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

192 篇 会议
7 册 图书
1 篇 期刊文献

馆藏范围

200 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

140 篇 工学
- 117 篇 计算机科学与技术...
- 50 篇 软件工程
- 28 篇 电气工程
- 16 篇 光学工程
- 16 篇 信息与通信工程
- 8 篇 生物工程
- 7 篇 电子科学与技术（可...
- 7 篇 控制科学与工程
- 5 篇 机械工程
- 5 篇 仪器科学与技术
- 4 篇 生物医学工程（可授...
- 3 篇 力学（可授工学、理...
- 3 篇 化学工程与技术
- 2 篇 动力工程及工程热...
- 2 篇 测绘科学与技术
- 2 篇 交通运输工程
- 2 篇 核科学与技术
56 篇 理学
- 29 篇 数学
- 27 篇 物理学
- 9 篇 生物学
- 9 篇 统计学（可授理学、...
- 3 篇 化学
- 3 篇 系统科学
- 2 篇 大气科学
- 2 篇 海洋科学
- 2 篇 地球物理学
44 篇 医学
- 40 篇 临床医学
- 4 篇 特种医学
6 篇 管理学
- 6 篇 图书情报与档案管...
2 篇 法学
- 2 篇 社会学
2 篇 农学
1 篇 文学
1 篇 艺术学

主题

51 篇 pattern recognit...
21 篇 object recogniti...
11 篇 training
9 篇 semantics
8 篇 face recognition
7 篇 image segmentati...
7 篇 neural networks
6 篇 artificial intel...
5 篇 object detection
5 篇 deep learning
5 篇 gesture recognit...
5 篇 predictive model...
5 篇 image recognitio...
4 篇 task analysis
4 篇 pattern matching
4 篇 benchmark testin...
4 篇 correlation
4 篇 computer vision
3 篇 noise measuremen...
3 篇 computer graphic...

机构

4 篇 univ freiburg de...
3 篇 school of artifi...
3 篇 nlpr & cebsit ca...
2 篇 cas ctr excellen...
2 篇 university of sc...
2 篇 university leipz...
2 篇 image and patter...
2 篇 tal education gr...
2 篇 univ erlangen nu...
2 篇 visual learning ...
2 篇 institute of inf...
2 篇 heidelberg colla...
2 篇 univ chinese aca...
1 篇 university of ka...
1 篇 katholieke unive...
1 篇 centre for resea...
1 篇 fgan-fom researc...
1 篇 electrical measu...
1 篇 ecole polytech f...
1 篇 univ erlangen nu...

作者

6 篇 burkhardt hans
5 篇 schnörr christop...
5 篇 ney hermann
4 篇 keysers daniel
4 篇 schiele bernt
4 篇 cremers daniel
4 篇 ran he
3 篇 ronneberger olaf
3 篇 fritz mario
3 篇 rosenhahn bodo
3 篇 weickert joachim
3 篇 reisert marco
2 篇 fei yin
2 篇 haxhimusa yll
2 篇 goebel peter mic...
2 篇 villmann thomas
2 篇 mochalova anasta...
2 篇 hornegger joachi...
2 篇 xu-yao zhang
2 篇 franke uwe

语言

200 篇 英文

检索条件"任意字段=25th Pattern Recognition Symposium of the German-Association-for-Pattern-Recognition"

共 200 条记录，以下是101-110 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：

pattern type specific modeling and correction methodology at high NA and off-axis illumination

Pattern type specific modeling and correction methodology at...

引用

25th Annual BACUS symposium on Photomask Technology

作者： Suh, Sungsoo Kang, Young-Seog Kim, In-Sung Woo, Sang-Gyun Cho, Hanku Moon, Joo-Tae Memory Division Process Development Team Samsung Electronics Co. Ltd. San #24 Nongseo-Ri Yong-in City Gyonggi-Do 449-711 Korea Republic of

In this work, a potential drawback of simultaneously representing a set of data that contains line-ends, isobar, block structure, and pitch linearity intensity signal using a single representative model have been resolved. In a typical model OPC procedure, a set of pattern data representative of OPC layout is calibrated using a single representative model, and this model may be a scalar or a vector at constant threshold or variable threshold. Nevertheless, traditional methodology treats a set of pattern data as a whole believing that it provides a best representation of a more complicated environment. In this study, pattern type specific models are used to perform optical proximity correction. this multi-model approach distinguishes each pattern type and specified pitch range a priori to obtaining intensity signal by checking for neighboring segment. Based on this search result, its segment is classified into a pattern type and subgroup, and then, pattern specific models are applied. this approach provides improved calibration result for strong off-axis illumination and optical proximity correction result which will be difficult to achieve with a single representative model.

关键词： pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Synergy-based learning of facial identity

Synergy-based learning of facial identity

引用

Joint 34th symposium of the german association for pattern recognition, DAGM 2012 and 36th symposium of the Austrian association for pattern recognition, OAGM 2012

作者： Köstinger, Martin Roth, Peter M. Bischof, Horst Institute for Computer Graphics and Vision Graz University of Technology Austria

ISBN: (纸本)9783642327162

In this paper we address the problem that most face recognition approaches neglect that faces share strong visual similarities, which can be exploited when learning discriminative models. Hence, we propose to model face recognition as multi-task learning problem. this enables us to exploit both, shared common information and also individual characteristics of faces. In particular, we build on Mahalanobis metric learning, which has recently shown good performance for many computer vision problems. Our main contribution is twofold. First, we extend a recent efficient metric learning algorithm to multi-task learning. the resulting algorithm supports label-incompatible learning which allows us to tap the rather large pool of anonymously labeled face pairs also for face identification. Second, we show how to learn and combine person specific metrics for face identification improving the classification power. We demonstrate the method for different face recognition tasks where we are able to match or slightly outperform state-of-the-art multi-task learning approaches. © 2012 Springer-Verlag.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Maximum entropy and Gaussian models for image object recognition

Maximum entropy and Gaussian models for image object recogni...

引用

24th symposium of the german pattern recognition association, DAGM 2002

作者： Keysers, Daniel Och, Franz Josef Ney, Hermann Lehrstuhl für Informatik VI Computer Science Department RWTH Aachen D-52056 Aachen Germany

ISBN: (纸本)354044209X

the principle of maximum entropy is a powerful framework that can be used to estimate class posterior probabilities for pattern recognition tasks. In this paper, we show how this principle is related to the discriminative training of Gaussian mixture densities using the maximum mutual information criterion. this leads to a relaxation of the constraints on the covariance matrices to be positive (semi-) definite. thus, we arrive at a conceptually simple model that allows to estimate a large number of free parameters reliably. We compare the proposed method with other state-of-the-art approaches in experiments with the well known US Postal Service handwritten digits recognition task. © Springer-Verlag Berlin Heidelberg 2002.

关键词： Covariance matrix

来源：评论

学校读者我要写书评

暂无评论

Active learning of ensemble classifiers for gesture recognition

Active learning of ensemble classifiers for gesture recognit...

引用

Joint 34th symposium of the german association for pattern recognition, DAGM 2012 and 36th symposium of the Austrian association for pattern recognition, OAGM 2012

作者： Schumacher, J. Sakič, D. Grumpe, A. Fink, Gernot A. Wöhler, C. Lehrstuhl Informatik XII Technische Universität Dortmund Germany Image Analysis Group Technische Universität Dortmund Germany

ISBN: (纸本)9783642327162

In this study we consider the classification of emblematic gestures based on ensemble methods. In contrast to HMM-based approaches processing a gesture as a whole, we classify trajectory segments comprising a fixed number of sampling points. We propose a multi-view approach in order to increase the diversity of the classifiers across the ensemble by applying different methods for data normalisation and dimensionality reduction and by employing different classifier types. A genetic search algorithm is used to select the most successful ensemble configurations from the large variety of possible combinations. In addition to supervised learning, we make use of both labelled and unlabelled data in an active learning framework in order to reduce the effort required for manual labelling. In the supervised learning scenario, recognition rates per moment in time of more than 86% are obtained, which is comparable to the recognition rates obtained by a HMM approach for complete gestures. the active learning scenario yields recognition rates in excess of 80% even when only a fraction of 20% of all training samples are used. © 2012 Springer-Verlag.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Evaluation of confidence measures for on-line handwriting recognition

Evaluation of confidence measures for on-line handwriting re...

引用

24th symposium of the german pattern recognition association, DAGM 2002

作者： Brakensiek, Anja Kosmala, Andreas Rigoll, Gerhard Dept. of Computer Science Faculty of Electrical Engineering Gerhard-Mercator-University Duisburg D-47057 Duisburg Germany Inst. for Human-Machine Communication Technical University of Munich D-80290 Munich Germany

ISBN: (纸本)354044209X

In this paper a writer-independent on-line handwriting recognition system is described comparing the effectiveness of several confidence measures. Our recognition system for single german words is based on Hidden Markov Models (HMMs) using a dictionary. We compare the ratio of rejected words to misrecognized words using four different confidence measures: One depends on the frame-normalized likelihood, the second on a garbage model, the third on a two-best list and the fourth on an unconstrained character recognition. the rating of recognition results is necessary for an unsupervised retraining or adaptation of recognition systems as well as for a user friendly human-computer interaction avoiding excessive call backs. © Springer-Verlag Berlin Heidelberg 2002.

关键词： Character recognition

来源：评论

学校读者我要写书评

暂无评论

Hands tracking from frontal view for vision-based gesture recognition

Hands tracking from frontal view for vision-based gesture re...

引用

24th german association for pattern recognition symposium, DAGM 2002

作者： Zieren, Jörg Unger, Nils Akyol, Suat Ahornst. 55 Aachen52074 Germany

ISBN: (纸本)354044209X

We present a system for tracking the hands of a user in a frontal camera view for gesture recognition purposes. the system uses multiple cues, incorporates tracing and prediction algorithms, and applies probabilistic inference to determine the trajectories of the hands reliably even in case of hand-face overlap. A method for assessing tracking quality is also introduced. Tests were performed with image sequences of 152 signs from german Sign Language, which have been segmented manually beforehand to offer a basis for quantitative evaluation. A hit rate of 81.1% was achieved on this material. © Springer-Verlag Berlin Heidelberg 2002.

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

Electron beam pattern generator sensitivity to target potentials

Electron beam pattern generator sensitivity to target potent...

引用

25th Annual BACUS symposium on Photomask Technology

作者： Ruan, Junru Hartley, John College of Nanoscale Science and Engineering University at Albany SUNY Albany NY 12203

Electrostatic chucking is the plan of record for mask clamping in Extreme Ultraviolet (EUV) lithography. In order to minimize mask distortion it is recommended by the EUV lithography community that identical electrostatic chucks be used in the mask patterning and metrology tools. the high voltages used in electrostatic chucking have the potential to establish voltages on the mask surface, which may influence the electron optical characteristics of the pattern generator to the detrimental imaging of the pattern. To understand the relationship between image degradation and mask surface voltages, we are modeling the interaction between mask potential and electron beam columns. the first system modeled consists entirely of electrostatic elements, and the second one is a more traditional electron beam lithography system with electrostatic and magnetic components. All of the working parameters of the systems were fixed to establish optimal imaging on the grounded mask. We then altered the potential on the mask surface and determined the impact on focus and deflection errors. the simulation results establish the relationship between the mask potential, focus and deflection errors. Detailed data of focus deflection error versus mask potential will be presented for these electron beam column configurations. When combined with ITRS roadmap specifications, these results set boundaries on mask and chuck configurations as well as grounding schemes. the results are also applicable to charged particle maskless lithography schemes as well as issues of substrate charging in both pattern generators and metrology tools.

关键词： pattern recognition

来源：评论

学校读者我要写书评

暂无评论

the use of deep learning to highlight the shape of geophysical signals 25

The use of deep learning to highlight the shape of geophysic...

引用

25th International symposium On Atmospheric and Ocean Optics - Atmospheric Physics

作者： Mochalov, Vladimir Mochalova, Anastasia RAS FEB Inst Cosmophys Res & Radio Wave Propagat Mirnaya Str 7 Paratunka 684034 Kamchatka Regio Russia

ISBN: (数字)9781510631694

ISBN: (纸本)9781510631694

During analyzing of geophysical data, the problem of highlighting a form of geophysical signals often appears. In this work, it is proposed to use deep learning, which is currently one of the top priorities in the field of artificial intelligence and machine learning. the samples of geophysical signals, as well as the generated samples of signals by their mathematical models and typical examples of forms, act as a training dataset for deep neural network. End-to-end demonstration examples of the highlighting of reflection traces from different layers of the ionosphere in the ionograms, as well as the highlighting of whistler forms in the VLF spectrograms are presented.

关键词： deep learning geophysical signals pattern recognition shape shape detection ionograms VLF whistlers

来源：评论

学校读者我要写书评

暂无评论

Fuzzy modeling based recognition of multi-font numerals

引用

25th symposium of the german association for pattern recognition, DAGM 2003

作者： Hanmandlu, Madasu Yusof, Mohd Hafizuddin Mohd Madasu, Vamsi Krishna Dept. of Electrical Engineering I.I.T. Delhi Hauz Khas New Delhi110016 India Multimedia University CyberjayaSelangor D.E.64100 Malaysia School of Information Technology and Electrical Engineering University of Queensland QLD4072 Australia

ISBN: (纸本)3540408614

In this paper, we present a new scheme for off-line recognition of multi-font numerals using the Takagi-Sugeno (TS) model. In this scheme, the binary image of a character is partitioned into a fixed number of sub-images called boxes. the features consist of normalized vector distances (γ) from each box. Each feature extracted from different fonts gives rise to a fuzzy set. However, when we have a small number of fonts as in the case of multi-font numerals, the choice of a proper fuzzification function is crucial. Hence, we have devised a new fuzzification function involving parameters, which take account of the variations in the fuzzy sets. the new fuzzification function is employed in the TS model for the recognition of multi-font numerals. © Springer-Verlag Berlin Heidelberg 2003.

关键词： Fuzzy sets

来源：评论

学校读者我要写书评

暂无评论

Riemannian SOS-Polynomial Normalizing Flows 1

引用

42nd german Conference on pattern recognition, DAGM GCPR 2020 held in parallel with 25th International symposium on Vision, Modeling, and Visualization, VMV 2020 and 10th Eurographics Workshop on Visual Computing for Biology and Medicine, VCBM 2020

作者： Schwarz, Jonathan Draxler, Felix Köthe, Ullrich Schnörr, Christoph Heidelberg Collaboratory for Image Processing Heidelberg University Heidelberg Germany Image and Pattern Analysis Group Heidelberg University Heidelberg Germany Visual Learning Lab Heidelberg University Heidelberg Germany

ISBN: (数字)9783030712785

ISBN: (纸本)9783030712778

Sum-of-Squares polynomial normalizing flows have been proposed recently, without taking into account the convexity property and the geometry of the corresponding parameter space. We develop two gradient flows based on the geometry of the parameter space of the cone of SOS-polynomials. Few proof-of-concept experiments using non-Gaussian target distributions validate the computational approach and illustrate the expressiveness of SOS-polynomial normalizing flows. © 2021, Springer Nature Switzerland AG.

关键词： Polynomials

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20页 << < 7 8 9 10 11 12 13 14 15 16 > >>

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：