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

4,745 篇 会议
55 册 图书
12 篇 期刊文献

馆藏范围

4,812 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

3,154 篇 工学
- 2,814 篇 计算机科学与技术...
- 2,228 篇 软件工程
- 1,265 篇 信息与通信工程
- 761 篇 控制科学与工程
- 691 篇 生物工程
- 666 篇 光学工程
- 530 篇 电气工程
- 454 篇 生物医学工程（可授...
- 419 篇 电子科学与技术（可...
- 300 篇 网络空间安全
- 182 篇 安全科学与工程
- 164 篇 机械工程
- 160 篇 仪器科学与技术
- 159 篇 交通运输工程
- 153 篇 动力工程及工程热...
- 153 篇 化学工程与技术
- 143 篇 石油与天然气工程
1,643 篇 理学
- 709 篇 生物学
- 636 篇 物理学
- 605 篇 数学
- 242 篇 化学
- 180 篇 统计学（可授理学、...
828 篇 管理学
- 464 篇 图书情报与档案管...
- 443 篇 管理科学与工程(可...
- 119 篇 工商管理
434 篇 医学
- 363 篇 临床医学
- 246 篇 基础医学(可授医学...
- 214 篇 药学(可授医学、理...
- 106 篇 公共卫生与预防医...
125 篇 法学
- 109 篇 社会学
95 篇 农学
45 篇 经济学
44 篇 文学
33 篇 教育学
12 篇 军事学

主题

321 篇 image processing
312 篇 deep learning
230 篇 image segmentati...
191 篇 signal processin...
172 篇 image classifica...
167 篇 image enhancemen...
162 篇 computer vision
140 篇 image recognitio...
138 篇 convolutional ne...
136 篇 feature extracti...
125 篇 training
115 篇 machine learning
96 篇 computer applica...
83 篇 neural networks
83 篇 computational mo...
79 篇 visualization
78 篇 object detection
71 篇 natural language...
69 篇 semantics
68 篇 artificial intel...

机构

24 篇 chitkara univers...
17 篇 maharishi school...
15 篇 lovely professio...
15 篇 tianjin universi...
13 篇 university of ch...
12 篇 the islamic univ...
12 篇 beijing institut...
11 篇 school of comput...
11 篇 centre of interd...
10 篇 peng cheng labor...
10 篇 graphic era hill...
9 篇 national univers...
9 篇 sun yat-sen univ...
9 篇 school of comput...
9 篇 vivekananda glob...
9 篇 college of compu...
8 篇 harbin engineeri...
8 篇 school of comput...
8 篇 maharishi school...
8 篇 gla university d...

作者

13 篇 chauhan rahul
11 篇 yang yang
10 篇 anand vatsala
8 篇 kukreja vinay
8 篇 gupta rupesh
7 篇 luo xiaonan
7 篇 zhao yang
6 篇 bin wang
6 篇 pei jihong
6 篇 kumar ankit
6 篇 choudhury tanupr...
6 篇 zhu ce
6 篇 ce zhu
6 篇 kumar gaurav
6 篇 bing li
6 篇 li wei
5 篇 gill kanwarparta...
5 篇 zhiguo cao
5 篇 nagaraj p.
5 篇 singh kamred udh...

语言

4,761 篇 英文
50 篇 其他
17 篇 中文
1 篇 土耳其文

检索条件"任意字段=2023 IEEE International Conference on Image Processing and Computer Applications, ICIPCA 2023"

共 4812 条记录，以下是421-430 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：

Separated Frequency Loss with Distinguished Weight for images Generation

Separated Frequency Loss with Distinguished Weight for Image...

引用

2023 international conference on computer applications Technology, CCAT 2023

作者： Wei, Jian Wang, Qinzhao Army Academy of Armored Force Department of Weaponry and Control Beijing China

ISBN: (纸本)9798350301540

Deep neural network models are more and more widely used in image reconstruction and generation tasks. By setting various loss functions, the model adaptively generates images that meet the corresponding constraints, which has a positive effect on improving image quality and enriching diversity. As an important image processing method, two-dimensional Fourier transform is widely used for image filtering and denoising, but its role has not been further explored. Based on the background of the fine-grained target image reconstruction task, this paper proposes a differentiated weight loss function based on frequency domain space in view of the problem that the global loss function of fixed constraints in the past brings great bias to model parameter update. The distinguishing regional weight coefficient is stetted by separating the high and low frequency regions, thus, to alleviate the high-frequency information introduced by the fine-grained target due to the diverse changes of individual morphology and environmental background. The model parameter update process gains much smoother with the guidance of separated frequency loss. Experimental results show that by setting the differentiated frequency domain region weight loss function, the model generates higher quality images in both image reconstruction and generation tasks. © 2023 ieee.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Invariant Convolutional Networks 12

Invariant Convolutional Networks

引用

12th international conference on image processing Theory, Tools and applications, IPTA 2023

作者： Lebl, Matej Flusser, Jan Institute of Information Theory and Automation Czech Academy of Sciences Dept. of Image Processing Prague Czech Republic

ISBN: (纸本)9798350325416

Neural networks are often trained on datasets, that are not fully representative of the expected query images. Many times, the difference stem from the query images being taken in sub-optimal conditions. The most common defects are rotation, scale, blur, noise and intensity & contrast change which were all thoroughly studied and described. In this paper we propose a novel neural network architecture which is invariant to such degradations by design. We incorporate the knowledge build for classical methods directly into the network architecture providing an alternative to the augmentation of the training dataset. In the experiments, the proposed solution outperforms the classical augmentation technique in both accuracy and computational resources needed. © 2023 ieee.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

A Real-Time Text Analysis System 47

A Real-Time Text Analysis System

引用

47th ieee-computer-Society Annual international conference on computers, Software, and applications (COMPSAC)

作者： Chi Mai Nguyen Phat Trien Thai Duy Khang Lam Van Tuan Nguyen Viettel High Technol Ind Corp Command Control Ctr Ho Chi Minh City Vietnam

ISBN: (纸本)9798350326970

We live in an age of information overload. Manual information processing is increasingly overwhelmed with the enormous amount of information created by the explosive growth of news portals and online social networks. Such a situation calls for an automatic system that can support the process of handling, analyzing, and filtering information, especially information from online sources. In this work, we proposed a text analysis system that automatically collects, extracts, and analyses information from public-source-text documents such as news portals and social media networks. The proposed system can handle both long and short-text documents. It also has real-time features and is not restricted by any input data domain. The system can be used in different domains, such as scientific research, marketing, and security-related domains. Moreover, the system is engineered in modules and is flexible. Each module is an independent microservice that can be used as a separate standalone application. The system is also extensible since new modules can be added easily.

关键词： text analysis system data mining natural language processing

来源：评论

学校读者我要写书评

暂无评论

TSFC: TEXTURE AND STRUCTURE FEATURES COUPLING FOR image INPAINTING 30

TSFC: TEXTURE AND STRUCTURE FEATURES COUPLING FOR IMAGE INPA...

引用

30th ieee international conference on image processing (ICIP)

作者： Liu, Lu Wang, Qi Yu, Wenxin Chen, Shiyu Gong, Jun Chen, Peng Southwest Univ Sci & Technol Mianyang Sichuan Peoples R China Southwest Automat Res Inst Mianyang Sichuan Peoples R China Chengdu Hongchengyun Technol Co Ltd Chengdu Peoples R China

ISBN: (纸本)9781728198354

image inpainting has made significant progress benefiting from the advantages of convolutional neural networks (CNNs). Deep learning-based methods have shown extraordinary performance in this field. In this paper, we propose a novel image inpainting architecture with pure CNN that can jointly reconstruct the structure and texture of the image. Our generative network architecture (TSFC) consists of two parallel stages: structure generation and texture generation. In the structure generation stage, we use the large convolution kernel, which is highly neglected in modern networks, using the effective perceptual field of the large convolution kernel to enhance the perception of overall structural features. In the texture generation stage, we use the small convolution kernel to extract local texture features. Qualitative and quantitative experimental results on CelebA-HQ and Paris Street View datasets demonstrate the effectiveness and superiority of our method.

关键词： image Inpainting Encoder-decoder Network computer Vision Deep Learning

来源：评论

学校读者我要写书评

暂无评论

Defect Detection of Wood Grain images with image Gradient Applied to AE-based generation 6

Defect Detection of Wood Grain Images with Image Gradient Ap...

引用

6th ieee international conference on Knowledge Innovation and Invention, ICKII 2023

作者： Si, Jongwook Kim, Sungyoung Kumoh National Institute of Technology Department of Computer Ai Convergence Engineering Gumi Korea Republic of Kumoh National Institute of Technology Department of Computer Engineering Gumi Korea Republic of

ISBN: (纸本)9798350323535

Detecting and managing various types of defects that occur in the manufacturing process is important for product quality control. Detecting flaws in product presentation is an ongoing research topic in computer vision. Recently, deep learning technology has been used to improve defect detection performance compared to traditional computer vision methods. In this study, we proposed a new method for detecting defects on the surface of wooden boards using image reconstruction with an autoencoder-based model and image gradient filters in image processing using edge detection. Although the reconstruction performance of the autoencoder is significantly inferior to the newest technologies, this characteristic is used to remove noise from input images. We used the publicly available anomaly detection dataset, MV-Tec AD, for training and evaluation and presented experimental results focusing on the "Wood"category. The proposed method in this study demonstrated better detection performance with image processing. © 2023 ieee.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Two-stage image inpainting method based on transformer and Fast Fourier convolution 2

Two-stage image inpainting method based on transformer and F...

引用

2nd international conference on image processing, computer Vision and Machine Learning, ICICML 2023

作者： Li, Changxing Chen, Zhuang Chongqing University of Posts and Telecommunications School of Software Engineering Chongqing China Chongqing University of Technology School of Computer Science and Engineering Chongqing China

ISBN: (纸本)9798350331417

In view of the insufficient ability of the currently existing deep learning-based methods to repair image high-frequency information and the small sensory field of the traditional convolutional methods. A two-stage image repair model is proposed. First, Transformer is used to repair the image initially;second, Fourier convolution is used to construct a generative network to refine the high-frequency details of the image;finally, the repair results are input into the discriminator for training to obtain the final image repair model. The experimental results on street view datasets show that the model in the paper has better restoration results in high-frequency details as well as semantic information;compared with mainstream methods, It achieves better results in peak signal-to-noise ratio and structural similarity. © 2023 ieee.

关键词： Generative adversarial network image inpainting multiple attention Receptive field

来源：评论

学校读者我要写书评

暂无评论

Research on Automatic Workpiece Sorting System Based on Machine Vision 3

Research on Automatic Workpiece Sorting System Based on Mach...

引用

2023 ieee 3rd international conference on Data Science and computer Application, ICDSCA 2023

作者： Ji, Linfeng Zhenjiang Vocational Technical College Zhenjiang China

ISBN: (纸本)9798350341546

This paper expounds the automatic recognition method of parts based on computer vision. The feature database of the processed parts is constructed by using machine learning method. image preprocessing, threshold segmentation, edge and contour extraction are used to analyze the features of the image of the inspected part to judge whether the inspected part is qualified or not. Aiming at the attitude error generated when the workpiece is placed, a method for positioning the center of gravity and rotation angle of the workpiece based on boundary detection and contour tracking is proposed. Use the similarity measure to determine the characteristics of the object to be processed. Simulation results show that the method proposed in this paper is effective. © 2023 ieee.

关键词： image processing Machine vision pattern recognition workpiece

来源：评论

学校读者我要写书评

暂无评论

AREF-Net: Bridging Residual, Efficient, and Attention-Based Architectures for image Classification

AREF-Net: Bridging Residual, Efficient, and Attention-Based ...

引用

2023 international conference on Advanced Computing and Communication Technologies, ICACCTech 2023

作者： Ansari, Adib Marken, Gagandeep Shobhit, Shobhit Dongre, Purvansh Chandigarh University Department of Mathematics Gharuan India Chandigarh University Department of Computer Science Engineering Gharuan India

ISBN: (纸本)9798350380880

In this study, we introduce AREF-Net (Attention-based Residual Efficient Fusion Network), an advanced CNN architecture that integrates attention processes, efficient scaling, and the principles of residual connections. AREF-Net excels at identifying complex image patterns by focusing on essential elements and muting less important ones. It subtly enhances model depth, width, and resolution through scaling techniques, facilitating the learning of hierarchical representations. We elaborate on AREF-Net's architecture, experimental setup, data processing, and training methods. Empirical evaluations on CIFAR-10 showcase its competitive performance. AREF-Net holds great promise for advancing computer vision in deep learning, offering versatility and robustness for various applications. Its integration of attention mechanisms and efficient scaling sets a precedent for future CNN research, opening new avenues for complex visual data processing. © 2023 ieee.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Disparity Estimation with Deep Feature Parallel Transformation 2

Disparity Estimation with Deep Feature Parallel Transformati...

引用

2nd international conference on image processing, computer Vision and Machine Learning, ICICML 2023

作者： Yue, Xin Lu, Zongqing Tsinghua Shenzhen International Graduate School Division of Information Science and Technology Shenzhen China

ISBN: (纸本)9798350331417

We propose a feature parallel transformation module to strength the matching ability in stereo. We obtain additional information from input images, enhance features from the feature extraction module and design a parallel cascading module to fuse the features, which have rich global information. In addition, our feature transformation modules can be applied to any existing stereo networks in a plug and play manner. Our simple yet effect module can perform outstandingly on stereo benchmarks. © 2023 ieee.

关键词： component Deep learning,Feature Transformation Parallel propagation Stereo matching

来源：评论

学校读者我要写书评

暂无评论

image to Text: Comprehensive Review on Deep Learning Based Unsupervised image Captioning 2

Image to Text: Comprehensive Review on Deep Learning Based U...

引用

2nd ieee international conference on Futuristic Technologies, INCOFT 2023

作者： Shetty, Aishwarya D Shetty, Jyothi Department of Cse Nitte India Visvesveraya Technological University Belagavi590018 India

ISBN: (纸本)9798350308846

The task of image captioning has seen considerable success using deep neural networks. This assessment offers a thorough overview of the most cutting-edge approaches for deep learning-based unsupervised image captioning. In order to bridge the gap between computer vision and natural language processing, the effort of creating meaningful textual captions for images is known as image captioning. Without using annotated image-caption pairings for training, unsupervised approaches try to provide captions. The review examines a variety of techniques, including generative adversarial networks (GANs), pre-training, transfer learning, and convolutional neural networks (CNNs) for extracting visual features, as well as recurrent neural networks (RNNs) or transformer models for language modelling. Researchers and practitioners can benefit from this survey's observations, classification of methodologies, and recommendations for the future of deep learning-based unsupervised image captioning. © 2023 ieee.

关键词： computer Vision deep learning Natural Language processing Unsupervised image captioning

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482页 << < 39 40 41 42 43 44 45 46 47 48 > >>

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：