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

4,743 篇 会议
55 册 图书
13 篇 期刊文献

馆藏范围

4,811 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

3,133 篇 工学
- 2,794 篇 计算机科学与技术...
- 2,208 篇 软件工程
- 1,245 篇 信息与通信工程
- 740 篇 控制科学与工程
- 691 篇 生物工程
- 666 篇 光学工程
- 511 篇 电气工程
- 454 篇 生物医学工程（可授...
- 400 篇 电子科学与技术（可...
- 299 篇 网络空间安全
- 182 篇 安全科学与工程
- 163 篇 机械工程
- 160 篇 仪器科学与技术
- 159 篇 交通运输工程
- 152 篇 动力工程及工程热...
- 152 篇 化学工程与技术
- 142 篇 石油与天然气工程
1,643 篇 理学
- 709 篇 生物学
- 637 篇 物理学
- 604 篇 数学
- 242 篇 化学
- 180 篇 统计学（可授理学、...
827 篇 管理学
- 463 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
433 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...
- 105 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

320 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

4,762 篇 英文
48 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 4811 条记录，以下是231-240 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：

ISAR image Registration Based on Normalized Correlation Coefficient 3

ISAR Image Registration Based on Normalized Correlation Coef...

引用

3rd ieee international conference on Power, Electronics and computer applications, ICPECA 2023

作者： Wu, Linhua Zhao, Lizhi Minzu University of China School of Information Engineering Beijing China

ISBN: (纸本)9781665472784

As an important part of attitude estimation for space target, the accuracy of ISAR image registration directly affects the result of attitude estimation. In this paper, we analyze the model of ISAR image registration and propose a novel method. First, the image is binarized to reduce the impact of echo SNR, and then the global normalized cross-correlation coefficient between the images is taken as the cost function to estimate the parameters with Snake Optimizer algorithm to achieve registration. The experiment proves the effectiveness of this method. © 2023 ieee.

关键词： image registration

来源：评论

学校读者我要写书评

暂无评论

Expoliting Confidence-Based Model Fusion for Boosting image Classification Accuracy 2

Expoliting Confidence-Based Model Fusion for Boosting Image ...

引用

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

作者： Jiang, Xinjian Nanjing University Department of Computer Science and Technology Jiangsu Nanjing210008 China

ISBN: (纸本)9798350331417

In the realm of deep learning, the traditional approach has been to train specialized models for individual tasks, which, although effective, is resource-intensive. The advent of large, universal models has mitigated this issue by offering multitask capabilities, reduced training time, and lower computational costs. However, these generalized models often underperform on specific tasks compared to specialized models. This paper introduces an innovative ensemble approach that integrates specialized and generalized models, specifically focusing on Contrastive Language-image Pretraining (CLIP) and EfficientNet. This work proposes three fusion strategies: Weighted Voting, Confidence Comparison, and Fully Connected Network Fusion, and evaluate them using the CIFAR-100 dataset. The ensemble model significantly outperforms individual models, achieving an adjusted accuracy of up to 0.848. The paper also introduces a novel evaluation metric, Confidence-Accuracy Correlation, to assess the reliability of model confidence. The findings could revolutionize ensemble learning by making it more adaptive and suited for real-world applications, thereby pushing the boundaries of possibility in artificial intelligence. © 2023 ieee.

关键词： CLIP deep learning image classification

来源：评论

学校读者我要写书评

暂无评论

image processing for Robotic Control in Life Science Laboratory Automation 5

Image Processing for Robotic Control in Life Science Laborat...

引用

5th international conference on Robotics and computer Vision, ICRCV 2023

作者： Yu, Haoying Møller, Vilhelm Krarup Frandsen, Rasmus John Normand Mansourvar, Marjan Department of Electrical Engineering Technical University of Denmark Copenhagen Denmark Department of Biotechnology and Biomedicine Technical University of Denmark Copenhagen Denmark

ISBN: (纸本)9798350326369

In the contemporary age of advanced technology, image processing plays a vital role as an efficient and indispensable tool across industries, enterprises, monitoring systems, and various applications. This study focuses on employing image processing techniques with an Opentrons industrial robot to ensure quality control during production. By leveraging the YOLOv5 model, the robot adeptly recognizes diverse pipette tip types, identifies liquids by their colors, and accurately measures liquid levels to estimate volume percentages within each tip. These detection results then guide a programmable robot, enabling it to perform specific actions on the tips based on predetermined parameters. This paper provides a comprehensive description of the methodology, implementation, and evaluation of our integrated control-robotic system, highlighting its potential to significantly enhance efficiency and precision in laboratory settings. © 2023 ieee.

关键词： Quality control

来源：评论

学校读者我要写书评

暂无评论

From Templates to Transformers: A survey of Multimodal image Captioning Decoders

From Templates to Transformers: A survey of Multimodal Image...

引用

2023 international conference on computer, Electronics and Electrical Engineering and their applications, IC2E3 2023

作者： Sharma, Himanshu Padha, Devanand Central University of Jammu Department of Computer Science and It Rahya-Suchani Jammu India

ISBN: (纸本)9798350338003

Automated text-to-image (image synthesis) and image-to-text (image captioning) generation are two of the most challenging and cutting-edge fields of study in computer Vision (CV) in conjunction with Natural Language processing (NLP). The image-to-text synthesis, also known as image Captioning (IC), has numerous applications in visual assistance, machine vision, remote security, healthcare, and remote sensing, among others. Since their origin, the IC frameworks have been constructed utilizing a two-subcomponent pipeline consisting of the visual feature extraction and natural language modeling subcomponents. The recent surge of interest in the applications of sequential deep learning models in machine translation has resulted in the development of efficient language modeling architectures. Deep sequential modeling architectures, such as Recurrent Neural Networks (RNN), Long Short Term Memory (LSTM), and Gated Recurrent Units (GRU), tackle the intricacies of the multi-modular space far better than existing machine learning-based translation approaches. The tremendous growth of deep language modeling architectures in IC necessitates a comprehensive review of its literature. In this survey, we conduct an exhaustive and analytical analysis of the language modeling architectures used in IC frameworks for caption generation, along with their training corpus datasets. We also identify a list of open research issues and potential research areas for future work. © 2023 ieee.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

END-TO-END LEARNED LIGHT FIELD image RESCALING USING JOINT SPATIAL-ANGULAR AND EPIPOLAR INFORMATION 30

END-TO-END LEARNED LIGHT FIELD IMAGE RESCALING USING JOINT S...

引用

30th ieee international conference on image processing (ICIP)

作者： Vinh Van Duong Thuc Nguyen Huu Yim, Jonghoon Jeon, Byeungwoo Sungkyunkwan Univ Dept Elect & Comp Engn Seoul South Korea

ISBN: (纸本)9781728198354

Light field (LF) rescaling is indispensable in accommodating different LF image resolutions for different applications. Unlikely most recent studies which only execute learned LF upscaling from a predefined downscaling method, we propose a novel LF rescaling framework by jointly optimizing learned LF downscaling and upscaling as a combined task. Specifically, our light field rescaling network (LFRN) simultaneously extracts features from different 2D subspaces of LF data (e.g., spatial-angular and epipolar subspaces) to fully handle 4D LF image information. Our newly designed attention fusion module (AFM) adaptively combines these two data features based on learnable embedding weights. Due to joint optimization of the learned LF downscaling and upscaling tasks, our LFRN method can achieve significant performance gain in both objective and subjective visual qualities compared to conventional predefined downscaling with learned LF upscaling task.

关键词： Convolutional neural network light field rescaling spatial-angular epipolar plane image

来源：评论

学校读者我要写书评

暂无评论

Research on the Auxiliary Training System of Tai Chi Fitness Qigong Based on computer 3D image Vision Technology

Research on the Auxiliary Training System of Tai Chi Fitness...

引用

image processing and computer applications (icipca), ieee international conference on

作者： Lin Wang Weifeng Deng Hainan Vocational University of Science and Technology Haikou China

Based on Kinect motion capture technology, this paper developed a set of auxiliary teaching software suitable for Tai Chi practice in view of the movement requirements of beginners. This teaching system can show students the standard moves of Tai Chi. A Kinect software system based on motion capture technology is established to realize the standardized measurement of motion capture. The collected data are filtered and de-nosed and stored to form a standard motion database. By collecting the data of the subjects' tai chi movement process, the subjects' movement process is presented in the form of color images in the interface window. The bone data is corresponding to the color image, and the key nodes in the image are identified. After the two sets of data are collected, the Dynamic Time Wide (DTW) method is used to deal with the corresponding frame matching problem. By assigning the rotation information of the connection points to the corresponding Unity3D human body model. Experiments show that the method adopts motion capture technology, DTW and other methods, and has been effectively coordinated with Unity3 3D simulation software for practice and scoring.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Occ²Net: Robust image Matching Based on 3D Occupancy Estimation for Occluded Regions

Occ<SUP>2</SUP>Net: Robust Image Matching Based on 3D Occupa...

引用

ieee/CVF international conference on computer Vision (ICCV)

作者： Fan, Miao Chen, Mingrui Hu, Chen Zhou, Shuchang MEGVII Technol Beijing Peoples R China

ISBN: (纸本)9798350307184

image matching is a fundamental and critical task in various visual applications, such as Simultaneous Localization and Mapping (SLAM) and image retrieval, which require accurate pose estimation. However, most existing methods ignore the occlusion relations between objects caused by camera motion and scene structure. In this paper, we propose Occ(2)Net, a novel image matching method that models occlusion relations using 3D occupancy and infers matching points in occluded regions. Thanks to the inductive bias encoded in the Occupancy Estimation (OE) module, it greatly simplifies bootstrapping of a multi-view consistent 3D representation that can then integrate information from multiple views. Together with an Occlusion- Aware ( OA) module, it incorporates attention layers and rotation alignment to enable matching between occluded and visible points. We evaluate our method on both real-world and simulated datasets and demonstrate its superior performance over state-of- the-art methods on several metrics, especially in occlusion scenarios.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LLIEFORMER: A LOW-LIGHT image ENHANCEMENT TRANSFORMER NETWORK WITH A DEGRADED RESTORATION MODEL 30

LLIEFORMER: A LOW-LIGHT IMAGE ENHANCEMENT TRANSFORMER NETWOR...

引用

30th ieee international conference on image processing (ICIP)

作者： Yi, Xunpeng Wang, Yuxuan Zhao, Yizhen Yan, Jia Zhang, Weixia Wuhan Univ Elect Informat Sch Wuhan Peoples R China Shanghai Jiao Tong Univ MoE Key Lab Artificial Intelligence Shanghai Peoples R China

ISBN: (纸本)9781728198354

Low-light image enhancement aims at improving human perception or the effectiveness of computer vision tasks of images taken in dark. The low-light images are usually seriously lack in visual information. To tackle this problem, we propose a general Low-light image Enhancement Transformer Network (LLIEFormer) with a degraded restoration model in this paper. The network of LLIEFormer synthesizes the advantages of Transformer to extract global information and convolutional neural networks to capture local details. We conduct extensive experiments on various low-illumination enhanced datasets including PairL1.6K and FiveK to demonstrate the effectiveness of our method. The results show that our LLIEFormer has better performance and wider applicability than other advanced methods. Our code will be available at https://***/xunpengyi/LLIEFormer.

关键词： Low-light image enhancement image restoration Transformer network

来源：评论

学校读者我要写书评

暂无评论

Efficient Approximate Vedic Multiplier: Design, Analysis, and Application in image Blending 2

Efficient Approximate Vedic Multiplier: Design, Analysis, an...

引用

2nd ieee international conference on computer Vision and Machine Intelligence, CVMI 2023

作者： Gupta, Sanjiv Kumar Yadav, Nilesh Kumar Dhawan, Amit Tiwari, Manish Jha, Sumit Kumar Motilal Nehru National Institute of Technology Department of Electronics and Communication Engineering Uttar Pradesh Allahabad211004 India

ISBN: (纸本)9798350305142

Approximate computing has become a widely recognized method for designing energy-efficient arithmetic architectures in the context of error-tolerant applications. This paper presents the design and analysis of a 4-bit approximate Vedic multiplier (AVMT) using the Urdhva Tiryagbhyam method. This Vedic approach, involving vertical and crosswise steps, outperforms traditional multiplication in terms of efficiency. An approximate 2-bit multiplier (AVM2) is designed, and an AVMT is proposed using AVM2. The proposed architecture has better propagation delay and less area utilization compared to other conventional multipliers. AVMT has an 11% reduction in area consumption and a 12% increase in processing speed compared to the exact Vedic multiplier. To assess its practicality in real-world scenarios, the proposed multiplier is integrated into an image-blending application. The results indicate that the system achieves a Structural Similarity Index (SSIM) average value of 0.91, which proves to be suitable for error-resilient image processing applications. © 2023 ieee.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

image Completion with Heterogeneously Filtered Spectral Hints 23

Image Completion with Heterogeneously Filtered Spectral Hint...

引用

23rd ieee/CVF Winter conference on applications of computer Vision (WACV)

作者： Xu, Xingqian Navasardyan, Shant Tadevosyan, Vahram Sargsyan, Andranik Mu, Yadong Shi, Humphrey SHI Lab UIUC Urbana IL 61801 USA UO Urbana IL 61801 USA Peking Univ Beijing Peoples R China Picsart AI Res PAIR Beijing Peoples R China

ISBN: (纸本)9781665493468

image completion with large-scale free-form missing regions is one of the most challenging tasks for the computer vision community. While researchers pursue better solutions, drawbacks such as pattern unawareness, blurry textures, and structure distortion remain noticeable, and thus leave space for improvement. To overcome these challenges, we propose a new StyleGAN-based image completion network, Spectral Hint GAN (SH-GAN), inside which a carefully designed spectral processing module, Spectral Hint Unit, is introduced. We also propose two novel 2D spectral processing strategies, Heterogeneous Filtering and Gaussian Split that well-fit modern deep learning models and may further be extended to other tasks. From our inclusive experiments, we demonstrate that our model can reach FID scores of 3.4134 and 7.0277 on the benchmark datasets FFHQ and Places2, and therefore outperforms prior works and reaches a new state-of-the-art. We also prove the effectiveness of our design via ablation studies, from which one may notice that the aforementioned challenges, i.e. pattern unawareness, blurry textures, and structure distortion, can be noticeably resolved. Our code will be open-sourced at: https://***/SHI-Labs/SH-GAN.

关键词： Deep learning computer vision image resolution Codes Filtering Transforms Benchmark testing

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 << < 20 21 22 23 24 25 26 27 28 29 > >>

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：