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

15,153 篇 会议
233 篇 期刊文献
229 册 图书
3 篇 学位论文

馆藏范围

15,618 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

8,092 篇 工学
- 5,417 篇 计算机科学与技术...
- 2,792 篇 软件工程
- 2,445 篇 电气工程
- 1,573 篇 信息与通信工程
- 1,006 篇 控制科学与工程
- 833 篇 光学工程
- 572 篇 电子科学与技术（可...
- 552 篇 生物医学工程（可授...
- 549 篇 机械工程
- 507 篇 仪器科学与技术
- 414 篇 生物工程
- 285 篇 测绘科学与技术
- 204 篇 航空宇航科学与技...
- 189 篇 交通运输工程
- 180 篇 材料科学与工程（可...
- 145 篇 安全科学与工程
- 119 篇 化学工程与技术
4,111 篇 理学
- 2,774 篇 物理学
- 1,130 篇 数学
- 467 篇 生物学
- 325 篇 系统科学
- 271 篇 统计学（可授理学、...
- 146 篇 化学
1,618 篇 医学
- 1,440 篇 临床医学
- 215 篇 特种医学
- 201 篇 基础医学(可授医学...
- 134 篇 药学(可授医学、理...
858 篇 管理学
- 515 篇 管理科学与工程(可...
- 378 篇 图书情报与档案管...
- 130 篇 工商管理
77 篇 法学
68 篇 农学
42 篇 经济学
40 篇 教育学
27 篇 文学
25 篇 军事学
20 篇 艺术学
1 篇 哲学

主题

2,703 篇 image processing
1,407 篇 image segmentati...
1,150 篇 signal processin...
805 篇 real-time system...
750 篇 feature extracti...
748 篇 cameras
552 篇 image edge detec...
540 篇 signal processin...
478 篇 image reconstruc...
470 篇 image coding
447 篇 algorithm design...
377 篇 deep learning
370 篇 object detection
345 篇 hardware
344 篇 computer vision
339 篇 accuracy
337 篇 image color anal...
335 篇 real time system...
333 篇 clustering algor...
317 篇 computer archite...

机构

22 篇 signal and image...
19 篇 samara national ...
17 篇 school of electr...
12 篇 information syst...
11 篇 samara national ...
11 篇 univ texas san a...
11 篇 department of el...
11 篇 school of electr...
10 篇 department of el...
10 篇 electrical compu...
9 篇 school of electr...
9 篇 institute of ima...
9 篇 tongji universit...
9 篇 purdue univ sch ...
9 篇 university of ch...
9 篇 center for signa...
8 篇 shanghai jiao to...
8 篇 information syst...
8 篇 university of to...
8 篇 image processing...

作者

22 篇 anon
13 篇 de-shuang huang
12 篇 jagdish chand ba...
11 篇 jie yang
11 篇 p. pirsch
10 篇 hannig frank
10 篇 panetta karen
10 篇 c.-c.j. kuo
10 篇 j.m. mendel
10 篇 plaza antonio
10 篇 r. chellappa
9 篇 semenishchev e.
9 篇 zelensky a.
9 篇 bovik alan c.
9 篇 wei li
8 篇 frank hannig
8 篇 yves wiaux
8 篇 a.s. willsky
8 篇 mahalanobis a
8 篇 ilias maglogiann...

语言

14,979 篇 英文
539 篇 其他
90 篇 中文
26 篇 土耳其文
4 篇 俄文
3 篇 葡萄牙文
2 篇 法文
1 篇 西班牙文

检索条件"任意字段=Conference on Image Processing - Algorithms and Systems VI"

共 15618 条记录，以下是791-800 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：

processing of Analyzed Textual Information to a Meaningful Structure

Processing of Analyzed Textual Information to a Meaningful S...

引用

International Russian Automation conference, RusAutoCon 2022

作者： Semenov, R.E. MIREA – Russian Technological University 78 Vernadskogo Ave. Moscow119454 Russia

ISBN: (纸本)9783031223105

The results of studies of the morphological analysis of the text are demonstrated. Application of the technology of automatic processing of Russian-language texts to determine the parts of speech presented in the digital image. Definition of significant and non-essential information in the text. Identification and construction of a concept for implementation into an intelligent automated text recognition and analysis system. The correspondence of each word of the text to a certain part of speech according to a predetermined structure. The automatic selection of the necessary algorithms for bringing the text to the final form is carried out to get a real-time response. The designed system uses a certain structure, according to which, at the same time, text analysis is carried out to identify the main idea of a group of proposals, and presents the information received in an ordered form. The system can be upgraded and receive constant support in the form of updates to the relevance databases and calculation of criteria for weight characteristics. It can be implemented in the systems of Internet resources, used as an independent project supporting autonomous operation, or for implementation in intelligent systems. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

FAST: A Dual-tier Few-Shot Learning Paradigm for Whole Slide image Classification 38

FAST: A Dual-tier Few-Shot Learning Paradigm for Whole Slide...

引用

38th conference on Neural Information processing systems, NeurIPS 2024

作者： Fu, Kexue Luo, Xiaoyuan Qu, Linhao Wang, Shuo Xiong, Ying Maglogiannis, Ilias Gao, Longxiang Wang, Manning Qilu University of Technology Shandong Academy of Sciences Jinan China Digital Medical Research Center School of Basic Medical Sciences Fudan University China Shanghai Key Lab of Medical Image Computing and Computer Assisted Intervention China Fudan University China University of Piraeus Greece Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan China

The expensive fine-grained annotation and data scarcity have become the primary obstacles for the widespread adoption of deep learning-based Whole Slide images (WSI) classification algorithms in clinical practice. Unlike few-shot learning methods in natural images that can leverage the labels of each image, existing few-shot WSI classification methods only utilize a small number of fine-grained labels or weakly supervised slide labels for training in order to avoid expensive fine-grained annotation. They lack sufficient mining of available WSIs, severely limiting WSI classification performance. To address the above issues, we propose a novel and efficient dual-tier few-shot learning paradigm for WSI classification, named FAST. FAST consists of a dual-level annotation strategy and a dual-branch classification framework. Firstly, to avoid expensive fine-grained annotation, we collect a very small number of WSIs at the slide level, and annotate an extremely small number of patches. Then, to fully mining the available WSIs, we use all the patches and available patch labels to build a cache branch, which utilizes the labeled patches to learn the labels of unlabeled patches and through knowledge retrieval for patch classification. In addition to the cache branch, we also construct a prior branch that includes learnable prompt vectors, using the text encoder of visual-language models for patch classification. Finally, we integrate the results from both branches to achieve WSI classification. Extensive experiments on binary and multi-class datasets demonstrate that our proposed method significantly surpasses existing few-shot classification methods and approaches the accuracy of fully supervised methods with only 0.22% annotation costs. All codes and models will be publicly available on https://***/fukexue/FAST. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamic SpikFormer: Low-Latency & Energy-Efficient Spiking Neural Networks with Dynamic Time Steps for vision Transformers

Dynamic SpikFormer: Low-Latency & Energy-Efficient Spiking N...

引用

2025 IEEE International conference on Acoustics, Speech, and Signal processing, ICASSP 2025

作者： Datta, Gourav Liu, Zeyu Li, Anni Beerel, Peter A. Dept. of Electrical Computer & Systems Engineering Case Western Reserve University Cleveland United States Ming Hsieh Dept. of Electrical and Computer Engineering University of Southern California Los Angeles United States

ISBN: (纸本)9798350368741

Spiking Neural Networks (SNNs) have emerged as a popular spatio-temporal computing paradigm for complex vision tasks. Recently proposed SNN training algorithms have significantly reduced the number of time steps (down to 1) for improved latency and energy efficiency, however, they target only convolutional neural networks (CNN). These algorithms, when applied to the recently spotlighted vision transformers (viT), either require a large number of time steps or fail to converge. Based on the analysis of the histograms of the ANN and SNN activation maps, we hypothesize that each viT block has a different sensitivity to the number of time steps. We propose a novel training framework that dynamically allocates the number of time steps to each viT module depending on a trainable score assigned to each timestep. In particular, we generate a scalar binary time step mask that filters spikes emitted by each neuron in a leaky-integrate-and-fire (LIF) layer. The resulting SNNs have high activation sparsity and require only accumulate operations (AC), except for the input embedding layer, in contrast to expensive multiply-and-accumulates (MAC) needed in traditional viTs. This yields significant improvements in energy efficiency. We evaluate our training framework and resulting SNNs on image recognition tasks including CIFAR10, CIFAR100, and imageNet with different viT architectures. We obtain a test accuracy of 95.97% with 4.97 time steps with direct encoding on CIFAR10. © 2025 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on video Content Analysis and Recommendation System Based on image processing Technology in New Media Environment

Research on Video Content Analysis and Recommendation System...

引用

Digital Analysis and processing, Intelligent Computation (DAPIC), International conference on

作者： Bei Zhang Anhui Professional College of Art Hefei Anhui China

ISBN: (数字)9798331536169

ISBN: (纸本)9798331536176

In the new media environment, the research of video content analysis and recommendation system is particularly important. This paper discusses how to use image processing technology to deeply analyze and accurately recommend film and television content. With the diversification of presentation forms and communication channels of film and television content, the problems of information overload and uneven content quality have become increasingly prominent. This study aims to solve these problems and improve the user experience by constructing a video content analysis and recommendation system based on image processing technology. The system includes four core modules: data acquisition, image processing, content analysis and recommendation algorithm. By integrating image processing, machine learning and recommendation algorithm, the whole process from data acquisition to personalized recommendation is implemented efficiently. The experimental results demonstrate that the hybrid recommendation strategy outperforms single algorithms in various evaluation metrics, including accuracy, recall, F1 score, and Mean Reciprocal Rank (MRR), significantly enhancing the precision of recommendations and user satisfaction. This study not only provides a scientific basis and decision support for content creation, distribution, and marketing in the film and television industry but also lays a solid foundation for building more intelligent film and television content recommendation systems.

关键词： Industries Content management TV Machine learning algorithms Accuracy image processing Data acquisition Media User experience Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Homography Estimation Network Based on Dense Correspondence 28th

Homography Estimation Network Based on Dense Correspondence

引用

28th International conference on Neural Information processing

作者： Yang, Xiaohang Kong, Lingtong Liang, Ziyun Yang, Jie Shanghai Jiao Tong Univ Inst Image Proc & Pattern Recognit Shanghai Peoples R China

ISBN: (纸本)9783030923099;9783030923105

Reliable homography estimation is essential for plenty of computer vision tasks. However, the ground truth of homography is difficult to obtain. Moreover, it is relatively hard for ordinary convolutional neural networks to model correspondence, which leads to the difficulty for optimization. In this paper, we propose a novel framework based on unsupervised dense correspondence. We extract feature pyramid for each image and estimate the dense correspondence map in a coarse-to-fine manner. Relying on correlation layers and photometric loss, we can get rid of the deficiency of ordinary networks and estimate reliable dense correspondence for each image pair, which facilitates the later prediction of homography matrix. To achieve the homography training on both synthetic dataset and realistic dataset, we apply different losses for different tasks respectively being supervised loss and triplet loss, to regulate the training procedure. Qualitative and quantitative evaluations illustrate the effectiveness of the dense correspondence map, and shows the competitive performance of our method compared with traditional feature-based algorithms and deep learning methods.

关键词： Homography estimation Dense correspondence Unsupervised learning image alignment

来源：评论

学校读者我要写书评

暂无评论

image processing and Control of Tracking Intelligent Vehicle Based on Grayscale Camera 5

Image Processing and Control of Tracking Intelligent Vehicle...

引用

5th IEEE International conference on image processing Applications and systems (IPAS)

作者： Zhang, Jian Liu, Yufan Li, Ao Zeng, Jinshan Xie, Hongtu Sun Yat Sen Univ Sch Elect & Commun Engn Shenzhen Campus Shenzhen Peoples R China Nanchang Hangkong Univ Sch Informat Engn Nanchang Jiangxi Peoples R China

ISBN: (纸本)9781665462198

In order to realize the rapid and stable recognition and automatic tracking of various complex roads by the intelligent vehicles, this paper proposes image processing and cascade Proportion Integration Differentiation (PID) steering and speed control algorithms based on CMOS grayscale cameras in the context of the national college student intelligent vehicle competition. First, the grayscale image of the track is acquired by the grayscale camera. Then, the Otsu method is used to binarize the image, and the information of black boundary guide line is extracted. In order to improve the speed of the race, various track elements in the image are identified and classified, and the deviation between the actual centerline position and the ideal centerline position of the intelligent vehicle is calculated. Third, the discrete incremental cascade PID control algorithm is used to calculate the pulse width modulation (PWM) signal corresponding to the deviation. And the PWM signal is acted on the steering motor through the driving circuit, driving the intelligent vehicle to always drive along the middle road, so as to achieve the purpose of automatic tracking guidance. Experiments prove that the intelligent vehicle of this design can identify complex roads quickly and in a stable way, accurately complete automatic tracking, and obtain higher speed performance.

关键词： tracking intelligent vehicle proportional integral derivative control CMOS grayscale camera binary image image processing

来源：评论

学校读者我要写书评

暂无评论

Employing Tensor Decomposition and Contextual Inference for Reducing the Semantic Discrepancy in image processing 2

Employing Tensor Decomposition and Contextual Inference for ...

引用

2nd IEEE International conference on Communication, Security and Artificial Intelligence, ICCSAI 2023

作者： Suneetha, K. Gupta, Namit University Karnataka Bangalore India College of Computing Science and Information Technology Teerthanker Mahaveer University Uttar Pradesh Moradabad India

ISBN: (纸本)9798350369960

Despite the growing need for effective image tagging in both commercial and research domains, the inconsistency between image content and text annotations remains a significant issue. We propose an innovative approach that leverages deep learning and tensor decomposition to enhance the quality of image labelling and eliminate the reliance on labor-intensive manual tagging. Our methodology transforms images into tensors, facilitating the formation of a standardized feature space. We employ a sophisticated five-layer neural network architecture that integrates three-level tensor decomposition to match images with their context groups accurately. This structure is adept at capturing the nuanced patterns in data, which is crucial for reducing the semantic discrepancy between visual and textual information. We have rigorously evaluated our algorithm using the Corel-10K dataset, focusing on the specific case of penguin images, to demonstrate the efficacy of our model. The results showcase a marked improvement in the relevance of generated tags, thereby enhancing the retrieval accuracy and mitigating the issue of inappropriate tag assignment. This work not only contributes to the fields of Machine Learning and Data Mining by refining feature extraction and context estimation techniques but also has significant implications for the development of NLP algorithms that can better interpret and generate descriptive tags for visual content. Moreover, our approach sets the stage for future explorations into the integration of AI-driven image tagging systems with robotic systems for autonomous data handling and organization. © 2023 IEEE.

关键词： Contextual Estimation image Understanding Techniques Semantic Gap Minimization Tensor-Based image Analysis visual Data Interpretation

来源：评论

学校读者我要写书评

暂无评论

A Web-based Dicom image and Plane viewer 5

A Web-based Dicom Image and Plane Viewer

引用

5th IEEE International conference on Electrical, Computer and Communication Technologies, ICECCT 2023

作者： Priya Darshini, B. Deepan Chakkaravarthy, N. Gokul, B. Sabari Maharaja, B. KPR Institute of Engineering and Technology Department of Biomedical Engineering Tamil Nadu Coimbatore India

ISBN: (纸本)9781665493604

Preclinical research, clinical diagnosis, and treatment can all benefit from the information that a medical image can offer. Due to the increased usage of digital medical imaging, numerous researchers are actively creating medical image processing algorithms and systems to provide the clinical community with improved results, such as accurate clinical parameters or processed images from the original images. We describe a Web-based DICOM reader in this work that was created solely using web technology, specifically Python, Streamlit, and Docker. When it comes to programming languages, Python has established itself as a competitor to MATLAB and Julia, two prominent scientific programming languages. In this work, we examine the potential of Python and Docker as co-implementers of the DICOM viewer. A demonstration field is available to new users, for learning purposes. Three different types of image planes namely axial, coronal, and sagittal are also available, which helps doctors readily detect cancers. Additionally, we can adjust the image plane's threshold levels to suit our needs. We also provide a JSON version of the website for use in forthcoming research initiatives. © 2023 IEEE.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

CIFAR-10 Dataset image Classification Using CNN 8th

CIFAR-10 Dataset Image Classification Using CNN

引用

8th International conference on Information System Design and Intelligent Applications, ISDIA 2024

作者： Sucharitha, M. Sesha Talpa Sai, P.H.V. vijayagovindan, Sanjith Razmin, Fabina Ravindran, Byju Kiran Babu, Vadapalli V. S. Naveen Kumar, G.S. Bhaumik, Amiya School of Electronics Engineering VIT-AP University Amaravati India Malla Reddy College of Engineering and Technology Hyderabad India School of Information Technology Lincoln University College Petaling Jaya Malaysia Malla Reddy University Hyderabad India Lincoln University College Petaling Jaya Malaysia

ISBN: (纸本)9789819786657

image classification is an essential technology that is widely used in all aspects of human life. This work combined multiple image feature sources using deep learning algorithms to identify photos from the publicly available CIFAR10 image dataset. The same architecture, which consists of convolution modification and max-pooling of layers connected with several completely linked layers, is used to build most conventional convolutional neural networks (CNNs). This system consists of two steps: Pre-processing and Classification. The modified bilateral filtering method was employed in this study’s preprocessing steps. This study used convolutional neural network (CNN) architectures as suggested by the VGG-19 model to classify the CIFAR10 image dataset. The accuracy, precision, recall, and F1-score of the results are evaluated after simulating the suggested model. The testing results demonstrate that the proposed method reach a recall value of 96.4%, F1-score of 94.1%, accuracy of 97.3%, and maximum precision of 96.1%. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Wiener filtering

来源：评论

学校读者我要写书评

暂无评论

Application of Deep Learning Methods for Forest Fire Intelligent image processing 2nd

Application of Deep Learning Methods for Forest Fire Intelli...

引用

2nd International conference on Advances in Information and Communication Technology, ICTA 2023

作者： Long, Nguyen The Huong, Nguyen Thu G, Shmeleva Anna. Lien, Pham Thi Department of Informatics Institute of Cybersecurity and Digital Technologies MIREA – Russian Technological University Moscow119454 Russia Laboratory of Artificial Intelligence and Machine Learning Institute of Information Technology and Data Science Irkutsk National Research Technical University Irkutsk664074 Russia University of Information and Communication Technology Thai Nguyen University Thai Nguyen70000 Viet Nam

ISBN: (纸本)9783031495281

There are many challenges for a Deep Learning application project. Many problems need to be solved in an optimal way to improve the performance of the system. We can focus on a specific step or on the whole process. The aim of the work is to show a new way of using convolutional neural networks is proposed to image intelligent process. Due to the influence of climate change, natural disasters are becoming more complicated and have serious consequences. In particular, the phenomenon of forest fires is affected by factors such as humidity, temperature and vegetation characteristics, etc., so the detection and prediction of forest fires face many challenges. In this study, we focus on using image processing techniques and visual algorithms to preprocess data and filter noise, in order to create a complete database for training and testing model. Natural elements are also used in combination with object features (forest fire images) to build feature vectors. This study will allow to develop the technology and open up new opportunities for its subsequent application. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： image processing

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 << < 76 77 78 79 80 81 82 83 84 85 > >>

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：