based Appearance Models

引用

IEEE computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： Lexing Xie P. Perez Department of Electrical Engineering Columbia University New York NY USA Campus de Beaulieu Irisa/Inria Rennes France

We extend the GMM-based approach of [Selection of scale-invariant parts for object class recognition], for learning part-based appearance models of object categories, to the unsupervised case where positive examples are corrupted with clutter. To this end, we derive an original version of EM which is able to fit one GMM per class based on partially labeled data. We also allow ourselves a small fraction of un-corrupted positive examples, thus obtaining an effective, yet cheap, slightly supervised learning. Proposed technique allows as well a saliency-based ranking and selection of learnt mixture components. Experiments show that both the semi-supervised GMM fitting with side information and the component selection are effective in identifying salient patches in the appearance of a class of objects. They are thus promising tools to learn class-specific models and detectors similar to those by Weber et al.[Unsupervised learning of models for recognition], but at a lower computational cost, while accommodating larger numbers of atomic parts.

关键词： Supervised learning Detectors Image edge detection Computational efficiency Focusing Costs Unsupervised learning Context modeling Turning computer Society

来源：评论

学校读者我要写书评

暂无评论

Efficient Regularized Least Squares Classification

Efficient Regularized Least Squares Classification

引用

IEEE computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： Peng Zhang Jing Peng EECS Department Tulane University New Orleans LA USA

Kernel-based regularized least squares (RLS) algorithms are a promising technique for classification. RLS minimizes a regularized functional directly in a reproducing kernel Hilbert space defined by a kernel. In contrast, support vector machines (SVMs) implement the structure risk minimization principle and use the kernel trick to extend it to the nonlinear case. While both have a sound mathematical foundation, RLS is strikingly simple. On the other hand, SVMs in general have a sparse representation of the solution. In this paper, we introduce a very fast version of the RLS algorithm while maintaining the achievable level of performance. The proposed new algorithm computes solutions in O(m) time and O(1) space, where m is the number of training points. We demonstrate the efficacy of our very fast RLS algorithm using a number of (both real simulated) data sets.

关键词： Least squares methods Resonance light scattering Kernel Hilbert space computer errors Support vector machines Support vector machine classification Risk management Equations Training data

来源：评论

学校读者我要写书评

暂无评论

Learning From a Small Number of Training Examples by Exploiting Object Categories

Learning From a Small Number of Training Examples by Exploit...

引用

IEEE computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： K. Levi M. Fink Y. Weiss School of Computer Science and Engineering Hebrew University of Jerusalem Jerusalem Israel Center for Neural Computation Hebrew University of Jerusalem Jerusalem Israel

In the last few years, object detection techniques have progressed immensely. Impressive detection results have been achieved for many objects such as faces [11, 14, 9] and cars [11]. The robustness of these systems emerges from a training stage utilizing thousands of positive examples. One approach to enable learning from a small set of training examples is to find an efficient set of features that accurately represent the target object. Unfortunately, automatically selecting such a feature set is a difficult task in itself. In this paper we present a novel feature selection method that is based on the notion of object categories. We assume that when learning to recognize a new object (like an apple) we also know a category it belongs to (fruit). We further assume that features that are useful for learning other objects in the same category (e.g. pear or orange) will also be useful for learning the novel object. This leads to a simple criterion for selecting features and building classifiers. We show that our method gives significant improvement in detection performance in challenging domains.

关键词： Object detection Face detection computer science Robustness Humans computer vision computer displays Switches computer Society pattern recognition

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共47页 << < 24 25 26 27 28 29 30 31 32 33 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：