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

8,430 篇 会议
38 篇 期刊文献
7 册 图书

馆藏范围

8,474 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

4,194 篇 工学
- 3,828 篇 计算机科学与技术...
- 2,067 篇 软件工程
- 1,218 篇 光学工程
- 530 篇 控制科学与工程
- 400 篇 信息与通信工程
- 282 篇 仪器科学与技术
- 262 篇 机械工程
- 233 篇 电气工程
- 155 篇 生物工程
- 144 篇 生物医学工程（可授...
- 110 篇 电子科学与技术（可...
- 57 篇 安全科学与工程
- 52 篇 建筑学
- 51 篇 化学工程与技术
- 48 篇 土木工程
- 43 篇 交通运输工程
- 39 篇 力学（可授工学、理...
1,991 篇 理学
- 1,352 篇 物理学
- 1,167 篇 数学
- 415 篇 统计学（可授理学、...
- 212 篇 生物学
- 49 篇 化学
- 34 篇 系统科学
222 篇 管理学
- 160 篇 图书情报与档案管...
- 66 篇 管理科学与工程(可...
- 36 篇 工商管理
202 篇 艺术学
- 202 篇 设计学（可授艺术学...
189 篇 医学
- 188 篇 临床医学
- 38 篇 基础医学(可授医学...
39 篇 法学
- 37 篇 社会学
21 篇 农学
11 篇 教育学
7 篇 经济学
6 篇 军事学

主题

3,322 篇 computer vision
1,174 篇 pattern recognit...
901 篇 cameras
873 篇 conferences
761 篇 computer science
660 篇 image segmentati...
624 篇 layout
573 篇 training
540 篇 shape
507 篇 robustness
451 篇 humans
423 篇 feature extracti...
422 篇 face recognition
402 篇 computational mo...
389 篇 object detection
345 篇 visualization
340 篇 computer archite...
335 篇 application soft...
291 篇 lighting
267 篇 image reconstruc...

机构

41 篇 microsoft resear...
30 篇 department of co...
25 篇 department of co...
23 篇 institute for co...
22 篇 department of co...
22 篇 school of comput...
20 篇 university of sc...
20 篇 swiss fed inst t...
19 篇 institute of com...
18 篇 swiss fed inst t...
17 篇 tsinghua univers...
17 篇 the robotics ins...
17 篇 carnegie mellon ...
17 篇 department of co...
16 篇 computer vision ...
16 篇 school of comput...
15 篇 institute of inf...
15 篇 school of comput...
14 篇 department of in...
14 篇 department of co...

作者

57 篇 timofte radu
25 篇 s.k. nayar
24 篇 van gool luc
24 篇 huang thomas s.
22 篇 nayar shree k.
22 篇 t. kanade
21 篇 jain anil k.
20 篇 t.s. huang
19 篇 luc van gool
18 篇 xiaoou tang
18 篇 horst bischof
17 篇 a.k. jain
17 篇 t. darrell
16 篇 g. healey
16 篇 bowyer kevin w.
16 篇 bischof horst
15 篇 m.j. black
15 篇 m. shah
15 篇 a. zisserman
15 篇 heung-yeung shum

语言

8,459 篇 英文
8 篇 其他
7 篇 中文
1 篇 土耳其文

检索条件"任意字段=1966 IEEE Computer Society Conference on Computer Vision and Pattern Recognition"

共 8475 条记录，以下是4671-4680 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：

Acceleration Strategies for Gaussian Mean-Shift Image Segmentation

Acceleration Strategies for Gaussian Mean-Shift Image Segmen...

引用

conference on computer vision and pattern recognition (CVPR)

作者： M.A. Carreira-Perpinan Department of Computer Science & Electrical Engineering OGI Oregon Health & Science University USA

Gaussian mean-shift (GMS) is a clustering algorithm that has been shown to produce good image segmentations (where each pixel is represented as a feature vector with spatial and range components). GMS operates by defining a Gaussian kernel density estimate for the data and clustering together points that converge to the same mode under a fixed-point iterative scheme. However, the algorithm is slow, since its complexity is O(kN2), where N is the number of pixels and k the average number of iterations per pixel. We study four acceleration strategies for GMS based on the spatial structure of images and on the fact that GMS is an expectation-maximisation (EM) algorithm: spatial discretisation, spatial neighbourhood, sparse EM and EM-Newton algorithm. We show that the spatial discretisation strategy can accelerate GMS by one to two orders of magnitude while achieving essentially the same segmentation; and that the other strategies attain speedups of less than an order of magnitude.

关键词： Acceleration Image segmentation Kernel Clustering algorithms Pixel Image converters Iterative algorithms Bandwidth computer science Equations

来源：评论

学校读者我要写书评

暂无评论

Dynamic Appearance Modeling for Human Tracking

Dynamic Appearance Modeling for Human Tracking

引用

conference on computer vision and pattern recognition (CVPR)

作者： Hwasup Lim O.I. Camps M. Sznaier V.I. Morariu Department of Electrical Engineering Pennsylvania State University University Park PA USA Department of Computer Science University of Maryland College Park MD USA

Dynamic appearance is one of the most important cues for tracking and identifying moving people. However, direct modeling spatio-temporal variations of such appearance is often a difficult problem due to their high dimensionality and nonlinearities. In this paper we present a human tracking system that uses a dynamic appearance and motion modeling framework based on the use of robust system dynamics identification and nonlinear dimensionality reduction techniques. The proposed system learns dynamic appearance and motion models from a small set of initial frames and does not require prior knowledge such as gender or type of activity. The advantages of the proposed tracking system are illustrated with several examples where the learned dynamics accurately predict the location and appearance of the targets in future frames, preventing tracking failures due to model drifting, target occlusion and scene clutter.

关键词： Humans Target tracking Nonlinear dynamical systems Predictive models computer science Robustness Histograms Educational institutions Biological system modeling Layout

来源：评论

学校读者我要写书评

暂无评论

"How many planar viewing surfaces are there in noncentral catadioptric cameras?" Towards singe-image localization of space lines

"How many planar viewing surfaces are there in noncentral ca...

引用

conference on computer vision and pattern recognition (CVPR)

作者： V. Caglioti S. Gasparini Dipartimento di Elettronica e Informazione Politecnico di Milano Milan Italy

In-door environments often contain several straight line segments. The 3D reconstruction of such environments can thus reduce to the localization of lines in the 3D space. Multi-view reconstruction requires the solution of the correspondence problem. The use of a single image to localize space lines is attractive, since the correspondence problem can be avoided. However, using a perspective camera (or a central one), a line can not be localized, since its viewing surface is planar, and hence it can contain infinite lines other than the correct one. In this paper we study the number of planar viewing surfaces for a general class of catadioptric cameras, constituted by an axial symmetric mirror and a perspective camera placed at generic relative position. We show that, under broad conditions, there is only a discrete set of planar viewing surfaces for the considered class of cameras. This result establishes a qualitative difference with respect to axial-symmetric cameras (e.g., catadioptric cameras constituted by an axial-symmetric mirror plus a perspective camera, whose viewpoint is constrained to be on the mirror axis), where an infinite set of planar viewing surfaces exists. Then, some conditions are derived for the localization of lines in the 3D space from single images. Preliminary experiments are also reported.

关键词： Cameras Mirrors Image reconstruction Surface reconstruction Image segmentation Layout Manufacturing computer society computer vision pattern recognition

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Appearance Model Approach for Model-based Articulated Object Tracking

An Adaptive Appearance Model Approach for Model-based Articu...

引用

conference on computer vision and pattern recognition (CVPR)

作者： A.O. Balan M.J. Black Department of Computer Science Brown University Providence RI USA

The detection and tracking of three-dimensional human body models has progressed rapidly but successful approaches typically rely on accurate foreground silhouettes obtained using background segmentation. There are many practical applications where such information is imprecise. Here we develop a new image likelihood function based on the visual appearance of the subject being tracked. We propose a robust, adaptive, appearance model based on the Wandering-Stable-Lost framework extended to the case of articulated body parts. The method models appearance using a mixture model that includes an adaptive template, frame-to-frame matching and an outlier process. We employ an annealed particle filtering algorithm for inference and take advantage of the 3D body model to predict selfocclusion and improve pose estimation accuracy. Quantitative tracking results are presented for a walking sequence with a 180 degree turn, captured with four synchronized and calibrated cameras and containing significant appearance changes and self-occlusion in each view.

关键词： Biological system modeling Humans Cameras Robustness Annealing Filtering algorithms Predictive models Legged locomotion computer science Object detection

来源：评论

学校读者我要写书评

暂无评论

Making a Long Video Short: Dynamic Video Synopsis

Making a Long Video Short: Dynamic Video Synopsis

引用

conference on computer vision and pattern recognition (CVPR)

作者： A. Rav-Acha Y. Pritch S. Peleg Computer Science and Engineering Hebrew University of Jerusalem Jerusalem Israel

The power of video over still images is the ability to represent dynamic activities. But video browsing and retrieval are inconvenient due to inherent spatio-temporal redundancies, where some time intervals may have no activity, or have activities that occur in a small image region. Video synopsis aims to provide a compact video representation, while preserving the essential activities of the original video. We present dynamic video synopsis, where most of the activity in the video is condensed by simultaneously showing several actions, even when they originally occurred at different times. For example, we can create a "stroboscopic movie", where multiple dynamic instances of a moving object are played simultaneously. This is an extension of the still stroboscopic picture. Previous approaches for video abstraction addressed mostly the temporal redundancy by selecting representative key-frames or time intervals. In dynamic video synopsis the activity is shifted into a significantly shorter period, in which the activity is much denser. Video examples can be found online in http://***/synopsis

关键词： Birds Videoconference Object detection Legged locomotion Displays Layout Video sequences computer science Power engineering and energy Image retrieval

来源：评论

学校读者我要写书评

暂无评论

Reconfigurable Streaming Architectures for Embedded Smart Cameras

Reconfigurable Streaming Architectures for Embedded Smart Ca...

引用

ieee computer society conference on computer vision and pattern recognition Workshops (CVPRW)

作者： S.M. Chai N. Bellas G. Kujawa T. Ziomek L. Dawson T. Scaminaci M. Dwyer D. Linzmeier Motorola Laboratories Embedded Systems Research

Smart cameras using FPGAs require an automation method to simplify the design process and to ensure both computation and memory performance are met. Reconfigurable logic allows exploration of different hardware accelerators and memory-hierarchy configurations based on application needs. This paper presents a streaming architecture template that is generated from high level program descriptions. A smart camera development platform, the software architecture, and demonstration template are also described.

关键词： Smart cameras Hardware computer architecture Field programmable gate arrays Application software computer vision Programming profession Control systems Process design Design optimization

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Empirical Study on Linear Subspace Methods for Facial Expression Analysis

A Comprehensive Empirical Study on Linear Subspace Methods f...

引用

ieee computer society conference on computer vision and pattern recognition Workshops (CVPRW)

作者： Caifeng Shan Shaogang Gong P.W. McOwan Department of Computer Science Queen''s Mary University of London London UK

Automatic facial expression analysis is a vital component of intelligent Human-computer Interaction (HCI). In this paper, we present a extensive empirical study on linear subspace methods for facial expression analysis. Locality Preserving Projections (LPP) and Orthogonal Neighborhood Preserving Projections (ONPP) are first time applied to facial expression analysis. We systematically examine a number of linear subspace methods, and show that, in our comparative studies, the Supervised LPP (SLPP) is superior in supervised methods, while ONPP performs best in unsupervised learning.

关键词： Linear discriminant analysis Principal component analysis Independent component analysis Human computer interaction computer science Unsupervised learning Learning systems Neural networks Bayesian methods Support vector machines

来源：评论

学校读者我要写书评

暂无评论

An Integrated Model of Top-Down and Bottom-Up Attention for Optimizing Detection Speed

An Integrated Model of Top-Down and Bottom-Up Attention for ...

引用

conference on computer vision and pattern recognition (CVPR)

作者： V. Navalpakkam L. Itti Department of Computer Science Neuroscience Graduate Program University of Southern California USA

Integration of goal-driven, top-down attention and image-driven, bottom-up attention is crucial for visual search. Yet, previous research has mostly focused on models that are purely top-down or bottom-up. Here, we propose a new model that combines both. The bottom-up component computes the visual salience of scene locations in different feature maps extracted at multiple spatial scales. The topdown component uses accumulated statistical knowledge of the visual features of the desired search target and background clutter, to optimally tune the bottom-up maps such that target detection speed is maximized. Testing on 750 artificial and natural scenes shows that the model’s predictions are consistent with a large body of available literature on human psychophysics of visual search. These results suggest that our model may provide good approximation of how humans combine bottom-up and top-down cues such as to optimize target detection speed.

关键词： Object detection Layout Biological system modeling Humans Face detection Acceleration Robots Navigation Surveillance computer science

来源：评论

学校读者我要写书评

暂无评论

A Comparison of 3D Biometric Modalities

A Comparison of 3D Biometric Modalities

引用

ieee computer society conference on computer vision and pattern recognition Workshops (CVPRW)

作者： D.L. Woodard T.C. Faltemier Ping Yan P.J. Flynn K.W. Bowyer Department of Computer Science and Engineering University of Notre Dame Notre Dame IN USA

Recently, researchers have focused on the use of threedimensional data as a source of distinguishing features for personal identification. In this paper, the recognition performance of three three-dimensional biometric modalities (face, ear, and finger surface) is compared. In addition, we combine the modalities in an attempt to improve overall recognition performance. The Iterative Closest Point (ICP) algorithm and root mean square (RMS) registration error are used to measure match quality in each case. The experimental results using a dataset of multi-modal biometric samples collected from a group of 85 individuals are presented.

关键词： Biometrics Ear Fingers Iterative closest point algorithm Face recognition Iterative algorithms Lighting Principal component analysis Image segmentation Image recognition

来源：评论

学校读者我要写书评

暂无评论

Selecting Principal Components in a Two-Stage LDA Algorithm

Selecting Principal Components in a Two-Stage LDA Algorithm

引用

conference on computer vision and pattern recognition (CVPR)

作者： Manli Zhu A.M. Martinez Department of Electrical and Computer Engineering Ohio State Uinversity Atlanta OH USA

Linear Discriminant Analysis (LDA) is a well-known and important tool in pattern recognition with potential applications in many areas of research. The most famous and used formulation of LDA is that given by the Fisher-Rao criterion, where the problem reduces to a simple simultaneous diagonalization of two symmetric, positive-definite matrices, A and B; i.e. B^-1 AV = VA. Here, A defines the metric to be maximized, while B defines the metric to be minimized. However, when B has near-zero eigenvalues, the Fisher-Rao criterion gets dominated by these. While this works well when such small variances describe vectors where most of the discriminant information is, the results will be incorrect when these small variances are caused by noise. Knowing which of these near-zero values are to be used and which need to be eliminated is a challenging yet fundamental task in LDA. This paper presents a criterion for the selection of those vectors of B that are best for classification. The proposed solution is based on a simple factorization of B^-1 A that permits the re-ordering of the eigenvectors of B without the need to effect the end result. This allows us to readily eliminate the noisy vectors while keeping the most discriminant ones. A theoretical basis for these results is presented along with extensive experimental results to validate the claims.

关键词： Linear discriminant analysis Eigenvalues and eigenfunctions Symmetric matrices Covariance matrix Scattering Principal component analysis pattern recognition Application software Vectors Instruments

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500页 << < 464 465 466 467 468 469 470 471 472 473 > >>

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：