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

4,073 篇 会议
53 篇 期刊文献
18 册 图书
1 篇 学位论文

馆藏范围

4,145 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

2,373 篇 工学
- 1,632 篇 计算机科学与技术...
- 1,017 篇 信息与通信工程
- 853 篇 软件工程
- 788 篇 电气工程
- 231 篇 光学工程
- 113 篇 生物工程
- 102 篇 电子科学与技术（可...
- 77 篇 控制科学与工程
- 76 篇 生物医学工程（可授...
- 72 篇 仪器科学与技术
- 56 篇 机械工程
- 36 篇 化学工程与技术
- 33 篇 网络空间安全
- 29 篇 测绘科学与技术
- 25 篇 动力工程及工程热...
- 25 篇 安全科学与工程
- 17 篇 轻工技术与工程
1,078 篇 理学
- 838 篇 物理学
- 247 篇 数学
- 120 篇 生物学
- 67 篇 统计学（可授理学、...
- 39 篇 系统科学
- 36 篇 化学
1,031 篇 医学
- 1,017 篇 临床医学
- 32 篇 基础医学(可授医学...
- 26 篇 药学(可授医学、理...
152 篇 管理学
- 81 篇 图书情报与档案管...
- 79 篇 管理科学与工程(可...
- 18 篇 工商管理
30 篇 法学
- 28 篇 社会学
11 篇 军事学
9 篇 文学
8 篇 农学
7 篇 教育学
5 篇 经济学

主题

510 篇 image coding
401 篇 image processing
352 篇 visual communica...
311 篇 visualization
235 篇 feature extracti...
229 篇 image segmentati...
173 篇 image compressio...
158 篇 image reconstruc...
146 篇 video coding
133 篇 training
130 篇 cameras
124 篇 humans
118 篇 image color anal...
114 篇 image quality
112 篇 signal processin...
109 篇 image enhancemen...
102 篇 image edge detec...
101 篇 deep learning
95 篇 image retrieval
93 篇 motion estimatio...

机构

36 篇 shanghai jiao to...
29 篇 institute of ima...
24 篇 school of electr...
20 篇 university of sc...
18 篇 shanghai jiao to...
16 篇 shanghai jiao to...
16 篇 tianjin univ sch...
16 篇 beijing universi...
11 篇 university of el...
11 篇 cas key laborato...
11 篇 tsinghua univ de...
10 篇 univ sci & techn...
10 篇 peking univ inst...
10 篇 institute of ima...
9 篇 zhejiang univers...
9 篇 tsinghua univ de...
9 篇 school of electr...
9 篇 xidian univ sch ...
9 篇 shanghai jiao to...
8 篇 school of remote...

作者

34 篇 zhai guangtao
26 篇 sumei li
25 篇 song li
22 篇 li sumei
21 篇 guangtao zhai
18 篇 li li
18 篇 li song
18 篇 min xiongkuo
16 篇 dong liu
16 篇 yang xiaokang
16 篇 shan liu
15 篇 chen zhibo
15 篇 andré kaup
13 篇 xie rong
13 篇 xiongkuo min
13 篇 gao wen
11 篇 heming sun
11 篇 zhibo chen
11 篇 zhenzhong chen
11 篇 gao zhiyong

语言

4,069 篇 英文
49 篇 土耳其文
27 篇 中文
17 篇 其他

检索条件"任意字段=Conference on Visual Communications and Image Processing 2001"

共 4145 条记录，以下是801-810 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：

Global Homography Motion Compensation for Versatile Video Coding

Global Homography Motion Compensation for Versatile Video Co...

引用

IEEE visual communications and image processing (VCIP)

作者： Yao Li Zhuoyuan Li Li Li Dong Liu Houqiang Li CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei China

ISBN: (纸本)9781665475938

In Versatile Video Coding (VVC), local affine motion compensation (LAMC) is adopted to handle complex motions, such as rotation and zooming. However, it is inefficient to use LAMC to handle the global motion due to the following two reasons. First, the use of LAMC may lead to some extra bit cost on the affine motion model parameters. Second, the precision of LAMC is restricted by the MV precision of the control points. Therefore, in this paper, we propose a global homography motion compensation (GHMC) framework to better characterize the global motion. For each coding block, an extra mode is added to perform motion compensation based on an 8-parameter global homography motion model. In addition, an extrapolation scheme is designed to derive the parameters from reference frames to save the bit cost for signaling them. The proposed framework is implemented into the VVC reference software VTM-6.0. Experimental results show that, on average, 0.69% and 0.66% BD-rate reduction is achieved under Low Delay P and Low Delay B configurations, respectively, for sequences with rich complex global motions.

关键词： Video coding Extrapolation Adaptation models Costs image coding visual communication Motion compensation

来源：评论

学校读者我要写书评

暂无评论

An image-guided mobile robotic system for underground pipe navigation and condition monitoring

An image-guided mobile robotic system for underground pipe n...

引用

2021 IEEE International conference on Electrical, Computer, communications and Mechatronics Engineering, ICECCME 2021

作者： Juganaikloo, Y.B. Gooroochum, M. University of Mauritius Mechanical and Production Engineering Department Reduit Mauritius

ISBN: (纸本)9781665412629

This paper presents the design of a mobile robotic system for navigating inside the vertical and horizontal segments of underground pipes using visual data. The development of this system stems from the need to inspect underground pipes buried for various reasons, and for which it becomes a challenging task to inspect the interior conditions of the pipe. The specific application under study was a horizontal ground-coupled heat exchanger system for which a 160 mm diameter PVC pipework of approximately 60m length was buried at a depth of 3m below ground. The purpose of the mobile robotic system was to provide video recording of the interior of the PVC pipe network while also measuring the prevailing temperature and humidity level using on-board sensors. This paper presents the design process followed to develop the system, with emphasis on the image processing and analysis techniques for navigation along straight segments, both vertical and horizontal, of the pipe and around corners. The system design allows the robot to contract in diameter at a 90-degree elbow pipe and navigate through bends, which are detected using visual cues generated by using specific lighting arrangements. © 2021 IEEE.

关键词： Condition monitoring

来源：评论

学校读者我要写书评

暂无评论

Recurrent Multi-connection Fusion Network for Single image Deraining

Recurrent Multi-connection Fusion Network for Single Image D...

引用

IEEE visual communications and image processing (VCIP)

作者： Yuetong Liu Rui Zhang Yunfeng Zhang Yang Ning Xunxiang Yao Huijian Han Dept. Computer Science & Technology Shandong University of Finance and Economics Jinan China Dept. Computer Science & Technology Shandong Jianzhu University Jinan China

ISBN: (纸本)9781665475938

Single image deraining is an important problem in many computer vision tasks because rain streaks can severely degrade the image quality. Recently, deep convolution neural network (CNN) based single image deraining methods have been developed with encouraging performance. However, most of these algorithms are designed by stacking convolutional layers, which encounter obstacles in learning abstract feature representation effectively and can only obtain limited features in the local region. In this paper, we propose a recurrent multi-connection fusion network (RMCFN) to remove rain streaks from single images. Specifically, the RMCFN employs two key components and multiple connections to fully utilize and transfer features. Firstly, we use a multi-scale fusion memory block (MFMB) to exploit multi-scale features and obtain long-range dependencies, which is beneficial to feed useful information to a later stage. Moreover, to efficiently capture the informative features on the transmission, we fuse the features of different levels and employ a multi-connection manner to use the information within and between stages. Finally, we develop a dual attention enhancement block (DAEB) to explore the valuable channel and spatial components and only pass further useful features. Extensive experiments verify the superiority of our method in visual effect and quantitative results compared to the state-of-the-arts.

关键词： image quality Rain Fuses visual communication Stacking Neural networks Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Quality-Constant Per-Shot Encoding by Two-Pass Learning-based Rate Factor Prediction

Quality-Constant Per-Shot Encoding by Two-Pass Learning-base...

引用

IEEE visual communications and image processing (VCIP)

作者： Chunlei Cai Yi Wang Xiaobo Li Tianxiao Ye Bilibili Inc. Shanghai China

ISBN: (纸本)9781665475938

Providing quality-constant streams can simultaneously guarantee user experience and prevent wasting bit-rate. In this paper, we propose a novel deep learning based two-pass encoder parameter prediction framework to decide rate factor (RF), with which encoder can output streams with constant quality. In first-pass, an RF is predicted based on spatial-temporal and pre-coding features of video segment. Then video segment is encoded using the predicted RF and then its VMAF is measured. If first pass VMAF doesn't meet target quality, a second pass prediction is performed using another model, in where results of first pass is added to features. Experiments show the proposed method requires only 1.55 times encoding complexity on average, meanwhile the accuracy, that the compressed video's actual VMAF is within ±1 around the target VMAF, reaches 98.88%. Compared with average rate mode, this method can both improve visual Quality and save ~10% bit-rate, as shown in demos 1 1 Subjective comparison videos can be downloaded at https://***/drive/folders/1BJNZ5HssxFaKBcXMenEdioLJ77hnZ-vx?usp=sharing..

关键词： Radio frequency Deep learning visualization image coding visual communication Predictive models User experience

来源：评论

学校读者我要写书评

暂无评论

Distinguishing Computer-Generated images from Photographic images: a Texture-Aware Deep Learning-Based Method

Distinguishing Computer-Generated Images from Photographic I...

引用

IEEE visual communications and image processing (VCIP)

作者： Zicheng Zhang Wei Sun Xiongkuo Min Tao Wang Wei Lu Guangtao Zhai Institute of Image Communication and Network Engineering Shanghai Jiao Tong University China

ISBN: (纸本)9781665475938

With the rapid development of computer graphics and generative models, computers are capable of generating images containing non-existent objects and scenes. Moreover, the computer-generated (CG) images may be indistinguishable from photographic (PG) images due to the strong representation ability of neural network and huge advancement of 3D rendering technologies. The abuse of such CG images may bring potential risks for personal property and social stability. Therefore, in this paper, we propose a dual-stream neural network to extract features enhanced by texture information to deal with the CG and PG image classification task. First, the input images are first converted to texture maps using the rotation-invariant uniform local binary patterns. Then we employ an attention-based texture-aware feature enhancement module to fuse the features extracted from each stage of the dual-stream neural network. Finally, the features are pooled and regressed into the predicted results by fully connected layers. The experimental results show that the proposed method achieves the best performance among all three popular CG and PG classification databases. The ablation study and cross-database validation experiments further confirm the effectiveness and generalization ability of the proposed algorithm.

关键词： Three-dimensional displays Fuses Databases visual communication Computational modeling Neural networks Feature extraction

来源：评论

学校读者我要写书评

暂无评论

ViEdge: An Edge-based Platform for Video Analytics Applications in Smart Estates

ViEdge: An Edge-based Platform for Video Analytics Applicati...

引用

International conference on Computer communications and Networks (ICCCN)

作者： Vishal Choudhary Rahul Aggarwal Hock Beng Lim Binbin Chen Center for Smart Systems (CS2) Singapore University of Technology and Design Singapore Information Systems Technology and Design Pillar (ISTD) Singapore University of Technology and Design Singapore

ISBN: (数字)9798350384611

ISBN: (纸本)9798350348439

Video analytics plays a crucial role in the development of smart estates and cities. Applications such as garbage dumping detection, lift monitoring, safety surveillance, etc. rely on video analytics, and require fast response time. Traditional cloud-based systems are ill-suited for these applications due to their limitations in handling large volume of video data with low latency. In contrast, the IoT-Edge-Cloud paradigm is better suited for such applications, but it presents challenges such as system heterogeneity, and resource allocation and orchestration. There is a need for an efficient platform for distributed video stream processing where resource orchestration and scalability aspects are tailored to smart estate *** this paper, we present ViEdge, an edge-based platform for video analytics applications in smart estates. It is highly adaptable and scalable, making it ideal for various deployments in such environments. Our implementation of ViEdge utilizes Kubernetes (K8s) for resource management and orchestration, and Apache Storm for distributed video stream processing. To study ViEdge’s customization capabilities, we evaluated its performance on a heterogeneous edge testbed. We observed increased latency in Apache Storm when integrated with Kubernetes, affecting overall application performance. However, by developing a heuristic-based scheduler, we demonstrate that ViEdge effectively reduces end-to-end latency and enhances frame processing rates.

关键词： Storms visual analytics Surveillance image edge detection Urban areas Streaming media Safety

来源：评论

学校读者我要写书评

暂无评论

Face Super Resolution based on Contrastive Learning

Face Super Resolution based on Contrastive Learning

引用

IEEE visual communications and image processing (VCIP)

作者： Wenlin Zhang Sumei Li Liqin Huang Tianjin International Engineering Institute Tianjin University Tianjin China School of Electrical and Information Engineering Tianjin University Tianjin China College of Physics and Information Engineering Fuzhou University Fuzhou China

ISBN: (纸本)9781665475938

Face super resolution (FSR) is a sub-field of super resolution (SR), which is to reconstruct low resolution (LR) face image into high resolution (HR) face image. Recently, the FSR methods based on face prior have been proved to be effective in FSR on higher upscaling factors. However, existing prior guided methods mostly adopt supervised prior extraction models trained with labels. The performance of supervised prior extraction method mainly depends on the accuracy of label so that the implicit informations of data are not fully utilized. And in practical application, the label acquisition work is routine and laborious. Therefore, to solve these problems, this paper proposes a novel contrastive learning (CL) based FSR method, which is based on the iterative collaboration of image reconstruction network and contrastive learning network. In each iteration, the reconstruction network uses the priors generated by the contrastive learning network to assist the image reconstruction and generates higher-quality SR images. Then, the SR image will feed into contrastive learning network to obtain more accurate prior. In addition, a new contrastive learning constraint function is designed to extract the representation of the augmented facial image as a prior by analysing the principal component information of the image. Quantitative and qualitative experimental results show that the proposed method is superior to the most advanced FSR method in high-quality face images super resolution reconstruction.

关键词： image resolution visual communication Design methodology Collaboration Feature extraction Data mining Iterative methods

来源：评论

学校读者我要写书评

暂无评论

ICME 2022 - IEEE International conference on Multimedia and Expo 2022, Proceedings

ICME 2022 - IEEE International Conference on Multimedia and ...

引用

2022 IEEE International conference on Multimedia and Expo, ICME 2022

ISBN: (纸本)9781665485630

The proceedings contain 377 papers. The topics discussed include: partial-to-partial point cloud registration based on multi-level semantic-structural cognition;noise-tolerant learning with silhouette coefficient for unsupervised person re-identification;disentangled visual representations for extreme human body video compression;quality-oriented feature regression for robust image similarity metric;salient object detection via bilateral feature fusion and score sorting attention mechanism;watermark-preserving keypoint enhancement for screen-shooting resilient watermarking;learning robust convolutional neural networks with relevant feature focusing via explanations;fusing acoustic and text emotional features for expressive speech synthesis;double attention network based on sparse sampling;learning to augment face presentation attack dataset via disentangled feature learning from limited spoof data;towards proper contrastive self-supervised learning strategies for music audio representation;just noticeable learning for unsupervised anomaly localization and detection;triple disentangling network for unsupervised domain adaptation;and multi-modal adversarial adaptive network for misinformation detection on social media.

关键词：

来源：评论

学校读者我要写书评

暂无评论

EMERGING THREAT of DEEP FAKE: HOW to IDENTIFY and PREVENT IT 6

EMERGING THREAT of DEEP FAKE: HOW to IDENTIFY and PREVENT IT

引用

6th International conference on Future Networks and Distributed Systems, ICFNDS 2022

作者： Taha, Murooj Amer Khudhair, Wijdan Mahood Khudhur, Ahmed Mahmood Mahmood, Omar Abdulkareem Hammadi, Yousif I. Al-Husseinawi, Riyam Shihab Ahmed Aziz, Ahmed Bilad Alrafidain University College Department of Computer Engineering Techniques Diyala Iraq Department of Communications Engineering College of Engineering University of Diyala 32001 Iraq Bilad Alrafidain University College Department of Medical Instruments Engineering Techniques Diyala Iraq International Business Management Department Tashkent State University of Economics Tashkent Uzbekistan

ISBN: (纸本)9781450399050

Although manipulations of visual and aural media have been around for as long as there have been media, the relatively recent introduction of deep fakes has marked a turning point in the creation of fake information. Deep fakes are automated methods that allow the creation of fake information that is becoming increasingly difficult for human observers to see. These procedures are made possible by the most recent technological advancements in artificial intelligence and deep learning. Deep Learning is a powerful method that is now being implemented in a variety of industries, including natural language processing, computer vision, image processing, and machine vision. Deep fakes are created by the use of deep learning algorithms in order to synthesize and modify photos, videos, or sounds of a person, to the point that human people are unable to discern the fake from the real one. In this article, we present a workable description of deep fakes as well as an outline of the technology that lies underneath them. In order to assist people in thinking about the future of deep fakes, we outline the benefits of the deepfake as well as the potential threats. This study presents a complete analysis of deep fake methods and discusses the most effective strategies for preventing counterfeiting. © 2022 ACM.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

1st International conference on Advanced Computing, Machine Learning, Robotics and Internet Technologies, AMRIT 2023

1st International Conference on Advanced Computing, Machine ...

引用

1st International conference on Advanced Computing, Machine Learning, Robotics and Internet Technologies, AMRIT 2023

ISBN: (纸本)9783031472237

The proceedings contain 46 papers. The special focus in this conference is on Advanced Computing, Machine Learning, Robotics and Internet Technologies. The topics include: Galactic Simulation: visual Perception of Anisotropic Dark Matter;Protocol Anomaly Detection in IIoT;Agricultural Informatics & ICT: The Foundation, Issues, Challenges and Possible Solutions—A Policy Work;a Guava Leaf Disease Identification Application;text to image Generation Using Attentional Generative Adversarial Network;attention-CoviNet: A Deep-Learning Approach to Classify Covid-19 Using Chest X-Rays;a Deep Learning Framework for Violence Detection in Videos Using Transfer Learning;multi-focus image Fusion Methods: A Review;cache Memory and On-Chip Cache Architecture: A Survey;authenticating Smartphone Users Continuously Even if the Smartphone is in the User’s Pocket;Comparative Analysis of Machine Learning Algorithms for COVID-19 Detection and Prediction;machine Learning Classifiers Explanations with Prototype Counterfactual;a Systematic Study of Super-Resolution Generative Adversarial Networks: Review;Stance Detection in Manipuri Editorial Article Using CRF;deep Learning Based Software Vulnerability Detection in Code Snippets and Tag Questions Using Convolutional Neural Networks;a Comprehensive Study of the Performances of Imbalanced Data Learning Methods with Different Optimization Techniques;Smart Parking System Using Arduino and IR Sensor;quMaDe: Quick Foreground Mask and Monocular Depth Data Generation;fine-Grained Air Quality with Deep Air Learning;enhancing Melanoma Skin Cancer Detection with Machine Learning and image processing Techniques;image processing Technique and SVM for Epizootic Ulcerative Syndrome Fish image Classification.

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415页 << < 77 78 79 80 81 82 83 84 85 86 > >>

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：