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

1,132 篇 会议
5 册 图书
3 篇 期刊文献

馆藏范围

1,140 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

772 篇 工学
- 628 篇 计算机科学与技术...
- 513 篇 软件工程
- 446 篇 生物工程
- 264 篇 信息与通信工程
- 250 篇 光学工程
- 157 篇 生物医学工程（可授...
- 87 篇 控制科学与工程
- 64 篇 安全科学与工程
- 60 篇 电气工程
- 47 篇 电子科学与技术（可...
- 46 篇 化学工程与技术
- 40 篇 交通运输工程
- 29 篇 机械工程
- 28 篇 材料科学与工程（可...
- 24 篇 仪器科学与技术
- 24 篇 农业工程
561 篇 理学
- 455 篇 生物学
- 226 篇 物理学
- 115 篇 数学
- 61 篇 统计学（可授理学、...
- 47 篇 化学
171 篇 管理学
- 103 篇 图书情报与档案管...
- 72 篇 管理科学与工程(可...
- 41 篇 工商管理
124 篇 医学
- 112 篇 临床医学
- 102 篇 基础医学(可授医学...
- 86 篇 药学(可授医学、理...
56 篇 农学
- 55 篇 作物学
32 篇 法学
- 30 篇 社会学
21 篇 教育学
- 21 篇 教育学
18 篇 经济学
7 篇 艺术学
1 篇 军事学

主题

240 篇 deep learning
139 篇 computer vision
73 篇 convolutional ne...
50 篇 object detection
42 篇 computational mo...
40 篇 feature extracti...
39 篇 training
37 篇 image classifica...
36 篇 accuracy
30 篇 image segmentati...
26 篇 convolution
22 篇 visualization
21 篇 machine learning
20 篇 computer archite...
17 篇 deep neural netw...
17 篇 face recognition
17 篇 image recognitio...
16 篇 neural networks
16 篇 convolutional ne...
15 篇 generative adver...

机构

16 篇 college of compu...
9 篇 chitkara univers...
8 篇 aviation univers...
7 篇 college of compu...
7 篇 school of comput...
4 篇 the state key la...
4 篇 college of compu...
4 篇 intelligent poli...
4 篇 national qinghai...
4 篇 school of comput...
4 篇 school of comput...
3 篇 school of comput...
3 篇 guangdong univer...
3 篇 computer science...
3 篇 chennai
3 篇 national key lab...
3 篇 computer science...
3 篇 school of comput...
3 篇 harbin institute...
3 篇 department of co...

作者

7 篇 liu bing
6 篇 bing liu
6 篇 zhaohao zhong
6 篇 zhong zhaohao
4 篇 mahamudul hasan
4 篇 kulkarni uday
4 篇 xueliang bao
4 篇 hasan mahamudul
4 篇 bao xueliang
4 篇 yuanyuan dang
4 篇 chikkamath satis...
4 篇 dang yuanyuan
3 篇 rishabh sharma
3 篇 bhattacharjee de...
3 篇 kukreja vinay
3 篇 krejcar ondrej
3 篇 mukesh kumar
3 篇 kumar manoj
3 篇 rakhra manik
3 篇 manik rakhra

语言

1,095 篇 英文
45 篇 其他
7 篇 中文

检索条件"任意字段=4th International Conference on Computer Vision, Image and Deep Learning, CVIDL 2023"

共 1140 条记录，以下是1-10 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：

2023 4th international conference on computer vision, image and deep learning, cvidl 2023

2023 4th International Conference on Computer Vision, Image ...

引用

4th international conference on computer vision, image and deep learning, cvidl 2023

ISBN: (纸本)9798350326444

the proceedings contain 136 papers. the topics discussed include: comparison of image generation methods based on diffusion models;research on image preprocessing and target detection of vehicle-machine cooperative system;a research on traditional tangka image classification based on visual features;research on image recognition based on neural network model learning algorithm;research on image recognition based on reinforcement learning;low-quality image binarization method based on threshold array system;comprehensive study of image processing techniques for low-altitude target recognition;visual cryptography scheme by freeform optics based on optimal mass transport;SPECT bone scan image classification by fusing multi-attention mechanism with deep residual networks;fine-grained image recognition method based on input perception joint probability prediction;deep learning in image classification: an overview;auricular images with annotations for segmenting key-organ mapping regions in auricular diagnosis;insulator image dataset generation based on generative adversarial network;structure-preserving domain adaptation network for generating pencil sketches;underwater image recovery method considering target polarization characteristics;and a dual attention network for multimodal remote sensing image matching.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamic Color Identification Using computer vision: OpenCV with Pandas 4

Dynamic Color Identification Using Computer Vision: OpenCV w...

引用

4th international conference on Sentiment Analysis and deep learning, ICSADL 2025

作者： Mohanraj, E. Kirubashini, V. Gobika, B. Archana, A.M. K.S. Rangasamy College of Technology Department of Artificial Intelligence and Data Science Tamil Nadu India

ISBN: (纸本)9798331523923

computer vision, the cornerstone of modern artificial intelligence. Moving forward with the development of new tools and techniques, OpenCV (Open Source computer vision Library) coupled with pandas' powerful data management capabilities has emerged as a versatile framework for real-world image processing tasks. this paper explores the application of OpenCV and pandas for real-time color recognition and OpenCV's enhanced functionality, such as video stream processing taking advantage of Pandas with efficient data management. the proposed system captures real-time images and processes user-defined interactions to identify the color. By combining pandas, the system optimizes access to the predefined color data stored in a CSV file, allowing for seamless color matching. this OpenCV and pandas together enables the system to dynamically display color names, RGB components and hex values in real time enhancing user interaction by double clicking. the combination of these technologies represents a powerful method for solving image-based problems for innovation and efficiency. Real world applications demonstrate their capabilities. © 2025 IEEE.

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

Cataract Detection and Classification Using YOLOv9 and Machine learning 4

Cataract Detection and Classification Using YOLOv9 and Machi...

引用

4th international conference on Sentiment Analysis and deep learning, ICSADL 2025

作者： Suryawanshi, Falguni Reddy, Ktv Department of Computer Science and Design Wardha India

ISBN: (纸本)9798331523923

Cataracts, a common age-related eye condition characterized by the clouding of the eye's natural lens, can impair vision if left untreated. Advances in cataract surgery have significantly improved treatment outcomes, but complications like posterior capsule rupture (PCR) still pose risks. Early detection is crucial, and recent developments in machine learning, particularly the YOLOv9 deep learning model, have shown promise in automating cataract detection using medical images such as eye scans. YOLOv9 can be trained to identify cataracts by recognizing distinct features like lens cloudiness and opacities. By leveraging image classification techniques and data augmentation, YOLOv9 achieves high accuracy in real-time cataract detection, assisting healthcare professionals in timely diagnoses and improving clinical workflows. Additionally, this model supports telemedicine applications by enabling remote analysis, expanding access to ophthalmic care. this paper highlights the significance of automated cataract detection using YOLOv9, its impact on early diagnosis, and its potential to enhance patient outcomes in ophthalmology through efficient image classification systems. © 2025 IEEE.

关键词： Ophthalmology

来源：评论

学校读者我要写书评

暂无评论

Real-Time Detection of Wrong-Way Vehicles Using YOLO and image Processing Techniques 4

Real-Time Detection of Wrong-Way Vehicles Using YOLO and Ima...

引用

4th international conference on Sentiment Analysis and deep learning, ICSADL 2025

作者： Celin, J. Jeya A Jeswin, J. Faizaan, A. Mohamed Babu, A.P. Chandru Anisto, M. Arul Kalasalingam Academy of Research and Education Department of Information Technology Tamil Nadu Virudhunagar India

ISBN: (纸本)9798331523923

Due to delayed notice and incorrect identification, wrong-way driving is a major traffic safety concern that frequently results in accidents. We describe a computer vision and deep learning based real-time wrong-way vehicle identification system to tackle these issues. To identify cars in video footage and follow their movements within predetermined zones, the system makes use of the YOLO (You Only Look Once) algorithm. It correctly detects instances of driving in the incorrect direction by analysing direction, and it promptly issues warnings by sending out email notifications with pictures of the vehicles and sounding an alert. According to evidence from experiments, the system is a useful tool for increasing road safety because it improves the efficiency of detection, decreases error rates, and speeds up response times. © 2025 IEEE.

关键词： deep learning

来源：评论

学校读者我要写书评

暂无评论

AI -Driven Detection of Gastrointestinal Disease based on Advanced deep learning Techniques 4

AI -Driven Detection of Gastrointestinal Disease based on Ad...

引用

4th international conference on Sentiment Analysis and deep learning, ICSADL 2025

作者： Izankar, Sakshi V. Puri, Chetan Burle, Rushikesh Computer Science and Design Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Maharashtra Wardha India Artificial Intelligence and Machine Learning Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Maharashtra Wardha India

ISBN: (纸本)9798331523923

Esophageal, gastric, and colorectal cancers (CRC) are some of the gastrointestinal (GI) cancers threatening global health with CRC being particularly concerning due to its high fatality rate. While early diagnosis is crucial in improving treatment efficiency, barriers such as image noise and visual subjective assessments during diagnostics such as colonoscopies often render it inconceivable. For better diagnostic accuracy in detecting gastrointestinal disease via endoscopic images, the research explores whether highly advanced artificial intelligence (AI) models such as vision Transformers (ViTs) and pre-trained DenseNet201 can be effective. We compare these models to popular deep learning techniques such as Support Vector Machines (SVM), ResNet50, VGG19, and GoogleNet. At a training accuracy of 99.9% and a validation accuracy of 98.8%, experiments on the KVASIR dataset indicate that vision Transformer is superior to other models since it can learn long-range dependencies. the robustness of deep learning models for identifying GI disease is exemplified by the superior performance of DenseNet201, ResNet50, and InceptionV3, all of which possess high accuracy, precision, and recall values. the paper illustrates the potential of vision Transformers, when combined with transfer learning and pre-trained CNN models, to revolutionize endoscopic diagnoses and provide a valuable resource to help physicians manage gastrointestinal conditions more effectively. © 2025 IEEE.

关键词： Endoscopy

来源：评论

学校读者我要写书评

暂无评论

Advancing Healthcare Diagnostics with a Hybrid AI Model 4

Advancing Healthcare Diagnostics with a Hybrid AI Model

引用

4th international conference on Sentiment Analysis and deep learning, ICSADL 2025

作者： Jihane, Benbrik Salma, Rattal Kamal, Ghoumid Miloud, Ar-Reyouchi El Ensao Mohammed i University Dept. Electronics Informatics and Telecommunications Oujda Morocco Abdelmalek Essaâdi University Dept. Telecommunication and Computer Science Tétouan Morocco

ISBN: (纸本)9798331523923

Artificial intelligence (AI) has significantly impacted the field of healthcare by advancing medical diagnostics and decision-making processes. this paper presents a unified framework that integrates Convolutional Multi-Layer Perceptrons (Conv MLP), Convolutional Neural Networks (ConvNet), and vision Transformers (ViTs) to address two critical tasks: sentiment analysis of medical reports and medical image recognition. By leveraging the distinct strengths of each architecture, the proposed hybrid model improves performance, effectively balancing computational efficiency, localized feature extraction, and global dependency modeling. the findings demonstrate that the model reduces task-specific errors and enhances convergence rates, achieving superior results in sentiment and image recognition tasks. this study advances the field of medical AI by overcoming the limitations of single-architecture models and establishing the feasibility of hybrid systems for robust, multi-modal applications. © 2025 IEEE.

关键词： Multilayer neural networks

来源：评论

学校读者我要写书评

暂无评论

Multi Class Spectral Discriminative Convolutional Neural Network Towards Hyperspectral image Classification of Crop Disease on Inclusion of Spectral Spatial Feature Fusion Mechanism 4

Multi Class Spectral Discriminative Convolutional Neural Net...

引用

4th international conference on Sentiment Analysis and deep learning, ICSADL 2025

作者： Boopathi Raja, A.S. Poovarasan, K. Udhayakiran, S. Muhammed Aleem, Shaik tharageswari, K. Karpagam Academy of Higher Education Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798331523923

Crop diseases occurs due to bacterial, viral, parasitic and fungal infection leads to various challenges to farmer and agricultural based business as crop diseases effects the normal growth of the crop and it spreads to other crops surrounding it. Especially those crop infection leads to great economic damage to the farmers and to the entire country. In order to prevent, classify and mitigate those crop infections, effective measures have to be carried out. Manual observation by biologist and agriculturist leads to misinterpretation and time consuming. In particular, remote sensing technologies using hyperspectral imaging techniques helps to monitor and acquire the agriculture information in various target regions effectively. Due to development of computer vision technique and artificial intelligence approaches in form of machine learning and deep learning architectures, countermeasure against the crop disease can be achieved easily on processing the acquired information in form of hyperspectral images. However traditional architecture faces multiple challenges in form of the spectral signatures unmixing as boundaries of the objects of different diseases types is very complex to be filtered. thus, a new spectral unmixing based object recognition method has to be constructed to categorizes different form of crop disease in the agriculture region. In this paper, Multi Class Spectral Discriminative Convolution Neural Network(MCSD-CNNN) using spectral and spatial feature fusion towards hyperspectral image classification for detect, classify and mitigate the crop diseases on various climate and various regions. Initially image preprocessing is carried out to eliminate the spectral noises. Preprocessed image is projected to convolution layer of the network to extract the endmembers of the spectral band representing the various crop species in the different climate and spatial regions. Extracted end member of the spectral band is represented spectral disease index map. th

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Innovative Object Detection with YOLOv4 and Adaptive Bounding Boxes 4

Innovative Object Detection with YOLOv4 and Adaptive Boundin...

引用

4th international conference on Sentiment Analysis and deep learning, ICSADL 2025

作者： Senbagavalli, M. Mahapatra, Sheila Jhansi, Sane CoE Computer Vision Alliance University Dept. of Cse & It Bangalore India Alliance University Department of Eee Bangalore India CoE Computer Vision Alliance University Dept. of Cse Bangalore India

ISBN: (纸本)9798331523923

this research work proposes a computer vision-based object detection system. It can recognize each and every object visible in the picture. Horizontal boundary boxes were used to detect different objects available in the detectors. However, buildings and cars in the aerial imagery are occasionally very close to form continuous objects that may suggest a direction. therefore, some approaches such as extending the horizontal bounding box to oriented box are proposed for a better object extraction;usually via directly regressing the angle or corners. Here we propose an orientation object detector which is simple but more accurate, and it is based on YOLOv4. Here yolov4 is used to detect objects yolo can able to find more than one object in a single image. the paper will contain specific implementation methodology for yolov4 with OpenCV, which includes model configuration settings, preprocessing steps and evaluation matrices such as mean average precision (map), recall and the precision. the object detection problem has transformed into a key problem in computer vision and has enabled improvements in areas including self-driving cars, medical systems, and even surveillance systems. In this paper, we present a new object detection system based on YOLOv4 which stands for 'You Only Look Once' version four and uses adaptive bounding boxes. the CSPDarknet-53 and spatial pyramid pooling (SPP) are the main reasons for YOLOv4's immense popularity, as is discussed in the literature. But with the constant changes of the bounding boxes, performance accuracy suffers greatly as they have a difficult time identifying the objects bounding boxes are placed within. To counter this problem, we present an explainable adaptive bounding box technique which relies heavily on the size shape and features of the context of the object being captured. the learnable bounding box adjustment layer which serves to refine the localized bounding boxes is integrated into the head of YOLOv4, where puttin

关键词： deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Person Re-Identification Using Siamese Triplet Network 4

Person Re-Identification Using Siamese Triplet Network

引用

4th international conference on Sentiment Analysis and deep learning, ICSADL 2025

作者： Menon, Aparna Yashwanthika, R. Shreya, J.V. Somasundaram, K. thangavel, Senthil Kumar Asawa, Shreeya Amrita School of Computing Department of Computer Science and Engineering Amrita Vishwa Vidyapeetham Coimbatore India Amrita School of Physical Sciences Department of Mathematics Amrita Vishwa Vidyapeetham Coimbatore India

ISBN: (纸本)9798331523923

Due to the increasing demand for public safety and the rapid development of intelligent surveillance networks, the re-identification of individuals (Re-ID) has become one of the most important research topics in computer vision. Person re-identification (Re-ID) has a wide range of applications, which increases its popularity in recent studies. the main goal of person re-identification (Re-ID) is to retrieve people with the same identity from different cameras. In the open world, there are still some challenges. First, existing re-ID research usually assumes that only one-factor variable (view, clothing, pedestrian pose, pedestrian occlusion, image resolution, RGB/IR modality) changes, and ignores the complexity of multi-factor variables in the open world. Second, existing ID methods are overly dependent on clothing color and other obvious pedestrian features that can be easily obscured or changed. In addition, the lack of benchmark datasets that include multifactor variables hinders the practical application of ID in the open world. the proposed model uses a deep learning model -Siamese triplet network to extract the features, and a similarity measure to re-identify the individual. the evaluation metrics used are cumulative matching features (CMC) and mean average precision (mAP). Preliminary results show that the model performs well in comparison to existing methods, and future work will focus on improving robustness under varying environmental conditions. © 2025 IEEE.

关键词： Reamers

来源：评论

学校读者我要写书评

暂无评论

Machine vision and image processing for intelligent online monitoring and control of pharmaceutical fluidized bed granulation processes 4

Machine vision and image processing for intelligent online m...

引用

4th international conference on computer vision, Application, and Algorithm, CVAA 2024

作者： Liu, Yan Wu, Tao Wang, Xue Zhong Beijing Key Laboratory of Enze Biomass Fine Chemicals College of New Materials and Chemical Engineering Beijing Institute of Petrochemical Technology Beijing102617 China

ISBN: (数字)9781510687622

ISBN: (纸本)9781510687615

Fluidized bed granulation is a unit operation widely used in the pharmaceutical, chemical and food processing industries. It is a manufacturing technology that by suspending lose powders using hot air and transforms the powders into granules of uniform sizes to improve compaction and flow characteristics. the granule size distribution and moisture content are important quality indicators that are currently characterized by sampling and offline analysis in the laboratory, leading to time delay in measurement. this work reports an investigation of machine vision combined with deep learning image segmentation for on-line real-time monitoring. A non-invasive microscopic imaging probe with an integrated light source is designed and mounted on the granulator’s sight glass to monitoring the granule dynamic changes in particle morphology and size. In addition, a near-infrared spectrometer combined with chemometric modeling is used for real-time monitoring of moisture content. © 2025 SPIE.

关键词： Near infrared spectroscopy

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114页 << < 1 2 3 4 5 6 7 8 9 10 > >>

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：