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

31,290 篇 会议
555 册 图书
534 篇 期刊文献
3 篇 学位论文

馆藏范围

32,380 篇 电子文献
4 种 纸本馆藏

日期分布

学科分类号

22,795 篇 工学
- 16,025 篇 计算机科学与技术...
- 12,470 篇 软件工程
- 4,879 篇 信息与通信工程
- 2,581 篇 控制科学与工程
- 2,196 篇 机械工程
- 1,899 篇 电子科学与技术（可...
- 1,682 篇 电气工程
- 1,457 篇 仪器科学与技术
- 1,248 篇 生物医学工程（可授...
- 1,152 篇 生物工程
- 980 篇 化学工程与技术
- 964 篇 光学工程
- 710 篇 材料科学与工程（可...
- 697 篇 动力工程及工程热...
- 619 篇 建筑学
- 522 篇 土木工程
8,888 篇 理学
- 5,355 篇 数学
- 1,780 篇 物理学
- 1,532 篇 统计学（可授理学、...
- 1,430 篇 系统科学
- 1,299 篇 生物学
- 845 篇 化学
6,760 篇 管理学
- 3,656 篇 管理科学与工程(可...
- 3,400 篇 图书情报与档案管...
- 1,426 篇 工商管理
908 篇 医学
- 740 篇 临床医学
- 638 篇 基础医学(可授医学...
824 篇 法学
- 679 篇 社会学
734 篇 教育学
- 700 篇 教育学
609 篇 经济学
- 601 篇 应用经济学
508 篇 农学
348 篇 文学
209 篇 军事学
101 篇 艺术学
8 篇 哲学
1 篇 历史学

主题

751 篇 educational inst...
521 篇 feature extracti...
440 篇 computational mo...
423 篇 vectors
386 篇 data mining
385 篇 computer archite...
382 篇 semantics
351 篇 image segmentati...
349 篇 computers
327 篇 algorithm design...
293 篇 support vector m...
289 篇 accuracy
272 篇 training
260 篇 information syst...
259 篇 databases
251 篇 servers
236 篇 cloud computing
217 篇 routing
200 篇 graphics process...
196 篇 wireless sensor ...

机构

81 篇 department of co...
57 篇 college of infor...
47 篇 school of comput...
45 篇 school of inform...
45 篇 school of comput...
43 篇 school of comput...
42 篇 ministry of educ...
41 篇 institute of inf...
40 篇 school of comput...
38 篇 school of comput...
38 篇 school of comput...
35 篇 college of infor...
35 篇 key laboratory o...
34 篇 school of inform...
33 篇 department of co...
30 篇 school of comput...
28 篇 school of inform...
26 篇 college of compu...
26 篇 school of inform...
25 篇 computer network...

作者

33 篇 yang yang
31 篇 zhang lei
26 篇 li li
25 篇 liu yang
23 篇 wang jing
22 篇 ma yan
21 篇 wang lei
20 篇 wang hui
19 篇 jun wang
18 篇 lei wang
18 篇 li peng
17 篇 park namje
17 篇 wang chao
16 篇 simon fong
16 篇 guo li
16 篇 wei li
15 篇 li yang
15 篇 wei liu
15 篇 zhang min
14 篇 zhang tao

语言

32,115 篇 英文
236 篇 中文
27 篇 其他
4 篇 法文
3 篇 俄文
1 篇 日文

检索条件"任意字段=2012 International Conference on Computer Science and Information Processing, CSIP 2012"

共 32382 条记录，以下是111-120 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：

Depth Assisted Portrait Video Background Blurring

Depth Assisted Portrait Video Background Blurring

引用

IS and T international Symposium on Electronic Imaging: Imaging and Multimedia Analytics at the Edge, IMAGE 2023

作者： Shen, Yezhi Xu, Weichen Lin, Qian Allebach, Jan P. Zhu, Fengqing Elmore Family School of Electrical and Computer Engineering Purdue University West LafayetteIN United States HP Inc Palo AltoCA United States

Video conferencing usage dramatically increased during the pandemic period and is expected to remain high in hybrid work. One of the key aspects of video conferencing experience is background blur and background replacement. In order to achieve a high-quality background blurring effect, an accurate portrait segmentation and high-quality blurring effect are necessary. Since depth sensors are becoming ubiquitous on mobile devices, software and hardware manufacturers are working together to utilize depth maps to improve the background blurring quality. Depth map has been used as an auxiliary input to categorize foreground and background human during post-processing in existing works. We further exploit the information in depth map by using depth map during inference and post-processing. In this paper, we propose an improved CNN model based on the well-known Portrait-Net method, a depth-assisted mask refinement that can correct error predictions using depth information, and a bokeh effect rendering module that can produce a photo-realistic bokeh effect for the background. © 2023, Society for Imaging science and Technology.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Improved Bounds for the Binary Paint Shop Problem 29th

Improved Bounds for the Binary Paint Shop Problem

引用

29th international Computing and Combinatorics conference, COCOON 2023

作者： Hančl, J. Kabela, A. Opler, M. Sosnovec, J. Šámal, R. Valtr, P. Faculty of Applied Sciences University of West Bohemia Pilsen Czech Republic Faculty of Information Technology Czech Technical University Prague Czech Republic Faculty of Mathematics and Physics Charles University Prague Czech Republic

ISBN: (纸本)9783031491924

We improve bounds for the binary paint shop problem posed by Meunier and Neveu [Computing solutions of the paintshop-necklace problem. Comput. Oper. Res. 39, 11 (2012), 2666-2678]. In particular, we disprove their conjectured upper bound for the number of color changes by giving a linear lower bound. We show that the recursive greedy heuristics is not optimal by providing a tiny improvement. We also introduce a new heuristics, recursive star greedy, that a preliminary analysis shows to be 10% better. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Paint

来源：评论

学校读者我要写书评

暂无评论

Object Detection Using Vision Transformed EfficientDet

Object Detection Using Vision Transformed EfficientDet

引用

2023 IEEE National Aerospace and Electronics conference, NAECON 2023

作者： Kar, Shreyanil El-Sharkawv, Mohamed Iupui Purdue School of Engineering and Technology Department of Electrical and Computer Engineering Indianapolis United States

ISBN: (纸本)9798350338782

computer vision, a subdivision of computer science and artificial intelligence focuses on enabling computers to interpret and analyze visual data from the world, such as images and videos. Recent advances in convolutional neural networks (CNNs), have improved the performance of computer vision systems remarkably, making them more accurate and efficient than ever before. Object detection using CNNs is a popular application of deep learning in computer vision. There are several popular frameworks for object detection that are widely used in the industry with many using the primary concept of convolution e.g., RetinaNet, EfficientNet, and EfficientDet etc. In this paper, we propose a novel hybrid approach for object detection by combining the power of Vision Transformers (ViT) with state-of-the-art EfficientDet architecture, resulting in a powerful object detection framework. The ViT backbone, known for its success in image classification and natural language processing (NLP) tasks, captures global dependencies in the input image using self-attention mechanisms. By incorporating ViT into the EfficientDet architecture, we enhance its ability to capture fine-grained details and context information, leading to improved object detection accuracy which leverages the strengths of both among other improvements to achieve highly accurate and efficient performance. The training of the model was done using PASCAL VOC 2007 and 2012 datasets and testing was executed on PASCAL VOC 2007 to achieve a mAP of 86.27%. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Optimized FOREX Rate Prediction Using Hybrid Machine Learning Algorithm 1

引用

2nd international conference on Intelligent Computing Systems and Applications, ICICSA 2023

作者： Latha, Challa Madhavi Bhuvaneswari, S. Soujanya, K.L.S. Department of Computer Science School of Engineering and Technology Pondicherry University Pondicherry Karaikal India Department of Information Technology CMR College of Engineering and Technology Medchal Hyderabad Kandlakoya India

ISBN: (数字)9789819754120

ISBN: (纸本)9789819754113

This research examines the application of fuzzy time series (FTS) models and different machine learning techniques to anticipate changes in foreign exchange (FOREX) data. The statistics used in this investigation include the actual FOREX prices and the high and low values of four different currencies. These statistics begin from January 2012 to November 2022;the data is available on the Reserve Bank of India website. This article investigates the significant flaws present in the literature information on FTS. This article identifies fundamental flaws in all FTS-based algorithms presently available in the literature and shows how to fix them. The study then describes the unique structure of improvised FTS. The Hybrid Machine Learning Algorithm is the name given to this structure. The purpose is to solve the identified issues present in FTS-based models previously published in the literature. The result was compared with the before and after optimization processes. After implementing the proposed hybrid machine learning algorithm, the result shows the better accuracy. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Spatio-Temporal Evolution of NPP in Helan Mountain from 2012 to 2021 Based on MODIS Satellite Data

Spatio-Temporal Evolution of NPP in Helan Mountain from 2012...

引用

international conference on Image, Vision and Intelligent Systems, ICIVIS 2023

作者： Lin, Yanyan Yu, Peng Cai, Xiaoying Xia, Le Zheng, Yuanmao He, Yuanrong School of Environmental Science and Engineering Xiamen University of Technology Xiamen China Hunan Key Laboratory of Remote Sensing of Ecological Environment in Dongting Lake Area Changsha China College of Computer and Information Engineering Xiamen University of Technology Xiamen China

ISBN: (纸本)9789819708543

In order to evaluate the methods and results of remotely sensed estimation of net primary productivity (NPP) in Helan Mountain, this article uses the MODIS NPP product data and land cover type product from years of 2012–2021 to analyze the ecological quality changes of the Helan Mountain Nature Reserve. The results showed that (1) the mean value of NPP in the study area decreases from 145.68 gC/(m2·a) in 2012 to 122.77 gC/(m2·a);the mean NPP of Helan Mountain from 2012–2021 is 141.32 gC/(m2·a);the total NPP changes in the range of 1.46~1.96 TgC/(m2·a);the NPP is slowly decreasing during 2016 and showed an opposite trend during 2016–2019;(2) The Helan Mountain is mainly covered by annual herbaceous vegetation followed by evergreen coniferous forest, and the area of annual herbaceous vegetation reaches more than 2300 km2, accounting for about 88% of the total area of the study area;(3) The NPP is mainly concentrated in the western part of Helan Mountain, and the main land cover categories are evergreen coniferous forest and annual herbaceous vegetation;the NPP shows a decreasing trend from 2012 to 2021. The total NPP reaches the maximum in 2019, the vegetation carbon sequestration capacity increases significantly, and the ecological quality of vegetation has been improved accordingly since the defense of 2017. The above study analyzed the remote sensing estimation of NPP in Helan Mountains in the past 10 years and sorted out the development trend of vegetation NPP in Helan Mountains, in order to provide theoretical basis for ecological protection and economic construction in Helan Mountains. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

A Bibliometric Analysis of Machine Translation Post-editing from 2012 to 2021

A Bibliometric Analysis of Machine Translation Post-editing ...

引用

2022 European conference on Natural Language processing and information Retrieval, ECNLPIR 2022

作者： Lu, Yanqi Sanda University Chool of Foreign Languages Shanghai201209 China

ISBN: (纸本)9781665473828

Machine translation post-editing (MTPE) has gained a lot of attention lately. This paper conducted a bibliometric analysis of 270 publications on MTPE retrieved from the core database of Web of science in recent decade from 2012 to 2021 with the aid of literature analysis software VOSviewer. By means of keyword co-occurrence and clustering of literature co-citation, this paper reviews the distribution of annual publications, disciplines, institutions and authors, citation structure of MTPE, etc. Meanwhile, the future trends related to the study of MTPE are predicted so as to provide reference and inspiration for further research. The research findings are as follows: the number of MTPE publications has fluctuated in the past decade, but the overall trend is increasing;MTPE studies are mainly distributed in linguistics and computer science;Dublin City University in Ireland is currently the most productive institution in MTPE research, and Joss Moorkens from the university plays a critical role in promoting the cooperation between scholars in this field;Spain is currently the most productive country in MTPE, but Ireland is the most cited country in the literature. From the analysis of keywords, the paper concludes that most of the current MTPE articles focus on the key concepts of 'quality' and 'effort while in the future, 'NMT', 'translation quality assessment' and 'MTPE skills and training' will be the research trends. © 2022 IEEE.

关键词： Quality control

来源：评论

学校读者我要写书评

暂无评论

A comparative study of Stock Price Prediction Based on BP and LSTM Neural Network 3

A comparative study of Stock Price Prediction Based on BP an...

引用

3rd international conference on Artificial Intelligence and computer Engineering, ICAICE 2022

作者： Huang, Shujia Wang, Ben Hao, Lingbo Si, Zebin School of Information Science and Technology Hangzhou Normal University Hangzhou China

ISBN: (纸本)9781510663473

In recent years, stock price prediction has become a research hotspot. The price of the stock market is unstable, which often rises or falls sharply due to the national policies, which makes it difficult for investors to achieve stable returns in the stock market. With the rapid rise of artificial intelligence, computers have become flexible in dealing with mathematical problems. Therefore, the extraordinary computing power of computers has been used to analyze and predict the trend of the stock market. More and more computer professionals began to enter the financial market and use neural network to study the trend of the stock market. This paper uses BP neural network and LSTM neural network to learn and predict the stock data of Shanghai Composite Index from January 2012 to June 2022. LSTM is a kind of RNN, but it is superior to other neural networks. It can effectively deal with data forgetting and gradient explosion problems, and bring reliability to the prediction results of the model. The two models are evaluated by analyzing MAE, MSE and the time required for model training. The results show that LSTM model can not only learn longer time span than BP model, but also better than BP model in MAE and MSE indexes, which provides some reference and guidance for the prediction of medium and long-term stocks. © 2023 SPIE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Visualization Analysis and Trends in Indonesian Internet of Things Research Using Bibliometrics 1

Visualization Analysis and Trends in Indonesian Internet of ...

引用

1st international conference on information System and information Technology, ICISIT 2022

作者： Maulana, Fairuz Iqbal Pangestu, Gusti Febriantono, M. Aldiki Arifuddin, Rahman Widartha, Vandha Pradwiyasma Bina Nusantara University School of Computer Science Computer Science Department Jakarta11480 Indonesia University of Merdeka Malang Department of Electrical Engineering Malang Indonesia Telkom University Information System of Industrial Engineering Faculty Bandung Indonesia

ISBN: (数字)9781665402002

ISBN: (纸本)9781665402002

The Internet of Things (IoT) has emerged as a critical issue and area of research for a variety of communities, academics, and industries worldwide. Due to the lack of research in IoT and understanding the direction of IoT development in the future. This research presents bibliometric analysis and analysis of science mapping on IoT. Data was taken from the Scopus database based on Indonesian state affiliation from 2012-2020. A total of 1415 documents (conference proceedings, journals, book series, and books) were retrieved, which were then processed online via Scopus Web and by VOSviewer software to perform advanced bibliometric analysis and science mapping analysis. The method is divided into five stages: keyword selection, initial search results, search result refinement, initial compilation, and data analysis. Scopus's list of the most frequently published and indexed articles, the most published papers are in the subject area of computer science (29.0%) with 938 documents, Engineering (20.7%) with 668 documents, Physics and Astronomy (9.5%) with 308 documents. The data processed and visualized on this topic offer exploratory information about the current status and trends in the IoT scientific literature and provide insight for established and novice researchers in understanding this research topic. © 2022 IEEE.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

TBA-GNN: A Traffic Behavior Analysis Model with Graph Neural Networks for Malicious Traffic Detection 18th

TBA-GNN: A Traffic Behavior Analysis Model with Graph Neura...

引用

18th international conference on Wireless Artificial Intelligent Computing Systems and Applications, WASA 2024

作者： Han, Xinbo Zhang, Meng Yang, Zheng Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9783031714634

Given the surge in network attack behavior, detecting malicious traffic has become a pivotal cybersecurity task. Many existing methods for malicious traffic detection rely on machine learning and deep learning, but they exhibit certain shortcomings: A considerable number of these methods rely on statistical features, which may lose their relevance as networks evolve and lead to the loss of important information. Additionally, Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN) face limitations in extracting features from network traffic, specifically, their inability to capture traffic interaction behavior information within a network flow. In this paper, we propose a Traffic Behavior Analysis model with Graph Neural Networks (TBA-GNN), which works directly with raw bytes and leverages the hierarchy structure of traffic (byte-packet-flow) to delve into valuable information. Firstly, we devise the PacketCNN to extract packet-level features from raw bytes. Subsequently, we construct a network flow as a Traffic Interaction Graph, containing both the traffic interaction behavior information and packet-level traffic information, and utilize the GNN to extract flow-level features. Finally, we perform a classification task to detect malicious traffic. We conduct extensive experiments on the ISCXIDS2012 and CICIDS2017 datasets, and the experimental results demonstrate that our model effectively identifies malicious traffic, outperforming baselines significantly. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Big-data-based network engineering recruitment data collection, warehousing, and analysis program 3

Big-data-based network engineering recruitment data collecti...

引用

3rd international conference on computer Vision and Data Mining, ICCVDM 2022

作者： Gao, Xinkai Guangzhou Institute of Science and Technology Guangzhou China Sun Yat-sen University Guangzhou China

ISBN: (纸本)9781510661363

In China,Network Engineering was officially established as an undergraduate major in 2012. Hundreds of thousands of Network Engineering graduates have entered the job market since 2016. What are their salary levels and employment quality? These are the major concerns of in-college Network Engineering students. Only by obtaining comprehensive, timely and reliable market frontier recruitment data, can they know what directions will bring higher salary and better growth space, thereby allocate their time more reasonably to learn the most beneficial courses. How to obtain timely, comprehensive and reliable cutting-edge recruitment data? This research introduces an automatic recruitment data collection, warehousing and analysis program based on big data. The program takes *** as the target website, scrapes all the network related recruitment data in Guangzhou from June 2021 to June 2022. Then stores and visually analyzes the data, and finally obtains the statistical data including total number of recruitment, average salary and the change curve of salary over working years for various posts in the network specialty. The statistical results show that Linux maintenance engineers and information security engineers have higher wages and better development prospects. These help guide Network Engineering students to determine their own direction of efforts. In addition, the data collection, storage and analysis process of this study has wide range of applicability, and can be extended to other situations that need data to assist decision-making. © COPYRIGHT SPIE.

关键词： Big data

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 << < 8 9 10 11 12 13 14 15 16 17 > >>

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：