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

25,302 篇 会议
282 篇 期刊文献
21 册 图书
3 篇 学位论文

馆藏范围

25,608 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

15,842 篇 工学
- 9,892 篇 计算机科学与技术...
- 6,083 篇 电气工程
- 5,779 篇 信息与通信工程
- 5,627 篇 软件工程
- 2,035 篇 光学工程
- 1,458 篇 控制科学与工程
- 1,281 篇 机械工程
- 1,157 篇 电子科学与技术（可...
- 877 篇 生物医学工程（可授...
- 834 篇 生物工程
- 799 篇 仪器科学与技术
- 268 篇 网络空间安全
- 253 篇 化学工程与技术
- 248 篇 安全科学与工程
- 243 篇 交通运输工程
- 183 篇 材料科学与工程（可...
- 167 篇 土木工程
- 164 篇 建筑学
5,731 篇 理学
- 3,491 篇 物理学
- 2,208 篇 数学
- 886 篇 生物学
- 566 篇 统计学（可授理学、...
- 419 篇 系统科学
- 317 篇 化学
3,025 篇 医学
- 2,900 篇 临床医学
- 313 篇 基础医学(可授医学...
- 229 篇 药学(可授医学、理...
1,401 篇 管理学
- 856 篇 管理科学与工程(可...
- 618 篇 图书情报与档案管...
- 169 篇 工商管理
181 篇 法学
134 篇 农学
58 篇 教育学
52 篇 文学
51 篇 经济学
51 篇 军事学
22 篇 艺术学

主题

3,123 篇 image processing
2,084 篇 image coding
2,027 篇 visualization
1,754 篇 image segmentati...
1,490 篇 feature extracti...
1,083 篇 image reconstruc...
908 篇 cameras
885 篇 signal processin...
833 篇 image color anal...
756 篇 humans
717 篇 image edge detec...
692 篇 image enhancemen...
667 篇 computer vision
651 篇 training
584 篇 image analysis
575 篇 deep learning
536 篇 image quality
481 篇 conferences
473 篇 object detection
470 篇 robustness

机构

51 篇 school of electr...
49 篇 shanghai jiao to...
39 篇 ieee
38 篇 university of sc...
36 篇 shanghai jiao to...
36 篇 school of comput...
34 篇 shanghai jiao to...
33 篇 university of ch...
32 篇 microsoft resear...
26 篇 national institu...
25 篇 department of el...
24 篇 hendisli&#x011f
23 篇 institute for in...
23 篇 institute of ima...
23 篇 istanbul teknik ...
23 篇 institute of dig...
22 篇 peking univ inst...
21 篇 institute of inf...
21 篇 univ chinese aca...
21 篇 univ sci & techn...

作者

62 篇 guangtao zhai
46 篇 song li
45 篇 zhai guangtao
32 篇 jie yang
27 篇 li li
25 篇 m. vetterli
25 篇 bovik alan c.
25 篇 li sumei
25 篇 li song
25 篇 sarp ertürk
24 篇 jing zhang
24 篇 b. macq
23 篇 zhang lei
23 篇 li zhuo
23 篇 d.r. bull
22 篇 jürgen seiler
21 篇 shi guangming
20 篇 liu yang
20 篇 zhang wenjun
18 篇 mohamed-chaker l...

语言

24,610 篇 英文
489 篇 土耳其文
394 篇 其他
137 篇 中文
2 篇 西班牙文
2 篇 葡萄牙文

检索条件"任意字段=IEEE Visual Communications and Image Processing Conference"

共 25608 条记录，以下是4341-4350 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：

Class Discriminative Maximum Mean and Covariance Discrepancy for Unsupervised Domain Adaptation

Class Discriminative Maximum Mean and Covariance Discrepancy...

引用

ieee International conference on Signal and image processing (ICSIP)

作者： Ting Zhu Yixiang Zheng Jiang Pu Special Equipment Safety Supervision Inspection Institute of Jiangsu Province Nanjing China

ISBN: (数字)9798350350920

ISBN: (纸本)9798350350937

Unsupervised domain adaptation is a hot topic in transfer learning, which aims to transfer knowledge from the labeled source domain to the related but unlabeled target domain. For reducing the difference between the distributions of both domains, it is important to choose a suitable distribution discrepancy metric. Recently, a new distribution discrepancy metric named maximum mean and covariance discrepancy (MMCD) was proposed, which combined traditional maximum mean discrepancy (MMD) with maximum covariance discrepancy (MCD). Since the MMCD captures both the first and second order statistics in a reproducing kernel Hilbert space, it can give better results than using MMD alone. However, existing MMCD based methods ignored the label information from the source domain, thus limited their classification performance. In this paper, a class discriminative MMCD domain adaptation (CD-McDA) method is proposed, which not only reduces the MMCD of marginal and class-conditional distributions between both domains, but also enhances the class discriminative ability, i.e. maximizing the inter-class dispersion and minimizing the intra -class scatter. Comprehensive experiments are carried out on two visual and one pressure vessel crack cross-domain classification tasks, and the results demonstrate the effectiveness of the proposed CD-McDA method.

关键词： Measurement visualization image processing Transfer learning Pressure vessels Hilbert space Kernel

来源：评论

学校读者我要写书评

暂无评论

Deep Fusion of Visible and Near Infrared images for Registration and Defogging Using Cross Modal Transformer

Deep Fusion of Visible and Near Infrared Images for Registra...

引用

ieee International conference on image processing

作者： Mengyao Ji Cheolkon Jung School of Electronic Engineering Xidian University Xian China

ISBN: (数字)9798350349399

ISBN: (纸本)9798350349405

According to Rayleigh scattering, the density of fog is closely related to the distance of the target from the visible light camera. However, the near infrared (NIR) spectral band is robust to the interference problem but has a single channel without color. In this paper, we propose deep fusion of visible (VIS) and near infrared (NIR) images for registration and defogging using cross modal transformer. The proposed fusion network has two main features: 1) Cross modal transformer deals with the channel and spatial redundancy between two source images while retaining their complementary information; 2) Since the blue channel in VIS image can represent the amount of fog in the scene according to Rayleigh scattering, we normalize it to obtain a fog weight map. To synthesize training data, the distance between object and camera is required, thus we use depth estimation to obtain it. Then, we assign different amounts of fog to each image to consider various weather conditions. First, we extract multi-scale features from the source images. Second, we use the cross modal transformer to reflect cross-domain interaction between the source images in spatial and channel domains. Third, we generate the fusion weight for the source images according to the fog weight map and reconstruct a fused result based on it. Various experiments on the widely-used benchmark and real-world datasets show that the proposed method generates natural-looking defogging results with clear textures in distant regions while keeping the original tone in near regions. Moreover, the proposed method outperforms state-of-the-art fusion methods in term of both visual quality and quantitative measurements.

关键词： Training visualization Rayleigh scattering image color analysis Transfer learning Training data Transformers

来源：评论

学校读者我要写书评

暂无评论

Deep Learning based Lip Movement Technique for Mute 6

Deep Learning based Lip Movement Technique for Mute

引用

6th ieee International conference on Communication and Electronics Systems, ICCES 2021

作者： Neeraja, K. Srinivas Rao, K. Praneeth, G. Mlr Institute of Technology Department of Information Technology Mlr Institute of Technology Department of Computer Science and Engineering

ISBN: (纸本)9781665435871

There is a significant change in technology, virtual reality (VR) has been used in this article as the simplest way of visual activity and interaction technique which provides visual nodal options supported by the automated lip-reading technology. With this advancement in the technology, the state of the human can be identified and captured through the lip movements. Deep Learning is used to analyze the real time thinking of the human visual choices. Using image processing technique, virtual reality technology is used to identify the driver's visual features and evaluate the critical time thinking. The ancient lip-reading recognition system, the need for responsive applications is difficult to fulfill. Deep Learning is now the emerging technique of artificial intelligence which acts as a normal human brain with the thinking capability. It consists of different layers which are used to evaluate the details like neurons in brain. In this article, the surface area of the lip is taken as the key element or the key feature of the lip movement. The horizontal distance and the vertical distance of the lips are used to calculate the surface area. This surface area is then used to estimate some parameter and store in the database. Based on the results, the accuracy is more than 85%. Therefore, our proposed system is more effective and more efficient than other traditional methods. © 2021 ieee.

关键词： image processing

来源：评论

学校读者我要写书评

暂无评论

Interactive image Segmentation with Cross-Modality Vision Transformers

Interactive Image Segmentation with Cross-Modality Vision Tr...

引用

International conference on Computer Vision Workshops (ICCV Workshops)

作者： Kun Li George Vosselman Michael Ying Yang University of Twente The Netherlands

Interactive image segmentation aims to segment the target from the background with the manual guidance, which takes as input multimodal data such as images, clicks, scribbles, polygons, and bounding boxes. Recently, vision transformers have achieved a great success in several downstream visual tasks, and a few efforts have been made to bring this powerful architecture to interactive segmentation task. However, the previous works neglect the relations between two modalities and directly mock the way of processing purely visual information with self-attentions. In this paper, we propose a simple yet effective network for click-based interactive segmentation with cross-modality vision transformers. Cross-modality transformers exploit mutual information to better guide the learning process. The experiments on several benchmarks show that the proposed method achieves superior performance in comparison to the previous state-of-the-art models. In addition, the stability of our method in term of avoiding failure cases shows its potential to be a practical annotation tool. The code and pretrained models will be released under https://***/lik1996/iCMFormer.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Generative Adversarial Networks for image Recognition Algorithms Based on Deep Learning and Traditional Methods

A Comparative Study of Generative Adversarial Networks for I...

引用

ieee International conference on Power, Intelligent Computing and Systems (ICPICS)

作者： Yihao Zhong Yijing Wei Yingbin Liang Xiqing Liu Rongwei Ji Yiru Cang New York University New York USA Northwestern University Evanston USA Northeastern University Seattle USA Columbia University New York USA Southern Methodist University Dallas USA Northeastern University Boston USA

ISBN: (数字)9798350374315

ISBN: (纸本)9798350374322

This paper delves into an innovative image recognition algorithm that merges deep learning techniques with Generative Adversarial Networks (GANs) and offers a comparative analysis against traditional image recognition methods. The primary objective of this study is to evaluate the benefits and future prospects of deep learning, with a particular focus on GANs, within the realm of image recognition. The paper begins by reviewing conventional image recognition approaches, highlighting classical algorithms such as SIFT and HOG, which are based on feature extraction, and their combination with classifiers like Support Vector Machines (SVM) and Random Forests. Following this, the paper outlines the fundamental principles, network architecture, and unique advantages of GANs in the context of image generation and recognition. To verify the effectiveness of GANs in image recognition tasks, a series of experiments were performed using several publicly available image datasets for both training and testing purposes. The findings reveal that GANs significantly outperform traditional methods, especially in the context of processing complex images, enhancing accuracy, and improving resistance to noise. GANs are particularly adept at capturing intricate, high-dimensional features and subtle details in images, leading to substantial improvements in recognition performance. Additionally, GANs demonstrate exceptional capabilities in addressing issues related to image noise, managing incomplete data, and generating high-quality visual content.

关键词： Deep learning Support vector machines Training Resistance visualization image recognition image synthesis Noise Generative adversarial networks Testing

来源：评论

学校读者我要写书评

暂无评论

Crawling Method for image-Based Space Matching in Digital Twin Smart Cities

Crawling Method for Image-Based Space Matching in Digital Tw...

引用

Metaverse Computing, Networking and Applications (MetaCom), ieee International conference on

作者： Hyeonji Kim Soorim Yang Jaeho Kim Department of Intelligent Mechatronics Engineering Sejong University Seoul Republic of Korea Department of Information and Communications Engineering Sejong University Seoul Republic of Korea

To provide interactive services between the digital twin smart city and the actual smart city, space matching in physical space and virtual space is required. visual place recognition, which is widely used for space matching, requires a 2D image database for 3D space because it identifies location information through matching between query images and database. We suggest a method of generating a database by collecting 2D images in 3D space for image-based spatial matching. In this paper, we introduce a crawling method that can collect continuous 2D images of the digital twin smart city. Our crawling method creates crawling units of a specific size and crawling points at regular intervals in the area where image crawling is required and generates the path for a virtual crawling device that can pass through all points on the unit. It makes a 2D image database that can express 3D space by crawling successive images obtained by rotating the virtual crawling device. By using our crawling method, we can help provide interactive services in the future smart city.

关键词：

来源：评论

学校读者我要写书评

暂无评论

(SSTA-NET)Speed and Short-Term Action Learning Networks for Indoor Wind Tunnel Skydiving Action Recognitions

(SSTA-NET)Speed and Short-Term Action Learning Networks for ...

引用

International conference on Vision, image and Signal processing (ICVISP)

作者： Yuxiang Li Liuyue Xu Wei Zhang Zhisheng Gao School of Computer and Software Engineering Xihua University Chengdu China

ISBN: (数字)9798331541460

ISBN: (纸本)9798331541477

Action recognition is widely used in video classification and motor behavior analysis. However, existing action recognition methods often overlook the importance of speed and distinct short-term actions. In particular, the similarity between various short-term actions during skydiving training poses a significant challenge for action recognition in indoor wind tunnel skydiving. We tackle these challenges by proposing a Speed and Short-Term Action Learning Network (SSTA-NET) for indoor wind tunnel skydiving action recognition. The network integrates a short-term action feature attention module that processes short-term action information within a single framework. To acquire dynamic motion data across varying movement types, SSTA-NET introduces a displacement map speed learning module that captures motion speed details in action videos. Our network also utilizes a video-efficient multi-scale attention module, designed to prioritize salient visual areas while reducing redundant spatio-temporal redundancy in the videos. SSTA-NET achieves an average improvement of 8.56% on the indoor wind tunnel skydiving dataset and 6.06% on the HMDB51 public dataset compared to other methods.

关键词： Training Location awareness visualization image recognition Wind tunnels Redundancy Dynamics Signal processing Feature extraction Motors

来源：评论

学校读者我要写书评

暂无评论

CMFNet: An End-to-End Ultra-Lightweight Underwater image Enhancement Network

CMFNet: An End-to-End Ultra-Lightweight Underwater Image Enh...

引用

ieee Information Technology, Networking, Electronic and Automation Control conference

作者： Shiyan Li Xiaolong Yang Huajin Han Qingbo Meng Tianjin Navigation Instruments Research Institute Tianjin China Tianjin Qisuo Precision Electromechanical Technology Co. Ltd Tianjin China Tianjin Key Laboratory of Special Severe Enviroment Computer Tianjin China

ISBN: (数字)9798350370805

ISBN: (纸本)9798350370812

As the main carrier of underwater information, underwater video images play a vital role in human exploration and development of the ocean. However, due to the optical properties of water and the complex and variable underwater environmental factors, the quality of observed underwater images is severely degraded, affecting the execution of underwater equipment tasks. Moreover, most current underwater image enhancement methods have high computational costs, which limits their application in real-time large-scale underwater image processing. In order to solve this problem, we propose the CMFNet, a new lightweight network can efficiently enhance underwater images in real time. This network processes through a color recovery module, a multi-scale feature extraction module, and a feature fusion module to improve image color representation while maintaining content style and spatial texture. To the best of our knowledge, CMFNet is the only network that can enhance 2K resolution images in real time. Extensive experiments and visual comparisons have shown that CMFNet can achieve optimal or suboptimal results with fewer parameters and computational complexity compared to other advanced underwater image enhancement methods, making it valuable for practical applications.

关键词： Knowledge engineering Water visualization image color analysis Feature extraction Optical imaging Real-time systems Spatial resolution image enhancement Underwater equipment

来源：评论

学校读者我要写书评

暂无评论

Detection of Human Brain Tumor by Medical image processing and PCA Based image Fusion

Detection of Human Brain Tumor by Medical Image Processing a...

引用

Mobile Networks and Wireless communications (ICMNWC), ieee International conference on

作者： M Narmadha L Arthi T Narmatha Department of Electronics and Communication Engineering IFET College of Engineering Villupuram India

ISBN: (纸本)9781665491129

Medical image processing is the use and investigation of human body image data, often obtained by a CT and MRI scan, to identify ailments and guide medical therapies like surgical planning or for research purposes. Radiologists, engineers and doctors employ medical image processing to more fully comprehend the anatomical structure of groups of patients. Brain tumour recognition involves image processing using Morphological function and image Fusion using PCA (Principal Component Analysis). Morphological operation compares the input image of matching pixel with its neighbor pixels. During morphological process, imperfections in the image are removed. In the output image, value of each pixel is calculated for fusion process. In order for multi-band image data to function at its best in the new image, the PCA approach is utilized to compress multi-band image data into a single image while minimizing the size of acquired image characteristics with no color distortion, reduced and with fused image SSIM range between 0.97-1, PSNR range between 35-40dB, MSE range between 10-15. Memory storage of patient database will be reduced when both MRI and CT scans are fused together.

关键词： Wireless communication image coding Databases Computed tomography Magnetic resonance imaging Biomedical image processing image fusion

来源：评论

学校读者我要写书评

暂无评论

Capturing the Essence: Exploring Cutting-Edge Feature Extraction Methods in Digital image processing

Capturing the Essence: Exploring Cutting-Edge Feature Extrac...

引用

Mobile Networks and Wireless communications (ICMNWC), ieee International conference on

作者： Prabu S Natarajan B Roshan George S. Sujitha P Divya Bharathi S. Rajeswari School of Computer Science and Engineering VIT University Chennai India Department of Computer Science and Engineering (AIE) Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India Department of Computer Science and Engineering Roever Engineering College Tamilnadu India Department of Artificial intelligence & Data science Panimalar Engineering College Chennai India Department of Computer Science and Engineering K. Ramakrishnan College of Engineering Tiruchirappalli Tamilnadu

Feature Extraction (FE) plays a vital role in the fields of image processing, machine learning and pattern recognition. Binarization, resizing, thresholding and normalization are the initial steps applied before extracting features from an image. FE methods are applied to images to extract the most essential features that help in detection, recognition and classification tasks. FE techniques are used in numerous applications, such as object recognition, character recognition and pattern recognition. This research study presents a comprehensive research study of different image FE techniques, including SURF, BRISK, PCA and SIFT, which have been employed for various applications in recent times. This research study explains each method's fundamental concepts and pros and cons and demonstrates in what scenario which feature extraction technique will be better. This research work also presents a summary table of FE techniques used in various applications with their accuracy percentage.

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500页 << < 431 432 433 434 435 436 437 438 439 440 > >>

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：