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

1,926 篇 会议
236 册 图书
24 篇 期刊文献

馆藏范围

2,185 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

1,605 篇 工学
- 1,333 篇 计算机科学与技术...
- 466 篇 软件工程
- 250 篇 电气工程
- 235 篇 机械工程
- 186 篇 光学工程
- 178 篇 信息与通信工程
- 119 篇 控制科学与工程
- 96 篇 生物工程
- 62 篇 生物医学工程（可授...
- 41 篇 仪器科学与技术
- 38 篇 电子科学与技术（可...
- 30 篇 化学工程与技术
- 21 篇 安全科学与工程
- 18 篇 材料科学与工程（可...
- 15 篇 交通运输工程
- 13 篇 建筑学
444 篇 理学
- 257 篇 物理学
- 202 篇 数学
- 110 篇 生物学
- 57 篇 统计学（可授理学、...
- 22 篇 化学
228 篇 医学
- 200 篇 临床医学
- 26 篇 基础医学(可授医学...
- 22 篇 特种医学
137 篇 管理学
- 83 篇 图书情报与档案管...
- 60 篇 管理科学与工程(可...
- 19 篇 工商管理
27 篇 艺术学
- 27 篇 设计学（可授艺术学...
16 篇 农学
- 15 篇 作物学
15 篇 法学
- 13 篇 社会学
9 篇 教育学
7 篇 经济学
5 篇 文学
5 篇 军事学

主题

320 篇 computer vision
286 篇 pattern recognit...
166 篇 artificial intel...
119 篇 feature extracti...
117 篇 computer imaging...
101 篇 image processing...
82 篇 face recognition
68 篇 training
61 篇 object detection
60 篇 image segmentati...
57 篇 computer applica...
54 篇 deep learning
51 篇 robustness
47 篇 computer graphic...
46 篇 cameras
45 篇 visualization
43 篇 semantics
38 篇 object recogniti...
37 篇 shape
36 篇 information syst...

机构

89 篇 univ chinese aca...
67 篇 chinese acad sci...
59 篇 national laborat...
56 篇 chinese acad sci...
50 篇 univ chinese aca...
36 篇 chinese univ hon...
36 篇 university of ch...
31 篇 institute of aut...
27 篇 chinese acad sci...
25 篇 school of artifi...
23 篇 univ sci & techn...
22 篇 chinese academy ...
18 篇 chinese acad sci...
17 篇 chinese univ hon...
16 篇 chinese acad sci...
16 篇 univ chinese aca...
15 篇 national laborat...
15 篇 computer vision ...
14 篇 tsinghua univers...
14 篇 department of in...

作者

32 篇 wang xiaogang
29 篇 lu hanqing
28 篇 tan tieniu
28 篇 wang jinqiao
23 篇 li stan z.
22 篇 pal umapada
21 篇 huang kaiqi
21 篇 lei zhen
21 篇 qiao yu
19 篇 tieniu tan
19 篇 hu weiming
18 篇 tang xiaoou
17 篇 xilin chen
15 篇 wang liang
15 篇 chen xilin
15 篇 cheng jian
14 篇 liu jing
14 篇 tang ming
13 篇 xiaoou tang
13 篇 shiguang shan

语言

2,165 篇 英文
19 篇 中文
7 篇 其他
1 篇 土耳其文

检索条件"任意字段=7th Chinese Conference on Pattern Recognition and Computer Vision"

共 2186 条记录，以下是2161-2170 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：

High-level spatial modeling in convolutional neural network with application to pedestrian detection

High-level spatial modeling in convolutional neural network ...

引用

Canadian conference on Electrical and computer Engineering (CCECE)

作者： Feng Liu Yongzhen Huang Wankou Yang Changyin Sun School of Automation. Southeast University Nanjing China Key Lab of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing China Key Lab of Child Development and Learning Science of Ministry of Education. Southeast University Nanjing China

ISBN: (纸本)9781479958306

Convolutional neural network (CNN) has achieved great success in many vision tasks. A key to this success is its ability to powerful automatically learns both high-level and low-level features. In general, low-level features have a small size of receptive fields and appear multiple times in different locations of objects, while high-level semantic features have a relatively large size of receptive fields and only appear once in a specific location of objects. However, traditional CNN treats these two kinds of features in the same manner, i.e., learning them by the convolution operation, which can be approximately considered as cumulating the probabilities that a feature appears in different locations. this strategy is reasonable for low-level features but not for high-level semantic ones, especially in the case of pedestrian detection, where a local feature can be shared by different locations but a semantic part, e.g., a head, only appears once for a human. To jointly model the spatial structure and appearance of high-level semantic features, we propose a new module to learn spatially weighted max pooling in CNN. the proposed method is evaluated on several pedestrian detection databases and the experimental results show that it achieves much better performance than traditional CNN.

关键词： Convolution Semantics Kernel Deformable models Computational modeling Feature extraction Training

来源：评论

学校读者我要写书评

暂无评论

chinese Native Dog Breed Classification Method based on Improved ResNet

Chinese Native Dog Breed Classification Method based on Impr...

引用

International conference on Information and computer Technologies (ICICT)

作者： Xinhua Zhang Chenwang Shen Jiaxi Xu Fenghao Yuan Chaofan Li Xu Liu University of Chinese Academy of Sciences Beijing China Chinese Academy of Sciences Shenyang Institute of Computing Technology Shenyang China School of Information Engineering Nanjing Xiaozhuang University Nanjing China Department of Computer Engineering Jinling Institute of Technology Nanjing China

ISBN: (数字)9798350385625

ISBN: (纸本)9798350385632

Dog classification has a wide range of applications in computer vision and zoology. However, traditional deep learning methods face challenges in classifying chinese native dog breeds due to the limitations and uniqueness of sample data. this paper proposes a classification method for domestic local dog breeds based on an improved ResNet (Residual Network). the model employs ResNet50 as the backbone network. By adjusting the fully connected layer to the Sigmoid output function and the BCELoss loss function, the misclassification probability of unseen categories is effectively reduced. Initially, crawler technology was utilized to obtain image data for nine types of native dogs, which were then preprocessed. Subsequently, these nine dog classification tasks were categorized into two groups. For each category, an improved ResNet was trained independently to obtain two distinct models. Finally, the two models were tested using multithreaded parallel techniques to compare their outputs and determine the most suitable dog breed classification result. Results demonstrate that the proposed algorithm performs well in the chinese native dog breed classification task. Compared with the unimproved model without parallel technology and the model using parallel technology but without improvement, the accuracy improved from 93.8% and 94.5% to 96.4%. Additionally, precision, recall, and F1-score reached 96.7%, 96.4%, and 96.5%, respectively. these findings fully confirm the effectiveness of the algorithm. this study provides a robust solution to promote the protection and research of indigenous dog breeds in China.

关键词： Training Adaptation models Computational modeling Neural networks Zoology Dogs Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

A CMOS Charge Pump with a Novel Structure in PLL

A CMOS Charge Pump with a Novel Structure in PLL

引用

2004 7th International conference on Solid-State and Integrated Circuits Technology（ICSICT 2004）

作者： Zhang Tao~(*1,3),Zou Xuecheng~(1,2),and Shen Xubang~(1,4) 1 Institute of pattern recognition and Artifical Intelligence,Huazhong Univ.of Sci.& Tech.,Wuhan 430074,China. 2 Department of Electronic Science and Technology,Huazhong Univ.of Sci.& Tech.,Wuhan 430074,China 3 Institute of Information,Wuhan Univ.of Sci.& Tech.,Wuhan 430081,China. 4 Xi'an Microelectronic Technology Institute,Xi'an 710054,China.

A novel structure for a charge pump circuit is proposed,in which the current follow technology is used to make perfect current matching characteristics,and two differential inverters are implanted to increase the speed of charge *** results,with 1silicon 0.25um 2.5V CMOS mixed signal process,show the good current matching characteristics regardless of the charge pump output voltages.

关键词： A CMOS Charge Pump with a Novel Structure in PLL

来源：评论

学校读者我要写书评

暂无评论

On improved graph-based alternative wiring scheme for multi-level logic optimization

On improved graph-based alternative wiring scheme for multi-...

引用

IEEE International conference on Electronics, Circuits and Systems (ICECS)

作者： Y.-L. Wu C.-N. Sze C.-C. Cheung H. Fan Chinese University of Hong Kong New Territories Hong Kong China Department of Computer Science University of Victoria Victoria BC Canada

ISBN: (纸本)0780365429

A much extended graph-based alternative wiring (GBAW) scheme to identify alternative wires in multilevel logic with promising results is presented. By modeling subsets of circuits as minimal graphs and applying purely graph-based local pattern search technique, we have found more than 40 graph patterns which contain alternative wires within 2-edge distance from the target wire. Applying proper grouping technique for the similar patterns, the complexity of our rewiring technique can be reduced. Experimental results on MCNC benchmarks show that our technique is much faster than the ATPG-based technique RAMBO with competitive number of alternative wires found. With this augmented pattern family of alternative wires, we are able to find 30% more alternative wires compared to RAMBO with 75 times speedup on average. We applied GBAW in logic minimization as a perturbation engine and simplify the target circuit by SIS algebraic operations. Results show a further reduction of 11.1% in literal count compared to applying algebraic operations alone.

关键词： Wiring Wires Automatic test pattern generation Circuit testing computer science Logic functions Logic circuits Minimization Engines Circuit optimization

来源：评论

学校读者我要写书评

暂无评论

Pedestrian Detection in Infrared Images Using HOG,LBP,Gradient Magnitude and Intensity Feature Channels

Pedestrian Detection in Infrared Images Using HOG,LBP,Gradie...

引用

17th International IEEE conference on Intelligent Transportation Systems & the Asia-Pacific Council on Systems Engineering conference 2014

作者： Raluca Brehar Sergiu Nedevschi the Image Processing and Pattern Recognition Group Computer Science DepartmentTechnical University of Cluj-Napoca

Recent work in monocular pedestrian detection is trying to improve the execution time while keeping the accuracy as high as possible.A popular and successful approach for monocular intensity pedestrian detection is based on the approximation（instead of computation） of image features for multiple scales based on the features computed on set of predefined *** port this idea to the infrared *** contributions reside in the combination of four channel features,namely infrared,histogram of gradient orientations,normalized gradient magnitude and local binary patterns with the objective of detecting pedestrians for night vision applications dealing with far infrared *** scale feature computation is done by feature *** contribution is the study of different formulations for Local Binary patterns like uniform patterns and rotation invariant patterns and their effect on detection *** detection speed is also boosted by the aid of a fast morphological based region of interest *** vary the number of approximated scales per octave and study the impact on execution time and accuracy.A reasonable result hits a speed of 18 fps with a log average miss rate of 39%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Information Bottleneck Based Target Tracking Algorithm

Information Bottleneck Based Target Tracking Algorithm

引用

International conference on Information Systems and computer Aided Education (ICISCAE)

作者： Dan Wang Feng Li Jun Jia Institute of Measurement and Testing Technology Chinese Flight Test Establishment Xi'an China

ISBN: (数字)9798350350760

ISBN: (纸本)9798350350777

Object tracking plays a crucial role in computer vision and finds extensive applications in various areas such as video surveillance, autonomous driving, and intelligent security systems. However, existing target tracking methods is deficient in handling information redundancy, and extracting key information, which affects the accuracy and robustness of tracking. In this paper, we propose a new method of target tracking that combines the information bottleneck theory, which optimizes the information transmission path and extracts key information related to the target tracking task by introducing an information bottleneck module in the tracking model. the information bottleneck approach can be used to extract robust feature representations that help the tracking algorithm remain stable and accurate in the face of target changes, occlusions and noise. the method is combined with Visual Transformer (ViT) to enhance the model's ability to adapt to targets in complex scenes. Experimental findings indicate that the proposed method delivers outstanding performance across multiple public datasets. With significant improvement in accuracy and robustness compared to existing methods, the research in this paper provides new ideas and methods to improve the performance of target tracking algorithms.

关键词： Deep learning Adaptation models Visualization Target tracking Accuracy Information processing Feature extraction Robustness Data mining Object tracking

来源：评论

学校读者我要写书评

暂无评论

An Efficient Algorithm for 3-D Interconnect Capacitance Extraction Considering the Floating Dummy-Fills

An Efficient Algorithm for 3-D Interconnect Capacitance Extr...

引用

2004 7th International conference on Solid-State and Integrated Circuits Technology（ICSICT 2004）

作者： Wenjian Yu~*,Mengsheng Zhang,Zeyi Wang Dept.of computer Science & Technology,Tsinghua University,Beijing 100084,China

the insertion of dummy metals is necessary to reduce the pattern-dependent variations of the dielectric thickness in the CMP *** makes conventional tools of capacitance extraction exhibit prohibitive calculation *** paper presents an efficient method for 3-D capacitance extraction with taking the floating dummies into *** on the QMM-accelerated BEM,our method inherits high computational speed while considering the floating conditions and using a new *** some typical structures including floating dummies,our method shows high accuracy and over 1000x speed-up over Raphael,about 10x speed-up over the method in Ref[5].

关键词： An Efficient Algorithm for 3-D Interconnect Capacitance Extraction Considering the Floating Dummy-Fills

来源：评论

学校读者我要写书评

暂无评论

Virtual Reality based Intelligent Vehicle Modeling in Driving SIMULATION System

Virtual Reality based Intelligent Vehicle Modeling in Drivin...

引用

the 7th International conference on computer-Aided Industrial Design and Conceptual Design (CAID&CD’2006)

作者： He Han-wu, deputy dean of Faculty of Electromechanical Engineering, GuangDong University of Technology Lu Yong-ming, graduate student of Faculty of Electromechanical Engineering, GuangDong University of Technology Lou Yan,Faculty of Electromechanical Engineering, GuangDong University of Technology

the driving intelligence of the virtual intelligent vehicle in the driving simulation system is crucial to the system's sense of reality and the reliability of the experiment. this paper focuses on the features and functionality of the virtual intelligent vehicle in driving simulation system. Intelligent vehicle should first distinguish the roadway network in order to drive correctly along a certain path. then the intelligent vehicle should be able to obtain the traffic information efficiently and to execute the decision-making process to response to the changing driving environment. this paper describes a method to construct the virtual intelligent vehicle using database technology and the collision detection algorithm. the experiment result illustrates that the virtual intelligent vehicles in virtual traffic environment can simulate the human vision genuinely and exhibit human-like driving behavior. the virtual intelligent vehicle can still keep the correctness and the efficiency in a comparatively complex traffic environment, also the stability of the system is satisfied.

关键词： intelligent vehicle, driving simulation, virtual reality

来源：评论

学校读者我要写书评

暂无评论

A Study of Automatic recognition of three Rodent Species: Applying Mathematic Morphological Characters of Skull

A Study of Automatic Recognition of Three Rodent Species: Ap...

引用

International conference on Bioinformatics and Biomedical Engineering (ICBBE)

作者： Xiongfeng Yuan Lingwang Gao Xiaoguang Ma Xin Zhang Tianyu Guo IPMist Laboratory College of Agriculture and Biotechnology China Agricultural University Beijing China College of Biological Sciences and Biotechnology Beijing Forestry University Beijing China Institute of Health Quarantine Chinese Academy of Inspection and Quarantine Sciences Beijing China Beijing Entry and Exit Inspection and Quarantine Bureau Beijing China

Based on the digital image processing technology, this study applied the mathematic morphological character extracting software to get exterior shape feature from skull of three rodent species (Meriones unguiculatus, Microtus brandti and Rattus norvegicus). Via SPSS 13.0 for Windows, the data was explored for automatic recognition. 22 mathematic morphological characters were extracted and the results of univariate two-factor analysis of variance showed that all the features can provide a reliable foundation for a rapid automatic recognition, though failed to distinguish gender. Stepwise discriminatory method was applied and 9 parameters were selected for rodent identification: short axis(X1), perimeter(X2), eccentricity(X3), sphericity(X4), bump area(X5), paraxial area of enclosing rectangle(X6), hu1(X7), hu2(X8), hu3(X9). With the selected parameters, two standardized canonical discriminant functions were found: Y1 = 8.014X1 - 3.585X2 + 9.682X3 - 2.504X4 + 7.823X5 - 10.948X6 - 0.896X7 + 12.471X8 - 0.781X9; Y2 = 2.593X1 + 0.242X2 + 6.323X3 + 0.509X4 - 1.219X5 - 2.898X6 - 4.226X7 + 7.674X8 + 0.785X9. these two discriminant functions worked well for identification, the accuracy rate was 100%.

关键词： Morphology Rodents Feature extraction Digital images computer vision

来源：评论

学校读者我要写书评

暂无评论

Engineering of intelligent systems : 14th International conference on Industrial and Engineering App

引用

2001年

作者： International conference on Industrial & Engineering Applications of Artificial Intelligence & Exper

来源：内蒙古大学图书馆图书评论

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219页 << < 210 211 212 213 214 215 216 217 218 219 > >>

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：