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

4,604 篇 会议
498 册 图书
70 篇 期刊文献

馆藏范围

5,171 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

3,380 篇 工学
- 2,744 篇 计算机科学与技术...
- 1,816 篇 软件工程
- 723 篇 信息与通信工程
- 720 篇 光学工程
- 667 篇 电气工程
- 415 篇 生物工程
- 359 篇 控制科学与工程
- 348 篇 生物医学工程（可授...
- 234 篇 机械工程
- 222 篇 电子科学与技术（可...
- 125 篇 仪器科学与技术
- 122 篇 化学工程与技术
- 116 篇 安全科学与工程
- 95 篇 交通运输工程
- 90 篇 材料科学与工程（可...
- 67 篇 建筑学
- 57 篇 土木工程
1,679 篇 理学
- 925 篇 物理学
- 721 篇 数学
- 452 篇 生物学
- 203 篇 统计学（可授理学、...
- 119 篇 化学
- 57 篇 系统科学
488 篇 管理学
- 268 篇 图书情报与档案管...
- 240 篇 管理科学与工程(可...
- 78 篇 工商管理
439 篇 医学
- 418 篇 临床医学
- 127 篇 基础医学(可授医学...
- 89 篇 药学(可授医学、理...
60 篇 法学
- 59 篇 社会学
54 篇 农学
35 篇 教育学
31 篇 艺术学
29 篇 经济学
11 篇 文学
10 篇 军事学

主题

817 篇 computer vision
624 篇 pattern recognit...
534 篇 image processing
353 篇 image processing...
347 篇 artificial intel...
337 篇 image segmentati...
279 篇 feature extracti...
208 篇 image recognitio...
174 篇 deep learning
155 篇 computer graphic...
151 篇 computer imaging...
140 篇 face recognition
123 篇 machine learning
123 篇 object recogniti...
117 篇 convolutional ne...
114 篇 image analysis
113 篇 object detection
108 篇 information syst...
105 篇 cameras
104 篇 computational mo...

机构

25 篇 istituto italian...
24 篇 google deepmind ...
24 篇 meta ai barcelon...
23 篇 politecnico di t...
14 篇 national center ...
14 篇 institute of ima...
10 篇 shanghai jiao to...
10 篇 tsinghua univers...
10 篇 university of ch...
10 篇 institute of aut...
9 篇 institute of ima...
9 篇 computer vision ...
8 篇 indian statistic...
8 篇 inria nancy gran...
8 篇 dalian universit...
8 篇 icube université...
8 篇 erasmus mc - uni...
8 篇 tencent jarvis l...
8 篇 university of ba...
7 篇 department of co...

作者

24 篇 cristian canton
24 篇 alessio del bue
24 篇 tatiana tommasi
24 篇 jordi pont-tuset
17 篇 de-shuang huang
14 篇 stefanie speidel
12 篇 wilfried philips
10 篇 mohamed kamel
9 篇 paul scheunders
9 篇 h. bischof
9 篇 jie yang
9 篇 stéphane cotin
9 篇 dan popescu
8 篇 umapada pal
8 篇 aurélio campilho
8 篇 yefeng zheng
8 篇 kok wai wong
8 篇 christian barill...
8 篇 ilias maglogiann...
8 篇 tieniu tan

语言

4,855 篇 英文
296 篇 其他
65 篇 中文

检索条件"任意字段=4th International Conference on Computer Vision, Pattern Recognition and Image Processing"

共 5172 条记录，以下是561-570 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：

Online Q&A for Machine Learning Courses Based on Formula recognition 4

Online Q&A for Machine Learning Courses Based on Formula Rec...

引用

4th international conference on Information Science and Education, ICISE-IE 2023

作者： Zhu, Xiaoke Chen, Xiaopan Li, Minghao Zhang, Tianxiang School of Computer and Information Engineering Henan University Kaifeng China Henan Engineering Research Center of Intelligent Technology and Application Henan University Kaifeng China Henan University Kaifeng Henan Key Laboratory of Big Data Analysis and Processing China

ISBN: (纸本)9798350394610

Mathematical formulas are ubiquitous in courses such as Machine Learning. Understanding these formulas is the primary challenge for studying of students. If a searchable knowledge base can be built for these formulas, it will help students learn. Accurate identification of these formulas is an important step in building and querying the knowledge base. However, mathematical formulas have complex two-dimensional and nested structures, which makes them inconvenient to search like ordinary text. this paper employs Faster R-CNN to detect regions containing mathematical formulas and improves its backbone network, anchor box dimensions, and pre-training network to make it more accurate and efficient in identifing these formulas. Furthermore, in order to enhance the features and meaningful representation of mathematical formulas in the input image, we introduce the distance transformation. Finally, comparative experiments were conducted on the publicly dataset GTDB. Our proposed approach achieved recognition rates of 91.22% and 85.74% for isolated and hybrid formulas detection. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Novel Edge AI with Power-Efficient Re-configurable LP-MAC processing Elements 4

Novel Edge AI with Power-Efficient Re-configurable LP-MAC Pr...

引用

4th international conference on Electrical, Communication and computer Engineering, ICECCE 2023

作者： Kamel, Mahmoud Madian, Ahmed Sobh, Ibrahim Digital Design Engineer NISC Research Center Nile University ST-Microelectronics Cairo Egypt Electronics Systems NISC Research Center Nile University Cairo Egypt Valeo Internal Automotive Software Egypt Cairo Egypt

ISBN: (纸本)9798350369694

Deep learning has become increasingly important in various fields, such as robotics, image processing, and speech recognition. However, the high computational requirements of deep learning models make it challenging to deploy them on edge & embedded devices with constrained power and area budgets. this paper proposes a novel low-power technique for implementing deep learning models on edge devices called LP-MAC (Low Power Multiply Accumulate). LP-MAC is designed for fixed-point format operations and takes advantage of reusing the input vector for MAC operations. It provides a new hardware design for the MAC unit, relying solely on adders, shifters, and multiplexers instead of multipliers, which consume more power. this makes LP-MAC more power-efficient with over 30% power reduction compared to conventional MAC. the LP-MAC technique offers efficient dynamically precision control of MAC operations, making it more power-efficient and real-time due to its low latency. these features make LP-MAC an ideal choice for implementing deep learning models on edge devices with low power budgets, particularly for Convolutional Neural Networks (CNNs), Fully Connected networks, and Transformer attention networks. the paper provides hardware implementations of such networks in addition to a methodology for upgrading any existing network to use LP-MAC instead of conventional MAC that uses multiplications. Additionally, an AHB-SLAVE co-processor of LP-MAC array has been designed for use in embedded devices. © 2023 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Bird Movement recognition Research Based on YOLOv4 Model 4

Bird Movement Recognition Research Based on YOLOv4 Model

引用

4th international conference on Artificial Intelligence and Advanced Manufacturing, AIAM 2022

作者： Zhao, Suyan Shandong University of Science and Technology Shandong Tai'an China

ISBN: (纸本)9781665463997

Taking the basic daily behavior of birds as the research object of this paper, the deep learning object detection algorithm is used to identify and detect the behavior and behavior of birds. Using the YOLOv4 model to extract features to complete the recognition of bird behavior and action and the location of birds, this study first crawled target images from the computer vision website and the China Bird Network, Pass the bird action image into the model after processing, and used the CSPdarknet network for feature extraction. Feature enhancement processing is carried out using PANet and SPP to expand the sensory field of view. In order to make the research results better applied to reality Finally, positioning and classification are implemented through the header layer. the yolo family of algorithms utilizes an end-to-end idea to revert to boundary locations and classifications using only a one-time feature extraction. this enables rapid capture and identification of bird targets, as well as real-time monitoring through OpenCV invocation of monitoring devices. the web front-end system is set up using the flask framework, and the results of model detection and recognition are passed to the backend to obtain more training data and optimize the model. the research shows that the yolov4 object detection and recognition algorithm can accurately capture the position of birds in images and videos and identify their behavior. the research of bird behavior and motion recognition is the exploration and prospect of deep learning algorithms in the biological field, which provides a feasible intelligent solution for the modernization of ecological civilization. © 2022 IEEE.

关键词： Birds

来源：评论

学校读者我要写书评

暂无评论

Fourth international conference on Signal processing and computer Science, SPCS 2023

Fourth International Conference on Signal Processing and Com...

引用

4th international conference on Signal processing and computer Science, SPCS 2023

ISBN: (纸本)9781510672505

the proceedings contain 152 papers. the topics discussed include: research on process route optimization method based on improved hybrid genetic algorithm;simulation of road;multi-node short-term power load forecasting model based on neural network ensemble;compressive sensing based one-bit sparse array direction-of-arrival estimation;directional modulation schemes in dual-function radar-communication system;elevator door motion recognition utilizing an imitation C3D network;radar radiation identification based on online transfer learning;inductance calculation and analysis of planar spiral coils in the wireless energy transmission system of implantable cardiac pacemaker;identification of Peking duck breed based on hyperspectral imaging with machine learning;and visible and near infrared image fusion based on texture information.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A computer vision Technology Applied in the Task of Mechanical Parts Inspection 4

A Computer Vision Technology Applied in the Task of Mechanic...

引用

4th international conference on Artificial Intelligence and Advanced Manufacturing, AIAM 2022

作者： Liu, Tianrui Zhou, Xumin Peking University School of Software and Microelectronics Beijing China

ISBN: (纸本)9781665463997

In this paper, based on the computer vision detection technology, the parts detection system is studied and discussed. this system mainly uses manual image segmentation and other methods, which can fully avoid the defects of image segmentation, improve the accuracy of image detection and ensure the detection speed. the system uses CCD or CMOS digital camera to capture the image of parts on the assembly line, which is roughly divided into three parts. First of all, it is necessary to take the template image that fully meets the quality requirements of the parts, and carry out preprocessing such as smooth filtering for the image taken. Second, during the test, the image of the component to be tested is taken on the assembly line, and the position of the detection target image and the standard template image is registered through the image registration algorithm. Finally, the image features of each partition area of the image to be detected are extracted and compared with the features of each partition area of the standard template image, so as to detect the processing quality of the assembly line parts, whether there is a component assembly error, error prompt and alarm, so as to achieve intelligent detection Purpose. © 2022 IEEE.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Detection of Plant Diseases and Recommendation of Plant Cycle using Machine Learning 4

Detection of Plant Diseases and Recommendation of Plant Cycl...

引用

4th international conference on Power, Energy, Control and Transmission Systems, ICPECTS 2024

作者： Divya, B. Alivn Ancy, A. Vivekanandan, G. Swapna, A. Kaniha, P. Indhu Priyadharshini, S. Sri Sai Ram Institute of Technology Dept of Computer Science and Engineering India Chennai Institute of Technology Dept of Electronics and Communication Engineering India

ISBN: (数字)9798331508845

ISBN: (纸本)9798331508845

Plant diseases create significant challenges to productivity in agriculture, food security, and ecological stability. Pathogens and environmental variables interact to cause plant diseases. Pathogens include various microorganisms like bacteria, fungi, and viruses, each with unique modes of spread. Environmental conditions such as temperature, humidity, and soil quality impact disease development and severity. the impacts of plant diseases are far-reaching. It affects crop yields and quality. Outbreaks of plant diseases can lead to economic losses, and food shortages which ultimately lead to hunger and poverty. Effective management of plant diseases requires an integrated approach that combines detection, preventive measures, cultural practices, and chemical interventions. the solution has two modules. the first module focuses on detection of plant diseases and its management. the second module focuses on recommendations of the plant cycle. Our proposed system utilizes CNN algorithms trained on a large amount of datasets. Using image analysis the features are extracted and patterns are recognized. therefore, the system can quickly identify the disorders.. the system also includes suggestions for preventive measures. the system integrates modules for recommending optimal plant cycles to the farmers and gardeners. It generates personalized recommendations for planting schedules and crop varieties. this system increases crop yields and decreases the risk of disease outbreaks. Our solution offers a holistic approach to plant health monitoring and management. © 2024 IEEE.

关键词： Productivity Plant diseases Pathogens Schedules Soil Feature extraction Stability analysis pattern recognition Crop yield thermal stability

来源：评论

学校读者我要写书评

暂无评论

RFNet: A Refinement Network for Semantic Segmentation 26

RFNet: A Refinement Network for Semantic Segmentation

引用

26th international conference on pattern recognition / 8th international Workshop on image Mining - theory and Applications (IMTA)

作者： Zhu, Guilin Wang, Runmin Han, Chang Liu, Yingying Ding, Yajun Liu, Minghao Liu, Li Sang, Nong Hunan Normal Univ Coll Informat Sci & Engn Changsha 410081 Peoples R China Wuhan Business Univ Lab Control & Applicat Technol Robot Wuhan 430056 Peoples R China Natl Univ Def Technol Sch Syst Engn Changsha 410000 Peoples R China Huazhong Univ Sci & Technol Sch Artif Intelligence & Automat Wuhan 430074 Peoples R China

ISBN: (数字)9781665490627

ISBN: (纸本)9781665490627

As one of the basic tasks of computer vision, semantic segmentation is widely used in many fields, e.g., medical images parsing, scene parsing, autonomous driving, etc. In the current mainstream approaches, downsampling or patching operation is required to ensure that the GPU memory is not overloaded for dealing with the high-resolution input images. However, the corresponding cost is the lack of details in the final segmentation map. In this work, we proposed RFNet, a refinement network which resolves the lack of detailed information in coarse predictions by fusing the coarse predictions and the fine predictions gained by fine input image patches. there are three key characteristics: (i) designing a spatial information extraction module which can efficiently process information in coarse and fine feature maps at spatial level. (ii) proposing an auxiliaryfusion information branch calculated from the prediction maps, which contribute to refine predictions. (iii) designing a boundary auxiliary loss function in the training process, which makes the model pay more attention to those pixels belonging to the boundary of objects. We show the superiority of the proposed RFNet on the Cityscapes dataset, the experimental results illustrate that ours RFNet performance outperforms other state-of-the-art approaches with low computation consumption. the codes will be available at: https://***/zhu-gl-ux/RFNet.

关键词： Training image color analysis Semantic segmentation image edge detection Memory management Graphics processing units Predictive models

来源：评论

学校读者我要写书评

暂无评论

Dyadic Interaction recognition Using Dynamic Representation and Convolutional Neural Network 1

引用

6th international conference on computer vision and image processing, CVIP 2021

作者： Shebiah, R. Newlin Arivazhagan, S. Centre for Image Processing and Pattern Recognition Department of Electronics and Communication Engineering Mepco Schlenk Engineering College Tamilnadu Sivakasi626005 India

ISBN: (数字)9783031113468

ISBN: (纸本)9783031113451

Human interaction recognition can be used in video surveillance to recognise human behaviour. the goal of this research is to classify human interaction by converting video snippets into dynamic images and deep CNN architecture for classification. the human interaction input video is snipped into a certain number of smaller segments. For each segment, dynamic image is constructed that efficiently encodes a video segment into an image with an action silhouette, which plays an important role in interaction recognition. the discriminative features are learned and classified from dynamic image using Convolutional Neural Network. the efficacy of the proposed architecture for interaction recognition is demonstrated by the obtained results on the SBU Kinect Interaction dataset, IXMAS, and TV Human Interaction datasets. © 2022, the Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Method for Predicting Skin Disease Using OM-Extreme Learning Machine 4

An Intelligent Method for Predicting Skin Disease Using OM-E...

引用

4th international conference on Smart Electronics and Communication, ICOSEC 2023

作者： Suja, G.P. Akshaya, M. Salim, Abu Sarfaraz, Mohd Kathiravan, Mathur Nadarajan Singh Pundir, Aditya Kumar Muslim Arts College Research Centre of Computer Science Tamilnadu Kanyakumari India Department of Cse Tamilnadu Coimbatore India College of Computer Science and Information Technology Jazan University Department of Computer Science Jazan Saudi Arabia College of Computer Science and Information Technology Jazan University Department of Information Technology and Security Jazan Saudi Arabia Dr N. G. P Arts and Science College Department of Biotechnology Tamil Nadu Coimbatore India Arya College of Engineering and Information Technology Department of Electronics and Communication Engineering Rajasthan Jaipur India

ISBN: (纸本)9798350300888

In terms of prevalence, skin disorders rank towards the top. Various organisms, including fungi, bacteria, allergens, viruses, and so on, can trigger skin illnesses. Improved speed and accuracy in the diagnosis of skin diseases has resulted from the development of lasers and Photonics-based medical technology. However, there is now a severe lack of affordable options for such diagnostics. therefore, at the outset, image processing techniques aid in constructing an automated screening system for dermatology. To aid in the categorization of skin disorders, feature extraction is essential. Several methods exist where computer vision can aid in the diagnosis of skin disorders. Skin infections are frequent in Saudi Arabia because of the country's scorching, desert climate. this proposed method adds to the literature on the early diagnosis of skin diseases. To help diagnose skin conditions, to recommended using image processing. this technique uses digital images of the affected skin to determine the disease kind through the application of image analysis. the method to offer straightforward, quick, and can be done with just a camera and a ***, feature extraction for segmentation, and model performance evaluation make up the suggested method. Preprocessing makes use of a histogram and an RGB to Grayscale conversion. Segmentation is performed with the help of adaptive thresholding. the GLCM, IQA, and complete reference methods are all utilized for feature extraction. Finally, OM-ELM is utilized to assess the model's performance. Comparing the suggested method to ELM and AE-ELM, it fares quite well. © 2023 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

image Repair and Restoration Using Deep Learning 4

Image Repair and Restoration Using Deep Learning

引用

4th international conference on Artificial Intelligence and Speech Technology, AIST 2022

作者： Cho, Rosa Kim Sood, Kanika Channapragada, Chinmayi Sree Chitra California State University Fullerton Department of Computer Science Fullerton United States

ISBN: (纸本)9781665499026

the art of image restoration lies in finding missing information inside the image and returning it back to its original state. While the field of fine arts and photographic restoration has been known and studied for years, recent technological advances have eliminated time-consuming processes and made image restoration far more feasible and easier to do. A novel method known as image inpainting has become a visionary tool for researchers in the field of image processing as digital picture editing has become more adaptable and image processing tools have improved. To understand how this method has become invaluable especially in the field of computer vision, we choose a deep learning technique that accepts multiple damaged photos as input undergoes training to construct a model to recognize missing information. We then validate the performance of the model to identify how well it can restore an image using multiple performance metrics. the process generates a series of successfully remastered images. © 2022 IEEE.

关键词： image reconstruction

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 << < 53 54 55 56 57 58 59 60 61 62 > >>

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：