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

4,746 篇 会议
55 册 图书
12 篇 期刊文献

馆藏范围

4,813 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

3,155 篇 工学
- 2,813 篇 计算机科学与技术...
- 2,227 篇 软件工程
- 1,264 篇 信息与通信工程
- 759 篇 控制科学与工程
- 691 篇 生物工程
- 668 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...
- 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
434 篇 医学
- 364 篇 临床医学
- 247 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

320 篇 image processing
312 篇 deep learning
231 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
51 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 4813 条记录，以下是461-470 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：

Decontamination Transformer For Blind image Inpainting 48

Decontamination Transformer For Blind Image Inpainting

引用

48th ieee international conference on Acoustics, Speech and Signal processing, ICASSP 2023

作者： Li, Chun-Yi Lin, Yen-Yu Chiu, Wei-Chen National Chiao Tung University Department of Computer Science Taiwan

ISBN: (纸本)9781728163277

Blind image inpainting aims at recovering the content from a corrupted image in which the mask indicating the corrupted regions is not available in inference time. Inspired that most existing methods for inpainting suffer from complex contamination, we propose a model that explicitly predicts the realvalued alpha mask and contaminant to eliminate the contamination from the corrupted image, thus improving the inpainting performance. To enhance the overall semantic consistency, the attention mechanism of transformers is exploited and integrated into our inpainting network. We conduct extensive experiments to verify our method against blind and non-blind inpainting models and demonstrate its effectiveness and generalizability to different sources of contaminant. © 2023 ieee.

关键词： Blind image inpainting Transformer

来源：评论

学校读者我要写书评

暂无评论

A Survey of AI Text-to-image and AI Text-to-Video Generators 4

A Survey of AI Text-to-Image and AI Text-to-Video Generators

引用

4th international conference on Artificial Intelligence, Robotics and Control, AIRC 2023

作者： Singh, Aditi Kent State University Department of Computer Science OH United States

ISBN: (纸本)9798350348248

Text-to-image and Text-to-Video AI generation models are revolutionary technologies that use deep learning and natural language processing (NLP) techniques to create images and videos from textual descriptions. This paper investigates cutting-edge approaches in the discipline of Text-to-image and Text-to-Video AI generations. The survey provides an overview of the existing literature as well as an analysis of the approaches used in various studies. It covers data preprocessing techniques, neural network types, and evaluation metrics used in the field. In addition, the paper discusses the challenges and limitations of Text-to-image and Text-to-Video AI generations, as well as future research directions. Overall, these models have promising potential for a wide range of applications such as video production, content creation, and digital marketing. © 2023 ieee.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Pothole Detection & Instance Detection Based on A Unified Approach for Globally Roads 1

Design and Implementation of Pothole Detection & Instance De...

引用

1st ieee international conference on Innovations in High Speed Communication and Signal processing, IHCSP 2023

作者： Pagale, Madhuri Mulik, Sunanda Purohit, Richa Thakare, Anuradha Jadhav, Sulaxan D y Patil International University Pune India Pimpri Chinchwad College of Engineering Pune India D y Patil International University Dept School of Computer Science Engineering and Applications Pune India Shri Balaji University Dept of Computer Science and Engineering Pune India Pune India

ISBN: (纸本)9798350345957

This work investigated the Pothole Identification and Instance Detection based on a Unified Approach to Global Roads. In this research, we developed Convolutional Neural Network(CNN) model to predict if a road is smooth or has potholes. Also, a Deep Neural Network(DNN) model was developed for instance detection. The research was carried out on the image dataset consisting of binary forms of smooth roads & potholes. The CNN model detected the instance on that side of the roadway. The bulk of pothole detection and instance detection research was based on deep learning techniques like CNN, DNN and Long-Short Time Memory. We succeeded to obtain an accuracy of 87% and a probability of 0.5348807 for pothole detection model. The experimental outcomes demonstrated the efficiency of the DNN methodology for instance detection. © 2023 ieee.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A Real Time Obstacle Detection Using Camera and Laser Line Generator 7

A Real Time Obstacle Detection Using Camera and Laser Line G...

引用

2023 7th international conference On Computing, Communication, Control And Automation, ICCUBEA 2023

作者： Dehankar, Sushank Dandawate, Akshay Gawade, Avishkar Bansode, Omkar Pawar, Atul PCCOE Dept. Computer Engineering Pune India

ISBN: (纸本)9798350304268

Detecting obstacles has been the major focus nowadays in the technological era. It has the most research subject over the last few decades. There are many applications which are using computer vision techniques such as security, surveillance, medical applications etc. Researchers have focused on coloured images where lighting is an important factor for images. As per their *** a scene and detecting objects is critical and camera and laser is used in this case. In this paper we will be able to take in live web cam image and highlights space where there are obstacles in the path. And the black area will demonstrate the free space available. By the help of laser line generator to assist in detecting the accuracy of obstacles through devices. The proposed model present in this paper present an effective model for obstacle detection using a camera and a laser line generator, on that system we can mount various devices such as robots, cars, helmets to test our model how effectively they are performing © 2023 ieee.

关键词： Camera CNN computer Vision image processing Laser Line Obstacle Detection

来源：评论

学校读者我要写书评

暂无评论

Improving image Classification with Quantum Neural Network

Improving Image Classification with Quantum Neural Network

引用

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

作者： Reejisha, R.A.S. Mohan, Anuraj Nss College of Engineering Department of Computer Science and Engineering Palakkad India

ISBN: (纸本)9798350338003

image classification is a fundamental task in computer vision that involves assigning labels to images based on their content. In recent years, deep learning techniques based on classical neural networks (CNN) have achieved modern performance on many image classification tasks. However, there is growing interest in using quantum neural networks (QNNs) for image classification, as quantum computing has the potential to improve the accuracy and speed of computation. We demonstrate the potential of our QNN model and QCNN model by applying it to the fashion MNIST dataset. The results indicate that the QNN model exhibits faster training speed and higher testing set accuracy compared to a QCNN with a similar architecture. © 2023 ieee.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Skin Lesion Classification Based on Segmented image 12

Skin Lesion Classification Based on Segmented Image

引用

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

作者： Dzieniszewska, Aleksandra Garbat, Piotr Piramidowicz, Ryszard Warsaw University of Technology Institute of Microelectronics and Optoelectronics Warsaw Poland

ISBN: (纸本)9798350325416

Early detection is crucial in successfully treating melanoma, considered one of the most lethal forms of skin cancer. Introducing an accurate and automated diagnosis method can increase accessibility and allow faster melanoma recognition, increasing patients' survival chances. Currently, deep learning based image processing techniques can be used to design such a system. One of the approaches to improve model performance is to combine the input image with a segmentation mask. Still, incorrect segmentation can lead to error propagation to further steps in the method. We present a method of combining a segmentation mask with a skin lesion image without permanent loss of information under the mask. We obscure unimportant parts of the image with Gaussian blur to draw network attention to a skin lesion, but information outside the mask can still be used. Such an approach leads to increased performance over the baseline model and robustness to inaccurate segmentation. Our best-performing model achieves an accuracy of 84.85% on the combined ISIC dataset. © 2023 ieee.

关键词： Dermatology

来源：评论

学校读者我要写书评

暂无评论

Simplifying Watermark Removal: Efficiently Enhancing Visual Integrity through Traditional image processing Techniques

Simplifying Watermark Removal: Efficiently Enhancing Visual ...

引用

2023 international conference on Evolutionary Algorithms and Soft Computing Techniques, EASCT 2023

作者： Motiramani, Maanaav Shinde, Abhitay Mukesh Patel School of Technology Management and Engineering Nmims Computer Engineering Mumbai India

ISBN: (纸本)9798350313413

This research paper presents a watermark removal technique for digital images using image processing methods, specifically thresholding with the Otsu method. Unlike complex deep learning algorithms, this approach focuses on simplicity and computational efficiency while achieving effective results. The Otsu method automatically determines an optimal threshold to separate the watermark from the background based on image segmentation. Experimental results demonstrate the efficacy of the proposed technique, showcasing high accuracy in removing watermarks with minimal distortion. Moreover, the method's computational efficiency makes it suitable for real-time applications. This research contributes to the field by highlighting the potential of traditional image processing techniques. The simplicity and interpretability of the approach make it accessible to researchers and practitioners with limited expertise in advanced methods. The results indicate promising performance in watermark removal for a diverse dataset of digital images with different watermark types and complexities. This research contributes valuable insights into effective and efficient watermark removal techniques, providing a practical solution for copyright protection, image authentication, and content restoration tasks. © 2023 ieee.

关键词： computational efficiency content preservation copyright protection digital images image authentication image processing image restoration noise reduction Otsu method post-processing real-time application thresholding traditional techniques visual integrity watermark removal

来源：评论

学校读者我要写书评

暂无评论

computer vision approach for motion blur image restoration system 14

Computer vision approach for motion blur image restoration s...

引用

14th international conference on Computing Communication and Networking Technologies, ICCCNT 2023

作者： Suresha, R. Jayanth, R. Shriharikoushik, M.A. Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science Mysuru Campus India

ISBN: (纸本)9798350335095

This paper presents a method for removing motion blur using the Inception ResNetv2 architecture. The proposed method combines Laplacian-variance-based classification with Inception ResNetv2 model tuning to achieve excellent inaccuracy. First, the Laplacian variance of the image is calculated, and based on this value, the image is classified into high, medium or low blur categories using quartile classification. The Inception ResNetv2 model is then tuned using hyperparameters to produce a blurred image. The proposed method is assessed using reference materials and compared to cutting-edge methods. Our results shows that it executes well with an average PSNR of 39.84. The proposed method also shows the better visual quality of out-of-focus images with more accurate, detailed edges and textures. The proposed method provides a reliable and efficient solution to eliminate motion inaccuracy. The combination of Laplacian-variance-based classification and Inception ResNetv2 model tuning provides a robust and efficient framework for motion blur removal with promising results that can be applied to different image processing applications © 2023 ieee.

关键词： image classification

来源：评论

学校读者我要写书评

暂无评论

image Forgery Detection Using CNN 1

Image Forgery Detection Using CNN

引用

1st international conference on Computational Intelligence for Information, Security and Communication applications, CIISCA 2023

作者： Geetha, Gear Chandana, Komarapalem Siri Gudelli, Madhavi Khasim, K.N.V. Gokaraju Rangaraju Institute of Engineering and Technology Department of ECE Telangana India

ISBN: (纸本)9798350339727

One of the biggest issues nowadays is picture forgeries or manipulation utilising various techniques. change of the original picture is not only done by the pic modification itself, but also who imitate as original to commit crimes. Forensic digital techniques are required to identify image modification and manipulation for such unlawful intentions. Inside the article, the intro of deep learning-based system for detecting picture modification that has produced outstanding results in recent studies. A convolutional neural network that has been shown effective for image processing is used initially. In addition, using a high pass filter the hidden features in picture are gathered comparatively semantic data. Gaussian blurring, median filtering, and other techniques are used to create changed photos for the studies. Boss Base 1.01 pictures with a resolution of 256x256 that were divided into 4 equal sections were resized and given additive white Gaussian noise addition. The performance of the suggested method is tested quantitatively, and image modification is identified. © 2023 ieee.

关键词： High pass filters

来源：评论

学校读者我要写书评

暂无评论

Towards Universal image Embeddings: A Large-Scale Dataset and Challenge for Generic image Representations

Towards Universal Image Embeddings: A Large-Scale Dataset an...

引用

ieee/CVF international conference on computer Vision (ICCV)

作者： Ypsilantis, Nikolaos-Antonios Chen, Kaifeng Cao, Bingyi Lipovsky, Mario Dogan-Schonberger, Pelin Makosa, Grzegorz Bluntschli, Boris Seyedhosseini, Mojtaba Chum, Ondrej Araujo, Andre Czech Tech Univ VRG FEE Prague Czech Republic Google Mountain View CA 94035 USA

ISBN: (纸本)9798350307184

Fine-grained and instance-level recognition methods are commonly trained and evaluated on specific domains, in a model per domain scenario. Such an approach, however, is impractical in real large-scale applications. In this work, we address the problem of universal image embedding, where a single universal model is trained and used in multiple domains. First, we leverage existing domain-specific datasets to carefully construct a new large-scale public benchmark for the evaluation of universal image embeddings, with 241k query images, 1.4M index images and 2.8M training images across 8 different domains and 349k classes. We define suitable metrics, training and evaluation protocols to foster future research in this area. Second, we provide a comprehensive experimental evaluation on the new dataset, demonstrating that existing approaches and simplistic extensions lead to worse performance than an assembly of models trained for each domain separately. Finally, we conducted a public research competition on this topic, leveraging industrial datasets, which attracted the participation of more than 1k teams worldwide. This exercise generated many interesting research ideas and findings which we present in detail. Project webpage: https://***/univ_emb/

关键词：

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 << < 43 44 45 46 47 48 49 50 51 52 > >>

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：