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

1,585 篇 会议
83 册 图书
16 篇 期刊文献

馆藏范围

1,684 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,044 篇 工学
- 875 篇 计算机科学与技术...
- 468 篇 软件工程
- 226 篇 信息与通信工程
- 186 篇 电气工程
- 100 篇 生物工程
- 98 篇 生物医学工程（可授...
- 84 篇 控制科学与工程
- 62 篇 光学工程
- 35 篇 机械工程
- 35 篇 电子科学与技术（可...
- 24 篇 仪器科学与技术
- 23 篇 化学工程与技术
- 21 篇 建筑学
- 21 篇 土木工程
- 20 篇 材料科学与工程（可...
- 20 篇 安全科学与工程
- 19 篇 交通运输工程
352 篇 理学
- 175 篇 数学
- 114 篇 生物学
- 88 篇 物理学
- 52 篇 统计学（可授理学、...
- 35 篇 系统科学
- 21 篇 化学
176 篇 管理学
- 92 篇 图书情报与档案管...
- 89 篇 管理科学与工程(可...
- 45 篇 工商管理
113 篇 医学
- 91 篇 临床医学
- 61 篇 基础医学(可授医学...
- 34 篇 药学(可授医学、理...
33 篇 法学
- 26 篇 社会学
17 篇 教育学
12 篇 经济学
8 篇 农学
3 篇 军事学
3 篇 艺术学
2 篇 文学

主题

238 篇 pattern recognit...
79 篇 cloud computing
74 篇 artificial intel...
71 篇 training
57 篇 feature extracti...
55 篇 neural networks
52 篇 machine learning
49 篇 deep learning
40 篇 computer archite...
36 篇 data mining
34 篇 computer imaging...
33 篇 pattern matching
33 篇 computer vision
32 篇 semantics
29 篇 image segmentati...
28 篇 computational mo...
28 篇 image recognitio...
28 篇 image processing...
27 篇 information syst...
26 篇 edge computing

机构

15 篇 school of comput...
15 篇 university of ch...
9 篇 school of comput...
8 篇 inria nancy gran...
8 篇 national center ...
8 篇 icube université...
8 篇 fujian key labor...
8 篇 erasmus mc - uni...
8 篇 tencent jarvis l...
8 篇 university of ba...
7 篇 college of intel...
6 篇 univ chinese aca...
6 篇 institute of ima...
6 篇 department of co...
6 篇 the 54th researc...
6 篇 school of artifi...
6 篇 dipartimento di ...
6 篇 dipartimento di ...
6 篇 computational sc...
6 篇 institute of com...

作者

13 篇 tan chew lim
12 篇 wang da-han
11 篇 yang jie
8 篇 stéphane cotin
8 篇 yefeng zheng
8 篇 chew lim tan
8 篇 philippe c. catt...
8 篇 marleen de bruij...
8 篇 stefanie speidel
8 篇 caroline essert
8 篇 nicolas padoy
7 篇 maier andreas
7 篇 yang yang
7 篇 hancock edwin r.
7 篇 rita cucchiara
7 篇 alberto del bimb...
6 篇 hugo jair escala...
6 篇 tao mei
6 篇 lu shijian
6 篇 marco bertini

语言

1,664 篇 英文
18 篇 其他
3 篇 中文

检索条件"任意字段=2021 10th International Conference on Computing and Pattern Recognition"

共 1684 条记录，以下是881-890 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：

Multi-layered Discriminative Restricted Boltzmann Machine with Untrained Probabilistic Layer

Multi-layered Discriminative Restricted Boltzmann Machine wi...

引用

international conference on pattern recognition

作者： Yuri Kanno Muneki Yasuda Graduate School of Science and Engineering Yamagata University Japan

An extreme learning machine (ELM) is a three-layered feed-forward neural network having untrained parameters, which are randomly determined before training. Inspired by the idea of ELM, a probabilistic untrained layer called a probabilistic-ELM (PELM) layer is proposed, and it is combined with a discriminative restricted Boltzmann machine (DRBM), which is a probabilistic three-layered neural network for solving classification problems. the proposed model is obtained by stacking DRBM on the PELM layer. the resultant model (i.e., multi-layered DRBM (MDRBM)) forms a probabilistic four-layered neural network. In MDRBM, the parameters in the PELM layer can be determined using Gaussian-Bernoulli restricted Boltzmann machine. Owing to the PELM layer, MDRBM obtains a strong immunity against noise in inputs, which is one of the most important advantages of MDRBM. Numerical experiments using some benchmark datasets, MNIST, Fashion-MNIST, Urban Land Cover, and CIFAR-10, demonstrate that MDRBM is superior to other existing models, particularly, in terms of the noise-robustness property (or, in other words, the generalization property).

关键词： Training Extreme learning machines Neural networks Stacking Benchmark testing Probabilistic logic pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Extensive Study on Color and Light Translation of 2D Images using Machine Learning Approaches

Extensive Study on Color and Light Translation of 2D Images ...

引用

international conference on System Modeling & Advancement in Research Trends (SMART)

作者： Jyoti Ranjan Labh R.K. Dwivedi College of Computing Science&amp Information Technology TMU Moradabad India College of Computing Science & Information Technology Moradabad India

ISBN: (纸本)9781665439718

For machine learning applications, digital image production provides for the efficient generation of huge volumes of training data while preserving control over the generation process to ensure the optimal content distribution and variation. Synthetic data has the potential to become an important element of the training pipeline as the demand for deep learning applications grows. Over the last decade, a broad range of strategies for producing training data have been presented. the collecting of these for comparison and categorization is required for future improvement. this study presents a complete list of available visual machine learning image synthesis approaches. In the context of 2D picture production, these are classed as light transfer and colour transfer. the focus is on the computational features of approaches for developing machine learning colour transfer between image-to-image translation in the future. Finally, the learning potential of each approach is assessed based on its reported quality and performance. the study is meant to serve as a complete reference for both data and application developers. this is a comprehensive list of all the methods and approaches discussed in this page.

关键词： Training Visualization Image color analysis Pipelines Training data Process control Production

来源：评论

学校读者我要写书评

暂无评论

Meta Soft Label Generation for Noisy Labels

Meta Soft Label Generation for Noisy Labels

引用

international conference on pattern recognition

作者： Görkem Algan Ilkay Ulusoy ASELSAN Middle East Technical University Electrical-Electronics Engineering

the existence of noisy labels in the dataset causes significant performance degradation for deep neural networks (DNNs). To address this problem, we propose a Meta Soft Label Generation algorithm called MSLG, which can jointly generate soft labels using meta-learning techniques and learn DNN parameters in an end-to-end fashion. Our approach adapts the meta-learning paradigm to estimate optimal label distribution by checking gradient directions on both noisy training data and noise-free meta-data. In order to iteratively update soft labels, meta-gradient descent step is performed on estimated labels, which would minimize the loss of noise-free meta samples. In each iteration, the base classifier is trained on estimated meta labels. MSLG is model-agnostic and can be added on top of any existing model at hand with ease. We performed extensive experiments on CIFAR10, Clothing1M and Food101N datasets. Results show that our approach outperforms other state-of-the-art methods by a large margin. Our code is available at https://***/gorkemalgan/MSLG_noisy_label.

关键词： Training Degradation Adaptation models Neural networks Clothing Training data pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of the 1st and 2nd Wave of COVID–19 and Visualizing the Increasing and Decreasing of COVID–19

Comparative Analysis of the 1st and 2nd Wave of COVID–19 an...

引用

international conference on System Modeling & Advancement in Research Trends (SMART)

作者： Saloni Gupta Deependra Rastogi Kartavya Chauhan Shivani Sharma Galgotias University Greater Noida School of computing Science and Engineering Galgotias University Greater Noida School of Computing Science and Engineering Galgotias University Greater Noida

ISBN: (纸本)9781665439718

the COVID-19 epidemic spread quickly across nations and country to country counter with lockdowns, about 1.6 billion students remain at home worldwide. Under these situations, and in order to keep student positive on current and for coming challenges. Firstly, we are going to do comparative study on 1st and 2nd wave of corona. Secondly, we are making a website that will give a complete detail about the Coronavirus disease and will tell us about the increasing, death and decreasing cases all over India and will show a map on particular state that will be searched and also make a graph on the particular set of data for the particular searched state. In order to make our website more attractive we are going to use CSS, Html and Python language in developing the website. At last, we will come to know briefly about COVID – 19 (Coronavirus) and also about the cases that are increasing and who all have recovered from it.

关键词： COVID-19 Epidemics Market research Corona

来源：评论

学校读者我要写书评

暂无评论

Research on Multi-station Integrated 5G Communication Scheme for Smart Energy Station 2021

Research on Multi-station Integrated 5G Communication Scheme...

引用

2021 the 10th international conference on Networks, Communication and computing

作者： Qin LI Zengqing QI Zhiqiang XU Jun LU Bowen LI Hunan Economic and Research Power Design Co. Ltd China Economic and Technical Research Institute of State Grid Hunan Electric Power Company China North China Electric Power University China

ISBN: (纸本)9781450385848

Smart energy station is a new generation of energy hub infrastructure based on substation, which realizes the multi-station functions of substation, energy storage station, photovoltaic station, charging station and data center station. To improve the processing capacity of the differentiated services of the smart energy station and the efficient coordination of data communication between each station, this paper proposed a multi-station integrated 5G communication scheme for smart energy station. Firstly, the related communication QoS requirements of the multi-site converged services is analyzed for smart energy stations. Secondly, a layered 5G-based communication networking model for smart energy stations is depicted including terminal-perception layer, edge-computing layer, communication-network layer, middle-platform layer and service-platform layer. Finally, a multi-station integrated 5G communication scheme is specified based on the proposed model by an application case, which is combined with UPF deployment strategy for Edge computing and 3-layered 5G-slicing strategy for services’ security. the case illustrates that the proposed scheme performs effectively for the multi-station Integrated services of smart energy stations.

关键词： Edge computing Multi-site integration 5G Smart energy station

来源：评论

学校读者我要写书评

暂无评论

the Framework and thinking of the Future Primary and Secondary School Information Support Environment

The Framework and Thinking of the Future Primary and Seconda...

引用

international conference on Educational and Information Technology (ICEIT)

作者： Jun Han Xiaoyan Li Jing Liu Capital Normal University Beijing China

ISBN: (数字)9781665422956

ISBN: (纸本)9781665446471

With the development and changes of the society, continuous technological innovation and improvement of people's learning needs have promoted the continuous transformation of schools, thus deriving the concept of future schools. In the future school construction process, the design of information support environment is of great significance. this paper analyzes the structural design of the future school information support environment, proposes the school-based, regional and public information structure design, and provides insights and reflections on the construction process. Expecting to provide references for further research and application of future school construction.

关键词： Technological innovation Cloud computing Education Reflection Internet of things Information technology Edge computing

来源：评论

学校读者我要写书评

暂无评论

Probability Guided Maxout

Probability Guided Maxout

引用

international conference on pattern recognition

作者： Claudio Ferrari Stefano Berretti Alberto Del Bimbo Media Integration and Communication Center University of Florence Italy

In this paper, we propose an original CNN training strategy that brings together ideas from both dropout-like regularization methods and solutions that learn discriminative features. We propose a dropping criterion that, differently from dropout and its variants, is deterministic rather than random. It grounds on the empirical evidence that feature descriptors with larger L2-norm and highly-active nodes are strongly correlated to confident class predictions. thus, our criterion guides towards dropping a percentage of the most active nodes of the descriptors, proportionally to the estimated class probability. We simultaneously train a per-sample scaling factor to balance the expected output across training and inference. this further allows us to keep high the descriptor's L2-norm, which we show enforces confident predictions. the combination of these two strategies resulted in our “Probability Guided Maxout” solution that acts as a training regularizer. We prove the above behaviors by reporting extensive image classification results on the CIFAR10, CIFAR100, and Caltech256 datasets. Code is available at https://***/clferrari/probability-guided-maxout.

关键词： Training pattern recognition Image classification

来源：评论

学校读者我要写书评

暂无评论

Cross-Domain Semantic Segmentation of Urban Scenes via Multi-Level Feature Alignment

Cross-Domain Semantic Segmentation of Urban Scenes via Multi...

引用

international conference on pattern recognition

作者： Bin Zhang Shengjie Zhao Rongqing Zhang Key Laboratory of Embedded System and Service Computing Ministry of Education China School of Software Engineering Tongji University Shanghai China

Semantic segmentation is an essential task in plenty of real-life applications such as virtual reality, video analysis, autonomous driving, etc. Recent advancements in fundamental vision-based tasks ranging from image classification to semantic segmentation have demonstrated deep learning-based models' high capability in learning complicated representation on large datasets. Nevertheless, manually labeling semantic segmentation dataset with pixel-level annotation is extremely labor-intensive. To address this problem, we propose a novel multi-level feature alignment framework for cross-domain semantic segmentation of urban scenes by exploiting generative adversarial networks. In the proposed multi-level feature alignment method, we first translate images from one domain to another one. then the discriminative feature representations extracted by the deep neural network are concatenated, followed by domain adversarial learning to make the intermediate feature distribution of the target domain images close to those in the source domain. With these domain adaptation techniques, models trained with images in the source domain where the labels are easy to acquire can be deployed to the target domain where the labels are scarce. Experimental evaluations on various mainstream benchmarks confirm the effectiveness as well as robustness of our approach.

关键词： Image segmentation Solid modeling Semantics Neural networks Virtual reality Feature extraction Robustness

来源：评论

学校读者我要写书评

暂无评论

Heterogeneous Graph-based Knowledge Transfer for Generalized Zero-shot Learning

Heterogeneous Graph-based Knowledge Transfer for Generalized...

引用

international conference on pattern recognition

作者： Junjie Wang Xiangfeng Wang Bo Jin Junchi Yan Wenjie Zhang Hongyuan Zha School of Computer Science and Technology East China Normal University Shanghai China Shanghai Jiaotong University Shanghai China Tencent Shenzhen China College of Computing Georgia Institute of Technology Atlanta GA USA

Generalized zero-shot learning (GZSL) tackles the problem of learning to classify instances involving both seen classes and unseen ones. the key issue is how to effectively transfer the model learned from seen classes to unseen classes. Existing works in GZSL usually assume that some prior information about unseen classes are available. However, such an assumption is unrealistic when new unseen classes appear dynamically. To this end, we propose a novel heterogeneous graph-based knowledge transfer method (HGKT) for GZSL, agnostic to unseen classes and instances, by leveraging graph neural network. Specifically, a structured heterogeneous graph is constructed with high-level representative nodes for seen classes, which are chosen through Wasserstein barycenter in order to simultaneously capture inter-class and intra-class relationship. the aggregation and embedding functions can be learned through graph neural network, which can be used to compute the embeddings of unseen classes by transferring the knowledge from their neighbors. Extensive experiments on public benchmark datasets show that our method achieves state-of-the-art results.

关键词： Training Knowledge engineering Adaptation models Heuristic algorithms Computational modeling Benchmark testing Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Privacy Attributes-aware Message Passing Neural Network for Visual Privacy Attributes Classification

Privacy Attributes-aware Message Passing Neural Network for ...

引用

international conference on pattern recognition

作者： Hanbin Hong Wentao Bao Yuan Hong Yu Kong Golisano College of Computing and Information Sciences Rochester Institute of Technology Rochester NY Illinois Institute of Technology Chicago IL

Visual Privacy Attribute Classification (VPAC) identifies privacy information leakage via social media images. these images containing privacy attributes such as skin color, face or gender are classified into multiple privacy attribute categories in VPAC. With limited works in this task, current methods often extract features from images and simply classify the extracted feature into multiple privacy attribute classes. the dependencies between privacy attributes, e.g., skin color and face typically coexist in the same image, are usually ignored in classification, which causes performance degradation in VPAC. In this paper, we propose a novel end-to-end Privacy Attributes-aware Message Passing Neural Network (PA-MPNN) to address VPAC. Privacy attributes are considered as nodes on a graph and an MPNN is introduced to model the privacy attribute dependencies. To generate representative features for privacy attribute nodes, a class-wise encoder-decoder is proposed to learn a latent space for each attribute. An attention mechanism with multiple correlation matrices is also introduced in MPNN to learn the privacy attributes graph automatically. Experimental results on the Privacy Attribute Dataset demonstrate that our framework achieves better performance than state-of-the-art methods for visual privacy attributes classification.

关键词： Privacy Visualization Data privacy Correlation Image color analysis Message passing Neural networks

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169页 << < 85 86 87 88 89 90 91 92 93 94 > >>

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：