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111-120 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：

Empirical Studies of the Existence of the Biometric Menagerie in the FRGC 2.0 Color Image Corpus

Empirical Studies of the Existence of the Biometric Menageri...

引用

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

作者： M. Wittman P. Davis P.J. Flynn Department of Computer Science and Engineering University of Notre Dame Notre Dame IN USA

The issue of recognizability of subjects in biometric identification is of particular interest to the designers of these systems. We have applied the concept of Doddington’s biometric menagerie to the area of facial recognition. We performed a series of tests for the presence of goats, lambs, and wolves on FRGC 2.0 color image data. The data for the subjects that appeared at the extreme end of these tests was then visually examined. Even a cursory comparison of images showed that for this set of data, some images fell into the defined menagerie categories. Our tests show the statistical existence of these animal classifications within the constraints of this set of FRGC 2.0 data using the baseline matching algorithm. Ultimately, these tests were limited by the image data set and matching algorithm used. For further confirmation of the existence of the menagerie, the analysis must be expanded to include different image sets and matching algorithms..

关键词： Biometrics Color Testing Face recognition Probes Principal component analysis Image analysis Statistics computer science USA Councils

来源：评论

学校读者我要写书评

暂无评论

Detecting Bilateral Symmetry in Perspective

Detecting Bilateral Symmetry in Perspective

引用

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

作者： H. Cornelius G. Loy Computational Vision & Active Perception Laboratory Royal Institute of Technology Stockholm Sweden

A method is presented for efficiently detecting bilateral symmetry on planar surfaces under perspective projection. The method is able to detect local or global symmetries, locate symmetric surfaces in complex backgrounds, and detect multiple incidences of symmetry. Symmetry is simultaneously evaluated across all locations, scales, orientations and under perspective skew. Feature descriptors robust to local affine distortion are used to match pairs of symmetric features. Feature quadruplets are then formed from these symmetric feature pairs. Each quadruplet hypothesises a locally planar 3D symmetry that can be extracted under perspective distortion. The method is posed independently of a specific feature detector or descriptor. Results are presented demonstrating the efficacy of the method for detecting bilateral symmetry under perspective distortion. Our unoptimised Matlab implementation, running on a standard PC, requires of the order of 20 seconds to process images with 1,000 feature points.

关键词： computer vision Object detection Image analysis Detectors Psychology Image reconstruction Vehicle detection Laboratories Robustness Mirrors

来源：评论

学校读者我要写书评

暂无评论

Good Continuation in Layers: Shading flows, color flows, surfaces and shadows

Good Continuation in Layers: Shading flows, color flows, sur...

引用

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

作者： O. Ben-Shahar A. Glaser S.W. Zucker Computer Science Ben-Gurion University of the Negev Israel Applied Mathematics Yale University New Heaven CT USA Computer Science Yale University New Heaven CT USA

We extend the concept of good continuation in a uniform fashion from boundaries to shading, hue, and texture. Each has the property that local measurements yield an orientation, which we explicitly establish for hue using geometric harmonic techniques. Good continuation arises in a geometric sense, because these orientations all vary smoothly in an appropriate sense. Thus they correspond to flows. Taken together they define a layered set of flows, in the sense the "horizontal" computations within each flow provide global consistency while "vertical" computations across flows enable the identification of shading and shadowing and different types of edges. Evidence is reviewed that primate visual systems enjoy such an organization.

关键词： computer science Computed tomography Shadow mapping Visual system computer vision Surface texture Mathematics Color Image segmentation Light sources

来源：评论

学校读者我要写书评

暂无评论

Robust Estimation in the Presence of Spatially Coherent Outliers

Robust Estimation in the Presence of Spatially Coherent Outl...

引用

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

作者： R. Fransens C. Strecha L. Van Gool ESAT-PSI Katholieke Universiteit Leuven Leuven Belgium

We present a generative model based approach to deal with spatially coherent outliers. The model assumes that image pixels are generated by either one of two distinct processes: an inlier process which is responsible for the generation of the majority of the data, and an outlier process which generates pixels not adhering to the inlier model. The partitioning into inlier and outlier regions is made explicit by the introduction of a hidden binary map. To account for the coherent nature of outliers this map is modelled as a Markov Random Field, and inference is made tractable by a mean field EM-algorithm. We make a connection with classical robust estimation theory, and derive the analytic expressions of the equivalent M-estimator for two limiting cases of our model. The effectiveness of the proposed method is demonstrated with two examples. First, in a synthetic linear regression problem, we compare our approach with different M-estimators. Next, in a 2D-face recognition experiment, we try to identify people from partially occluded facial images.

关键词： Robustness Spatial coherence Additive noise Pixel Face recognition computer vision Parameter estimation Image generation Image recognition Layout

来源：评论

学校读者我要写书评

暂无评论

Modeling Inter- and Intra-Patient Anatomical Variation Using a Bilinear Model

Modeling Inter- and Intra-Patient Anatomical Variation Using...

引用

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

作者： Yongwon Jeong R.J. Radke Department of Electrical Computer and Systems Engineering Rensselaer Polytechnic Institute Troy NY USA

We introduce a novel method for modeling the natural anatomical variation of an organ along inter-patient and intra-patient axes using a bilinear model. Bilinear models are attractive for this purpose since one type of variation can be explored while the other is held constant. We apply our model to a total of 204 prostate shapes contoured from CT imagery of 12 different patients, and show that the learned bilinear models can fit both training and testing shapes accurately. We also demonstrate the superior performance of the bilinear model over a linear model with the same number of parameters in adapting to prostate shapes from a new patient acquired immediately prior to consecutive fractions of radiation therapy.

关键词： Biomedical imaging Computed tomography computer vision Biomedical applications of radiation Application software Heart Image segmentation Shape control Training data Systems engineering and theory

来源：评论

学校读者我要写书评

暂无评论

Scrambling for Video Surveillance with Privacy

Scrambling for Video Surveillance with Privacy

引用

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

作者： F. Dufaux T. Ebrahimi Ecole Polytechnique Fédérale de Lausanne Lausanne Switzerland

In this paper, we address the problem of scrambling regions of interest in a video sequence for the purpose of preserving privacy in video surveillance. We propose an efficient solution based on transform-domain scrambling. More specifically, the sign of selected transform coefficients is pseudo-randomly flipped during encoding. We address more specifically the two cases of MPEG-4 and Motion JPEG 2000. Simulation results show that the technique can be successfully applied to conceal information in regions of interest in the scene while providing with a good level of security. Furthermore, the scrambling is flexible and allows adjusting the amount of distortion introduced. Finally, this is achieved with a small impact on coding performance and negligible computational complexity increase.

关键词： Video surveillance Privacy Layout Video compression computer architecture Face detection Cryptography Access control Video coding Performance analysis

来源：评论

学校读者我要写书评

暂无评论

Saliency and Segregation Without Feature Gradient: New Insights for Segmentation from Orientation-Defined Textures

Saliency and Segregation Without Feature Gradient: New Insig...

引用

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

作者： O. Ben-Shahar Ben-Gurion University of the Negev Beersheba Israel

The analysis of texture patterns, and texture segregation in particular, are at the heart of perceptual organization. In this paper we question the widely accepted view that the detection (both perceptual and computational) of salient perceptual singularities between perceptually coherent texture regions is tightly dependent upon feature gradients. Specifically, we study smooth orientation-defined textures (ODTs) and show that they exhibit striking perceptual singularities even without any outstanding gradients in their defining feature, namely orientation. We further show how these generic singularities are not only unpredictable from the orientation gradient, but that they also defy popular segmentation algorithms and neural models. We then examine smooth ODTs from a (differential) geometric point of view and develop a theory that fully predicts their perceptual singularities from two ODT curvatures. The computational results exhibit striking correspondence to segregation performed by human subjects and provide a conclusive evidence for the role of curvature in texture segregation. Extensions and implications of our results are developed for various aspects of visual processing.

关键词： Humans pattern analysis Heart Shape Surface texture Geometry Image segmentation Predictive models computer vision pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Combining Regions and Patches for Object Class Localization

Combining Regions and Patches for Object Class Localization

引用

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

作者： C. Pantofaru G. Dorko C. Schmid M. Hebert The Robotics Institute CMU USA TU Darmstadt Germany INRIA Rhone-Alpes France

We introduce a method for object class detection and localization which combines regions generated by image segmentation with local patches. Region-based descriptors can model and match regular textures reliably, but fail on parts of the object which are textureless. They also cannot repeatably identify interest points on their boundaries. By incorporating information from patch-based descriptors near the regions into a new feature, the Region-based Context Feature (RCF), we can address these issues. We apply Region-based Context Features in a semi-supervised learning framework for object detection and localization. This framework produces object-background segmentation masks of deformable objects. Numerical results are presented for pixel-level performance.

关键词： Object detection Shape Labeling Image segmentation Smart pixels Intelligent robots Image generation Semisupervised learning computer vision Layout

来源：评论

学校读者我要写书评

暂无评论

Strangeness Based Feature Selection for Part Based recognition

Strangeness Based Feature Selection for Part Based Recogniti...

引用

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

作者： Fayin Li J. Kosecka H. Wechsler George Mason University Fairfax VA USA

Motivated by recent approaches to object recognition, where objects are represented in terms of parts, we propose a new algorithm for selecting discriminative features based on strangeness measure. We will show that k-nearest neighbour strangeness can be used to measure the uncertainty of individual features with respect to the class labels and forms piecewise constant decision boundary. We study its properties and generalization capability by comparing it with optimal decision boundary and boundary obtained by k-nearest-neighbor methods. The proposed feature selection algorithm is tested both in simulation and real experiments, demonstrating that meaningful discriminative local features are selected despite the presence of large numbers of distractors. In the second stage we demonstrate how to integrate the local evidence provided by the selected features in the boosting framework in order to obtain the final strong classifier. The performance of the feature selection algorithm and the classifier is evaluated on the Caltech five object category database, achieving superior results in comparison with existing approaches at lower computational cost.

关键词： computer vision Object recognition Testing Supervised learning Vocabulary Boosting Spatial databases Computational efficiency Predictive models Data visualization

来源：评论

学校读者我要写书评

暂无评论

Cinematized Reality: Cinematographic 3D Video System for Daily Life Using Multiple Outer/Inner Cameras

Cinematized Reality: Cinematographic 3D Video System for Dai...

引用

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

作者： Hansung Kim R. Sakamoto K. Kogure I. Kitahara Media Information Science Laboratory ATR Keihanna Science City Kyoto Japan Department of Intelligent Interaction Technologies University of Tsukuba Tsukuba Ibaraki Japan

The purpose of Cinematized Reality is to record unexpected moments in people’s lives and create movies that look as if they were created from real, expertly captured film footage. The approach toward Cinematized Reality is to generate free-view video streams from multiple videos. The proposed system reconstructs 3D models of the capturing space using outer environmental cameras and an inner omni-directional camera, and then generates realistic video of those objects from a designated viewpoint by controlling a virtual camera as an expert would. This prototype system follows the grammar of film language and applies expert knowledge to generate desirable film footage using a sequence of shots taken by the virtual camera.

关键词： Calibration Videoconference Network servers Cities and towns Layout Instruments Shape measurement Smart cameras Information science computer vision

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 << < 8 9 10 11 12 13 14 15 16 17 > >>

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：