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

352 篇 会议
37 册 图书
5 篇 期刊文献

馆藏范围

394 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

254 篇 工学
- 207 篇 计算机科学与技术...
- 88 篇 软件工程
- 52 篇 电气工程
- 48 篇 信息与通信工程
- 28 篇 控制科学与工程
- 22 篇 生物工程
- 18 篇 生物医学工程（可授...
- 14 篇 光学工程
- 9 篇 电子科学与技术（可...
- 8 篇 仪器科学与技术
- 6 篇 安全科学与工程
- 5 篇 化学工程与技术
- 3 篇 机械工程
- 3 篇 材料科学与工程（可...
79 篇 理学
- 43 篇 数学
- 22 篇 生物学
- 20 篇 物理学
- 10 篇 统计学（可授理学、...
- 6 篇 化学
- 4 篇 系统科学
52 篇 医学
- 50 篇 临床医学
- 10 篇 基础医学(可授医学...
- 5 篇 药学(可授医学、理...
- 5 篇 特种医学
- 4 篇 中西医结合
33 篇 管理学
- 18 篇 图书情报与档案管...
- 15 篇 管理科学与工程(可...
- 7 篇 工商管理
8 篇 法学
- 6 篇 社会学
7 篇 艺术学
- 6 篇 设计学（可授艺术学...
2 篇 经济学
2 篇 农学
1 篇 教育学
1 篇 军事学

主题

98 篇 pattern recognit...
24 篇 feature extracti...
22 篇 machine learning
18 篇 affective comput...
16 篇 artificial intel...
16 篇 computer imaging...
14 篇 deep learning
14 篇 emotion recognit...
12 篇 neural networks
11 篇 support vector m...
11 篇 pattern classifi...
11 篇 face recognition
11 篇 data mining
10 篇 computer vision
9 篇 information syst...
9 篇 task analysis
9 篇 user interfaces ...
9 篇 training
8 篇 information syst...
8 篇 pattern matching

机构

6 篇 fujian key labor...
6 篇 school of comput...
5 篇 fujian key labor...
4 篇 university of te...
4 篇 university of ch...
4 篇 bournemouth univ...
4 篇 school of inform...
4 篇 gdynia maritime ...
3 篇 friedrich alexan...
3 篇 department of co...
3 篇 institute of hea...
3 篇 johns hopkins un...
3 篇 univ chinese aca...
3 篇 institute of com...
2 篇 fgan-fom researc...
2 篇 dept. of ict maw...
2 篇 foundation for r...
2 篇 pes univ ctr pat...
2 篇 college of compu...
2 篇 institute of ima...

作者

12 篇 wang da-han
6 篇 zhu shunzhi
5 篇 du xia
5 篇 yang jie
4 篇 julie a. jacko
4 篇 de-shuang huang
4 篇 ireneusz czarnow...
4 篇 maier andreas
4 篇 wu yun
4 篇 alfonso mateos c...
3 篇 jianhua tao
3 篇 fotouhi javad
3 篇 akira notsu
3 篇 seiki ubukata
3 篇 katsuhiro honda
3 篇 navab nassir
3 篇 unberath mathias
3 篇 luo bin
3 篇 chen si
2 篇 feng deying

语言

392 篇 英文
4 篇 中文
2 篇 其他

检索条件"任意字段=8th International Conference on Computing and Pattern Recognition, ICCPR 2019"

共 394 条记录，以下是81-90 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：

Continual Learning for Document Image Binarization 26

Continual Learning for Document Image Binarization

引用

26th international conference on pattern recognition / 8th international Workshop on Image Mining - theory and Applications (IMTA)

作者： Garrido-Munoz, Carlos Sanchez-Hernandez, Adrian Castellanos, Francisco J. Calvo-Zaragoza, Jorge Univ Alicante Dept Software & Comp Syst San Vicente Spain

ISBN: (数字)9781665490627

ISBN: (纸本)9781665490627

In the field of Document Image Analysis (DIA), it is common to find great heterogeneity in terms of the possible graphic domains. In this sense, it is interesting to build neural models that can be sequentially adapted to new domains without losing the knowledge from the domains already learned. this learning paradigm is known as Continual (or Lifelong) Learning (CL). Although the adaptation comes along with a training set of the new domain, neural networks suffer what is known as "catastrophic forgetting". therefore, assuming the constraint of not keeping data from the domains already addressed, this paradigm represents a challenge yet to be solved. this work presents an approach for CL in document image binarization, one of the most considered tasks within the DIA field. Our results report that it is indeed feasible to address CL in this field, given that the approach is successfully implemented and outperforms the baseline by a wide margin in most of the analyzed scenarios.

关键词： Training Graphics Adaptation models Text analysis Image analysis Neural networks pattern recognition

来源：评论

学校读者我要写书评

暂无评论

A New Hybrid Method with Biomimetic pattern recognition and Sparse Representation for EEG Classification

A New Hybrid Method with Biomimetic Pattern Recognition and ...

引用

8th international conference on Intelligent computing (ICIC)

作者： Ge, Yanbin Wu, Yan Tongji Univ Dept Comp Sci & Technol Shanghai 201804 Peoples R China

ISBN: (纸本)9783642318368

this paper presents a novel classification framework combining Biomimetic pattern recognition (BPR) with Sparse Representation (SR) for Brain Computer Interface based on motor imagery. this framework can work well when encountering the overlap coverage problem of BPR by introducing the idea of SR. Using Common Spatial pattern to extract the rhythm features of EEG data, we evaluate the performance of the proposed method in the datasets from previous BCI Competitions. By making comparison with those of LDA, SVM and original BPR, our proposed method shows the better classification accuracy.

关键词： biomimetic pattern recognition hyper sausage neuron sparse re-presentation brain-computer interface motor imagery

来源：评论

学校读者我要写书评

暂无评论

Forecasting of depth and ego-motion with transformers and self-supervision 26

Forecasting of depth and ego-motion with transformers and se...

引用

26th international conference on pattern recognition / 8th international Workshop on Image Mining - theory and Applications (IMTA)

作者： Boulahbal, Houssem Eddine Voicila, Adrian Comport, Andrew I. Renault Software Factory Ile De France France Cote Azur Univ CNRS I3S Nice France

ISBN: (数字)9781665490627

ISBN: (纸本)9781665490627

this paper addresses the problem of end-to-end self-supervised forecasting of depth and ego motion. Given a sequence of raw images, the aim is to forecast both the geometry and ego-motion using a self supervised photometric loss. the architecture is designed using both convolution and transformer modules. this leverages the benefits of both modules: Inductive bias of CNN, and the multi-head attention of transformers, thus enabling a rich spatio-temporal representation that enables accurate depth forecasting. Prior work attempts to solve this problem using multi-modal input/output with supervised ground-truth data which is not practical since a large annotated dataset is required. Alternatively to prior methods, this paper forecasts depth and ego motion using only self-supervised raw images as input. the approach performs significantly well on the KITTI dataset benchmark with several performance criteria being even comparable to prior non-forecasting self-supervised monocular depth inference methods.

关键词： Geometry Convolution Benchmark testing Transformers Feature extraction pattern recognition Forecasting

来源：评论

学校读者我要写书评

暂无评论

Intelligent Decision Technologies 2016 1st ed. 2016

引用

丛书名： Smart Innovation, Systems and Technologies

2016年

作者： Ireneusz Czarnowski Alfonso Mateos Caballero Robert J. Howlett Lakhmi C. Jain

ISBN: (数字)9783319396279

ISBN: (纸本)9783319396262

the KES-IDT-2016 proceedings give an excellent insight into recent research, both theoretical and applied, in the field of intelligent decision making. the range of topics explored is wide, and covers methods of grouping, classification, prediction, decision support, modelling and many more in such areas as finance, linguistics, medicine, management and transportation. this proceedings contain several sections devoted to specific topics, such as: Specialized Decision Techniques for Data Mining, Transportation and Project Management pattern recognition for Decision Making Systems New Advances of Soft computing in Industrial and Management Engineering Recent Advances in Fuzzy Systems Intelligent Data Analysis and Applications Reasoning-based Intelligent Systems Intelligent Methods for Eye Movement Data Processing and Analysis Intelligent Decision Technologies for Water Resources Management Intelligent Decision Making for Uncertain Unstructured Big Data Decision Making theory for Economics Interdisciplinary Approaches in Business Intelligence Research and Practice pattern recognition in Audio and Speech Processing the KES-IDT conference is a well-established international annual conference, interdisciplinary in nature. these two volumes of proceedings form an excellent account of the latest results and outcomes of recent research in this leading-edge area.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Intelligent Decision Technologies 2016 1st ed. 2016

引用

丛书名： Smart Innovation, Systems and Technologies

2016年

作者： Ireneusz Czarnowski Alfonso Mateos Caballero Robert J. Howlett Lakhmi C. Jain

ISBN: (数字)9783319396309

ISBN: (纸本)9783319396293

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Fast Implementation of Adaptive Histogram Equalization

A Fast Implementation of Adaptive Histogram Equalization

引用

2006 8th international conference on Signal Processing

作者： WANG Zhiming TAO Jianhua School of Information Engineering University of Science and Technology Beijing National Laboratory of Pattern Recognition Institute of AutomationChinese Academy of Sciences

ISBN: (纸本)0780397371

Adaptive Histogram Equalization(AHE) is a popular and effective algorithm for image contrast *** it's quite computationally expensive and time *** this paper,a fast implementation of AHE based on pure software techniques is *** accelerative techniques are combined to form the new fast AHE:First,local histogram is acquired by an iterative approach with a sliding window;Second,in computing cumulative histogram function,not more than half of the histogram is cumulated;third,by keep the block size W2 equal to the product of grey level number and integral power of 2,all the multiplication and division operations are replaced with fast bitwise *** theoretical analysis and experimental results demonstrate the proposed algorithm is effective.

关键词： Image Process Contrast Enhancement Histogram Equalization Adaptive Histogram Equalization

来源：评论

学校读者我要写书评

暂无评论

RBF nets in faults localization

引用

8th international conference on Artificial Intelligence and Soft computing (ICAISC 2006)

作者： Rafajlowicz, Ewaryst Wroclaw Univ Technol Inst Comp Engn Control & Robot PL-50370 Wroclaw Poland

ISBN: (纸本)3540357483

the task of faults localization is discussed in a model-free setting. As a tool for its solution we consider a multiclass pattern recognition problem with a metric in the label space. then, this problem is approximately solved, providing hints on selecting appropriate RBF nets. It was shown that the approximate solution is the exact one in several important cases. Finally, we propose the algorithm for learning the proposed RBF net. the results of its testing are briefly reported.

关键词： pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Heterogeneous Parallelization of Aho-Corasick Algorithm 8

Heterogeneous Parallelization of Aho-Corasick Algorithm

引用

8th international conference on Practical Applications of Computational Biology & Bioinformatics (PACBB)

作者： Soroushnia, Shima Daneshtalab, Masoud Plosila, Juha Liljeberg, Pasi Univ Turku Dept Informat Technol SF-20500 Turku Finland

ISBN: (纸本)9783319075815;9783319075808

pattern discovery is one of the fundamental tasks in bioinformatics and pattern recognition is a powerful technique for searching sequence patterns in the biological sequence databases. the significant increase in the number of DNA and protein sequences expands the need for raising the performance of pattern matching algorithms. For this purpose, heterogeneous architectures can be a good choice due to their potential for high performance and energy efficiency. In this paper we present an efficient implementation of Aho-Corasick (AC) and PFAC (Parallel Failureless Aho-Corasick) algorithm on a heterogeneous CPU/GPU architecture. We progressively redesigned the algorithms and data structures to fit on the GPU architecture. Our results on different protein sequence data sets show 15% speedup comparing to the original implementation of the PFAC algorithm.

关键词： Heterogeneous GPU pattern Matching Aho-Corasick CUDA OpenMP

来源：评论

学校读者我要写书评

暂无评论

Context-aware Deformable Alignment for Video Object Segmentation 26

Context-aware Deformable Alignment for Video Object Segmenta...

引用

26th international conference on pattern recognition / 8th international Workshop on Image Mining - theory and Applications (IMTA)

作者： Yang, Jie Xia, Mingfu Zhou, Xue Univ Elect Sci & Technol China UESTC Sch Automat Engn Chengdu Peoples R China UESTC Shenzhen Inst Adv Study Shenzhen Peoples R China

ISBN: (数字)9781665490627

ISBN: (纸本)9781665490627

Matching-based Semi-supervised video object segmentation (VOS) either resorts to non-local matching to retrieve and aggregate the spatiotemporal features of past frames or relies on template matching to learn similarity representation. Although achieving remarkable progress, they still suffer from considerable computation overhead and failure when confronting with large appearance changes, respectively. In this paper, we are motivated to address the above issues. Firstly, we propose a Context-aware Deformable Alignment (CDA) mechanism to align the spatio-temporal features of past frames more efficiently. To reduce computation complexity dramatically and retain the ability of modeling long-range spatio-temporal dependencies, the CDA mechanism that learns where to match in a deformable fashion belongs to local context-aware matching instead of nonlocal pixel-wise matching. Furthermore, we present a Dynamic Kernel Matching (DKM) technique to tackle the mismatches due to appearance and scale variations. DKM dynamically adapts the template feature to object appearance changes rather than fixing it, which improves the robustness for long-term VOS. Our framework dubbed CDANet is evaluated on popular benchmark sets, which achieves competitive performance compared with SOTA methods.

关键词： Deformable models Object segmentation Benchmark testing Robustness Spatiotemporal phenomena pattern recognition Object tracking

来源：评论

学校读者我要写书评

暂无评论

A new predictive approach to variables selection through Genetic Algorithm and Fuzzy Adaptive Resonance theory Using medical diagnosis as a case 8

A new predictive approach to variables selection through Gen...

引用

8th international conference on Ambient Systems, Networks and Technologies (ANT) / 7th international conference on Sustainable Energy Information Technology (SEIT)

作者： Djellali, Choukri Adda, Mehdi Univ Quebec Math Comp Sci & Engn Dept 300 Allee Ursulines Rimouski PQ G5L 3A1 Canada

Variables selection is challenging task due mainly to huge search space. this study addresses the increasingly encountered challenge of variables selection. It addresses the application of machine learning techniques to the problem of variables selection. We detailed the various models of the variables selection and examined the basic steps that are used to select the cost-effective predictors. We also walked through the initial settings and all variables selection stages, including architecture configuration, strategy generation, learning, model induction, and scoring. Results from this study show that the cost and generalization were seen to improve significantly in terms of computing time and recognition accuracy when the proposed system is applied for medical diagnosis. Good comparisons with an experimental study demonstrate the multidisciplinary applications of our approach. 1877-0509 (C) 2017 the Authors. Published by Elsevier B.V.

关键词： Data Mining pattern recognition Machine Learning Clustering Variables Selection Genetic Algorithm

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40页 << < 5 6 7 8 9 10 11 12 13 14 > >>

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：