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

5,918 篇 会议
128 册 图书
82 篇 期刊文献

馆藏范围

6,128 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

3,640 篇 工学
- 2,997 篇 计算机科学与技术...
- 1,522 篇 软件工程
- 940 篇 信息与通信工程
- 841 篇 电气工程
- 714 篇 生物工程
- 396 篇 生物医学工程（可授...
- 388 篇 光学工程
- 366 篇 控制科学与工程
- 144 篇 电子科学与技术（可...
- 129 篇 机械工程
- 105 篇 仪器科学与技术
- 102 篇 网络空间安全
- 100 篇 安全科学与工程
- 86 篇 化学工程与技术
- 75 篇 动力工程及工程热...
- 69 篇 交通运输工程
1,468 篇 理学
- 755 篇 生物学
- 649 篇 物理学
- 355 篇 数学
- 126 篇 统计学（可授理学、...
- 99 篇 化学
749 篇 医学
- 660 篇 临床医学
- 185 篇 基础医学(可授医学...
- 122 篇 药学(可授医学、理...
- 83 篇 特种医学
- 66 篇 公共卫生与预防医...
514 篇 管理学
- 276 篇 管理科学与工程(可...
- 274 篇 图书情报与档案管...
- 75 篇 工商管理
89 篇 农学
- 86 篇 作物学
49 篇 法学
34 篇 教育学
18 篇 经济学
9 篇 军事学
8 篇 文学
2 篇 艺术学
1 篇 哲学

主题

1,169 篇 convolutional ne...
1,132 篇 deep learning
902 篇 neural networks
656 篇 machine learning
623 篇 training
496 篇 feature extracti...
349 篇 accuracy
276 篇 computational mo...
248 篇 image classifica...
246 篇 image segmentati...
245 篇 image processing
226 篇 computer vision
218 篇 image recognitio...
190 篇 deep neural netw...
182 篇 visualization
170 篇 artificial intel...
169 篇 transfer learnin...
159 篇 computer archite...
158 篇 convolution
149 篇 support vector m...

机构

23 篇 chitkara univers...
10 篇 university of el...
9 篇 karnataka bangal...
9 篇 information syst...
9 篇 harbin institute...
8 篇 shanghai jiao to...
8 篇 school of comput...
8 篇 carnegie mellon ...
8 篇 school of comput...
7 篇 hefei university...
7 篇 south china norm...
7 篇 tongji universit...
7 篇 nanyang technolo...
7 篇 tech univ munich...
6 篇 chongqing univer...
6 篇 maharishi school...
6 篇 school of comput...
6 篇 univ chinese aca...
6 篇 king saud univer...
6 篇 department of co...

作者

14 篇 eyas el-qawasmeh
13 篇 de-shuang huang
8 篇 azizah abd manaf
7 篇 andrea vedaldi
7 篇 horst bischof
7 篇 mohana
7 篇 lazaros iliadis
7 篇 roy kaushik
6 篇 haijun zhang
6 篇 tianyong hao
6 篇 jan-michael frah...
6 篇 thomas brox
6 篇 zhou wu
6 篇 gokhan bilgin
6 篇 rueckert daniel
6 篇 liu chang
6 篇 zhao zhang
6 篇 chrisina jayne
5 篇 li li
5 篇 włodzisław duch

语言

5,893 篇 英文
179 篇 其他
47 篇 中文
34 篇 土耳其文
1 篇 俄文

检索条件"任意字段=Conference on Applications of Neural Networks and Machine Learning in Image Processing IX"

共 6128 条记录，以下是161-170 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：

Application of machine learning Algorithms in Artificial Intelligence image Recognition Technology 1

Application of Machine Learning Algorithms in Artificial Int...

引用

1st International conference on Intelligent Systems and Computational networks, ICISCN 2025

作者： Ouyang, Qi Dai, Siyang Xie, Kexin Sun, Zeyu Wang, Yao Polytechnic of Milan Milan Italy Faculty of Engineering and Information Technology The University of Melbourne VIC Australia College of Business and Public Management Wenzhou-Kean University Wenzhou China School of Environment and Science Griffith University Brisbane Australia Nanjing Stomatological Hospital Affiliated Hospital of Medical School Institute of Stomatology Nanjing University Nanjing China

ISBN: (纸本)9798331529246

In smart city applications such as medical image analysis, autonomous driving, and security monitoring, image recognition faces challenges like complex backgrounds, low-quality images, and diverse targets, affecting accuracy and robustness. This study explores machine learning algorithms to enhance image recognition performance by addressing noise interference, intricate backgrounds, and feature extraction difficulties. It combines Convolutional neural networks (CNN) with transfer learning, starting with data preprocessing to reduce noise, using pre-trained CNN models to extract high-level features, and fine-tuning with a ResNet transfer learning strategy for specific tasks. Additionally, ensemble learning methods are employed to further improve model robustness and accuracy. Experimental results show that the ensemble model maintains around 85% accuracy even with high background complexity, and transfer learning achieves 90% accuracy when the sample size reaches 1000. These findings demonstrate that transfer and ensemble learning effectively enhance image recognition accuracy and resilience in complex environments. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Performance Test of Holographic Video Communication System

Performance Test of Holographic Video Communication System

引用

International conference on Multimedia Computing, Networking and applications (MCNA)

作者： Kara, Kubra Lloret, Jaime Romero, Oscar Sendra, Sandra Univ Politecn Valencia Inst Invest Gest Integrada Zonas Costeras C Paranimf 1 Valencia 46730 Spain

ISBN: (纸本)9798350354744;9798350354737

Holography creates three-dimensional (3D) images with depth and relief, and can be applied to medicine, engineering, and entertainment, enabling holographic communication, live streaming, and virtual gatherings. Digital holography involves using digital displays, cameras, and beams. This paper discusses various holographic systems, including computational holography, which uses computers to produce 3D images, Deep Holography (DH), which utilizes deep neural networks (DNN), and tensor holography, which combines DNN and machine learning (ML) to produce 3D images in mid-air. This paper also addresses network challenges, such as the high data transmission, bandwidth limitations that can hinder the quality of the holographic image, and the low latency crucial for maintaining real-time interaction in holographic communication. While some scholars introduce the capacities of 6G networks, other authors propose a compression and differentiated prioritization technique. Holography can create striking images using convolutional neural networks (CNN) and an anti-aliasing double-phase (AA-DPM) method. Based on the communication performance test that has been carried out, it can be concluded that ensuring access to powerful and optimized hardware and software is crucial for both text and holographic image generation. As the complexity and length of the text increase, processing time augments as well. There are significant differences between using powerful servers and weaker hardware. Finally, it can be concluded that it is imperative to prioritize hardware and software for image generation to facilitate a smooth conversation.

关键词： Digital holography Network infrastructure image quality Technical resource Performance test

来源：评论

学校读者我要写书评

暂无评论

Accelerating Sparse Convolutional neural networks with Systolic Arrays on FPGA

Accelerating Sparse Convolutional Neural Networks with Systo...

引用

conference on applications of machine learning

作者： Nehete, Hemkant Verma, Gaurav Yadav, Shailendra Kaushik, Brajesh Kumar Indian Inst Technol Roorkee Dept Elect & Commun Engn Roorkee 247667 Uttar Pradesh India

ISBN: (纸本)9781510665651;9781510665644

Convolutional neural networks (CNNs) are frequently used in a wide range of applications, including speech, image recognition and natural language processing. However, due to the computational complexity of CNNs, deploying these networks on resource-limited edge devices has become a significant challenge. Sparse CNNs use the sparsity in the weight matrices of the networks to minimize computations while maintaining accuracy. By storing only the nonzero values, the Compressed Sparse Row (CSR) format compresses the sparse matrix, lowering the memory requirement and computational complexity of the network. This work presents a novel approach for accelerating Sparse CNNs on Field-Programmable Gate Arrays (FPGAs) using the CSR format and systolic arrays. The proposed method takes advantage of systolic arrays' parallel processing capabilities to perform CSR-based sparse convolutions. Furthermore, an algorithm has been presented that optimizes the data layout to maximize data reuse and minimize data movement between different processing elements of the systolic array and external memory. The architecture is evaluated and compared to a state-of-the-art GPU implementation on several benchmark datasets. The proposed architecture outperformed the GPU-based implementation in terms of throughput and power efficiency by 1.42x and 22.4x, respectively. The presented approach provides a promising solution for accelerating Sparse CNNs on resourceconstrained devices and enabling the deployment of these networks in a variety of applications.

关键词： Sparse CNN Accelerator FPGA Compressed Sparse Row (CSR) Systolic array

来源：评论

学校读者我要写书评

暂无评论

Estimation of the optimal number of neurons in extreme learning machine using simulated annealing and the golden section 9

Estimation of the optimal number of neurons in extreme learn...

引用

9th International conference on Days of Applied Mathematics (ICDAM)

作者： Gelvez-Almeida, E. Mora, M. Huerfano-Maldonado, Y. Salazar-Jurado, E. Martnez-Jeraldo, N. Lozada-Yavina, R. Baldera-Moreno, Y. Tobar, L. Univ Catolica Maule Lab Invest Tecnol Reconoc Patrones Talca Chile Univ Simon Bolivar Fac Ciencias Basicas & Biomed San Jose De Cucuta Colombia Univ Catolica Maule Fac Ciencias Basicas Talca Chile Univ Tecnol Peru Fac Ciencias & Ingn Lima Peru

Extreme learning machine is a neural network algorithm widely accepted in the scientific community due to the simplicity of the model and its good results in classification and regression problems;digital image processing, medical diagnosis, and signal recognition are some applications in the field of physics addressed with these neural networks. The algorithm must be executed with an adequate number of neurons in the hidden layer to obtain good results. Identifying the appropriate number of neurons in the hidden layer is an open problem in the extreme learning machine field. The search process has a high computational cost if carried out sequentially, given the complexity of the calculations as the number of neurons increases. In this work, we use the search of the golden section and simulated annealing as heuristic methods to calculate the appropriate number of neurons in the hidden layer of an Extreme learning machine;for the experiments, three real databases were used for the classification problem and a synthetic database for the regression problem. The results show that the search for the appropriate number of neurons is accelerated up to 4.5x times with simulated annealing and up to 95.7x times with the golden section search compared to a sequential method in the highest-dimensional database.

关键词： Simulated annealing

来源：评论

学校读者我要写书评

暂无评论

MSCNet: Multi-Scale Connected Network for image Denoising

MSCNet: Multi-Scale Connected Network for Image Denoising

引用

International Joint conference on neural networks (IJCNN)

作者： Gao, Lijun Jin, Xiao Zhang, Youzhi Wang, Suran Sun, Zeyang Shenyang Aerosp Univ Sch Comp Sci Shenyang Liaoning Peoples R China

ISBN: (纸本)9798350359329;9798350359312

image denoising aims to enhance image quality and visual effects, finding extensive applications in various fields such as digital photography, medical imaging, video processing, and image restoration. Although deep learning-based denoising methods have made significant progress, the post-denoising results often suffer from information loss and blurring, and the network structures tend to be complex. To address these challenges, this study proposes a Multi-Scale Connected Network for image Denoising (MSCNet) based on U-net. Specifically, this paper introduces a skip connection designed to effectively fuse shallow fine-grained information and deep semantic information, thereby improving the effects of information transmission and integration. Additionally, a channel-wise attention mechanism and a non-linear module involving point-wise multiplication of half-channel activations are presented, aiming to extract more abundant semantic features while reducing network computation. Experimental results on multiple datasets validate that, compared to other denoising methods, MSCNet demonstrates superior denoising performance.

关键词： image denoising U-net skip connection attention mechanism non-linear

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Study on Deep learning Techniques used for SAR and Optical image Registration

A Comprehensive Study on Deep Learning Techniques used for S...

引用

2024 International conference on Artificial Intelligence and Quantum Computation-Based Sensor applications, ICAIQSA 2024

作者： Harshini, R. Kumari, Prameela N. School of ECE REVA University Bengaluru India

ISBN: (纸本)9798331517953

In this paper reviews recent advancements in deep learning-based remote sensing image processing, focusing on image registration, classification, and segmentation. Remote sensing faces challenges due to geometric, radiometric, and spectral differences between various imaging modalities like Synthetic Aperture Radar (SAR) and optical images. Traditional methods struggle with these discrepancies, especially in multimodal datasets. Recent deep learning techniques, such as Convolutional neural networks (CNNs) and Generative Adversarial networks (GANs), have significantly improved accuracy in image alignment, feature extraction, and data fusion. This review synthesizes key studies that address these challenges and highlights future research opportunities to enhance remote sensing applications through deep learning models. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

An Overview Comparison between Convolutional neural networks and Vision Transformers 24

An Overview Comparison between Convolutional Neural Networks...

引用

7th International conference on Networking, Intelligent Systems and Security, NISS 2024

作者： Oubadriss, Adib Laassiri, Jalal Makrani, Adil El Laboratory of Research in Informatics Fs Uit Kenitra Morocco

ISBN: (纸本)9798400709296

Deep learning is having a particularly revolutionary effect in the field of artificial intelligence, namely in computer vision, where machines are equipped with the capacity to comprehend and evaluate visual information. Throughout history, convolutional neural networks, or CNNs, have been essential for image processing applications because of their superior hierarchical feature extraction capabilities. Presenting Vision Transformers (ViTs), a revolutionary approach that applies transformer topologies originally intended for natural language processing to computer vision. With an emphasis on how well CNNs and ViTs perform in image processing, this article provides a thorough comparison of the two models. With a focus on image processing, the article aims to give researchers and practitioners a better understanding of computer vision methodologies by analyzing state-of-the-art of recent researches in different fields examining their mechanisms, architectural structures, and effectiveness in handling visual data. This will help them make informed decisions in this ever-changing field. © 2024 ACM.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

An Exhaustive Survey on the Methods and applications of Graph neural networks 8th

An Exhaustive Survey on the Methods and Applications of Grap...

引用

8th International conference on Information Science, Communication and Computing

作者： Fan, Dong Cheng, Jieren Tang, Xiangyan Lu, Kai Hainan Univ Sch Comp Sci & Technol Haikou 570228 Hainan Peoples R China Hainan Blockchain Technol Engn Res Ctr Haikou 570228 Hainan Peoples R China Sch Cyberspace Secur Sch Cryptol Haikou 570228 Hainan Peoples R China Hainan Vocat Coll Polit & Law Dept Publ Safety Technol Haikou 571100 Hainan Peoples R China

ISBN: (纸本)9789819617838;9789819617814;9789819617807

The widespread use of deep learning has achieved unprecedented success. neural networks have achieved remarkable results in natural language processing, image recognition and other application fields. The key to the success of neural networks lies in its efficient processing of Euclidean space data, but the results obtained when traditional neural networks are used in non-Euclidean spaces are often not satisfactory to researchers. Graph neural network has been widely developed as a neural network that can be used in non-Euclidean space. This paper starts with the basic knowledge of graphs, introduces graph neural networks, and makes a new classification of them. Then it illustrates its application from 18 application areas. Finally, I put forward my own views on the future development and challenges of graph neural networks.

关键词： Graph neural networks Convolution Recurrent Graph Generation Euclidean non-Euclidean

来源：评论

学校读者我要写书评

暂无评论

Development Of An image Restoration Algorithm Utilizing Generative Adversarial networks (GAN’s) For Enhanced Performance In Engineering applications: A Comprehensive Approach To Improving image Quality And Clarity Through Advanced machine learning Techniques

Development Of An Image Restoration Algorithm Utilizing Gene...

引用

2024 IEEE International conference on Innovation and Novelty in Engineering and Technology, INNOVA 2024

作者： Manjunath, T.C. Pavithra, G. Samyama Gunjal, G.H. Ninawe, Swapnil S. Dept. of Electronics & Communication Engineering Rajrajeswari College of Engineering Bangalore India Department of Electronics & Communication Engineering Dayananda Sagar College of Engineering Karnataka Bangalore India Department of Computer Science & Engineering University Visvesvaraya College of Engineering Karnataka Bangalore India

ISBN: (纸本)9798331505134

image restoration, a critical task in computer vision and image processing, focuses on recovering degraded or damaged images to their original, high-quality state. This paper introduces an innovative approach to image restoration using Generative Adversarial networks (GANs). GANs, a prominent deep learning framework, consist of two neural networks—a generator and a discriminator—that compete to produce and evaluate realistic images. The generator creates images, while the discriminator distinguishes between real and generated ones, refining the generator's capability through adversarial training. Leveraging GANs' ability to learn complex image features, the proposed algorithm restores degraded images affected by noise, blur, and low resolution, producing high-quality, realistic results. Simulation outcomes demonstrate significant advancements in image restoration, showcasing GANs as a powerful tool for addressing challenges in this domain. The study underscores the potential of GANs in generating visually appealing restorations and advancing the state-of-the-art in image processing and restoration tasks. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

A CROSS DOMAIN GENERATIVE NETWORK FOR ACCELERATED MRI 31

A CROSS DOMAIN GENERATIVE NETWORK FOR ACCELERATED MRI

引用

2024 International conference on image processing

作者： Ibrahim, Vazim Paul, Joseph Suresh Cochin Univ Sci & Technol Ernakulam 682022 Kerala India Indian Inst Informat Technol & Management Kerala Trivandrum 695581 Kerala India Digital Univ Kerala Sch Informat Trivandrum 695317 Kerala India

ISBN: (纸本)9798350349405;9798350349399

Compressed sensing (CS) is a method for accelerating MRI acquisition by acquiring less data through undersampling of Fourier space (k-space). Existing deep learning-based CSMRI methods are commonly concerned with optimizing datadriven network models with input undersampled data points and an efficient learning framework. Generative modelling is a learning framework employed in different applications for learning an abstract distribution of observed data and thereby generating new data points similar to the true features. In this regard, the current work proposes a Generative Adversarial Network (GAN) based Cross Domain Extrapolation Generative Adversarial Network (CdE-GAN) that incorporates an extrapolation mechanism through decoder-type architectural design to represent the fine details with a large set of pixels. The results obtained from the experiments show that the extrapolation network enables robust and accurate estimation of missing frequencies, alleviating the structural artifacts at higher acceleration/downsampling factors compared to state-of-the-art methods.

关键词： Compressed Sensing MRI Super-Resolution MRI Generative Adversarial Network Cross-domain networks Convolutional neural Network

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 << < 13 14 15 16 17 18 19 20 21 22 > >>

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：