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
51 篇 期刊文献
18 册 图书
1 篇 学位论文

馆藏范围

4,143 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

2,371 篇 工学
- 1,630 篇 计算机科学与技术...
- 1,017 篇 信息与通信工程
- 850 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
- 35 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
1,077 篇 理学
- 837 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
1,032 篇 医学
- 1,018 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
402 篇 image processing
353 篇 visual communica...
311 篇 visualization
235 篇 feature extracti...
230 篇 image segmentati...
174 篇 image compressio...
158 篇 image reconstruc...
147 篇 video coding
133 篇 training
130 篇 cameras
124 篇 humans
118 篇 image color anal...
115 篇 image quality
111 篇 signal processin...
109 篇 image enhancemen...
102 篇 deep learning
102 篇 image edge detec...
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

3,958 篇 英文
126 篇 其他
49 篇 土耳其文
41 篇 中文

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

共 4143 条记录，以下是1241-1250 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：

Research on Multi-focus image Fusion processing Algorithm

Research on Multi-focus Image Fusion Processing Algorithm

引用

Chinese Control and Decision conference, CCDC

作者： Tongying LI Hongbo ZHU Nantong Polytechnic College Nantong China Key Lab on Wideband Wireless Communications Nanjing University of Posts and Telecommunications Nanjing China

ISBN: (数字)9781728158556

ISBN: (纸本)9781728158563

When two or more objects in the scene are at different distances from the camera, the image obtained cannot be in focus everywhere. Usually many images are taken at different focus settings. By fusing images with different focus point, and image that is in focus everywhere can be obtained. This paper uses wavelet transform theory to deal with the fusion of the multi-focuses images and implements it using computer simulation. It can be analyzed from the experimentation results that each object is clear after the fusion and the fused image is more suitable for human visual perception and computer processing.

关键词： image fusion Matlab Discrete wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

GRNet: Deep Convolutional Neural Networks based on Graph Reasoning for Semantic Segmentation

GRNet: Deep Convolutional Neural Networks based on Graph Rea...

引用

IEEE visual communications and image processing (VCIP)

作者： Yang Wu Aimin Jiang Yibin Tang Hon Keung Kwan College of Internet of Things Hohai University University of Windsor

ISBN: (数字)9781728180687

ISBN: (纸本)9781728180694

In this paper, we develop a novel deep-network architecture for semantic segmentation. In contrast to previous work that widely uses dilated convolutions, we employ the original ResNet as the backbone, and a multi-scale feature fusion module (MFFM) is introduced to extract long-range contextual information and upsample feature maps. Then, a graph reasoning module (GRM) based on graph-convolutional network (GCN) is developed to aggregate semantic information. Our graph reasoning network (GRNet) extracts global contexts of input features by modeling graph reasoning in a single framework. Experimental results demonstrate that our approach provides substantial benefits over a strong baseline and achieves superior segmentation performance on two benchmark datasets.

关键词： Semantics Convolution Cognition image segmentation Feature extraction Training Network architecture

来源：评论

学校读者我要写书评

暂无评论

processing Color images, Brightness and Color Conversion

Processing Color Images, Brightness and Color Conversion

引用

2019 International conference on Information Science and communications Technologies, ICISCT 2019

作者： Beknazarova, Saida Safibullaevna Mukhamadiyev, Abduvali Shukurovich Kizi, Jaumitbayeva Mehriban Karamtdin Tashkent University of Information Technologies Named by Muhammad Al-Khwarizmi Dept. Audiovisual Technologies Tashkent Uzbekistan

ISBN: (纸本)9781728125640

The use of color in image processing is due to two main reasons. Firstly, color is an important feature that often facilitates recognition and selection of an object in an image. Secondly, a person is able to distinguish between thousands of different shades of color and only about two dozen shades of gray. The second circumstance is especially important when visual (that is, performed directly by man) image *** of color images can divided into two main areas: image processing in natural colors and image processing in pseudo-colors. In the first case, the images in question are usually formed by color image recording devices, such as a color television camera or a color scanner. In the second case, the task is to assign colors to some intensity values of a monochrome signal or to some ranges of changes in its intensity. Until relatively recently, digital processing of color images was carried out mostly at the level of pseudo colors. Over the past decade, however, color input devices and color image processing hardware have become quite affordable. As a result, natural image processing technology currently used in a wide range of applications, including publishing systems, visualization systems, and the Internet. It will be clear from the subsequent discussions that some halftone processing techniques developed in previous chapters are directly applicable to color images. Other methods should be reformulated and consistent with the properties of the color space, which constructed later in this chapter. The methods described in this chapter are far from exhaustive;they illustrate a variety of techniques applicable to color image processing. © 2019 IEEE.

关键词： Luminance

来源：评论

学校读者我要写书评

暂无评论

Efficient Light Deep Network for Street Scene Parsing

Efficient Light Deep Network for Street Scene Parsing

引用

IEEE visual communications and image processing (VCIP)

作者： ZheHui Wang Sanyuan Zhao Jianbing Shen Zhengchao Lei Beijing Institute of Technology Coordination Center of China

ISBN: (数字)9781728180687

ISBN: (纸本)9781728180694

The semantic segmentation is a dense pixel label pre-diction task, which takes quite a lot of resources and computation cost in most of the time. In our approach, we pay attention to balance the speed and better performance which outperforms the state of the art in speed and accuracy for real-time performance. We come up with the idea of new efficient deep backbone that can extract more semantic details, reduce the computation cost and be easy to deploy at the same time. We call our new backbone as Cascaded Mobile Network, which is proved to be very useful. Our proposed model achieves 72.1 mIOU on the CityScapes val, and 69.5 on CamVid. We achieve good balance between speed and accuracy.

关键词： Feature extraction Semantics Real-time systems image segmentation Knowledge engineering Convolution Training

来源：评论

学校读者我要写书评

暂无评论

A Discrete Cosine Model of Light Field Sampling for Improving Rendering Quality of Views

A Discrete Cosine Model of Light Field Sampling for Improvin...

引用

IEEE visual communications and image processing (VCIP)

作者： Ying Wei Changjian Zhu You Yang Yan Liu School of Electron. Engineering Guangxi Normal Univ Guilin China School of Electron. and Inform. Comm Huazhong Univ. of Sci. and Tech Wuhan China

ISBN: (数字)9781728180687

ISBN: (纸本)9781728180694

A number of theories have been proposed for reducing sampling rate of light field. But these theories still need a great many of samples (images) to obtain sufficient geometric information. In this paper, we utilize the sparse representation of light field in Discrete Cosine Transform domain to present a Discrete Cosine Sparse Basis (DCSB). Thus, we can find out the zeros of DCSB to reduce sampling requirement of light field for alias-free rendering. Finally, experimental results demonstrate the effectiveness of our approach without lose information.

关键词： image reconstruction Discrete cosine transforms Two dimensional displays Rendering (computer graphics) Graphics Art Three-dimensional displays

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Nonlinear Transform for HEVC Intra Coding

Deep Learning-Based Nonlinear Transform for HEVC Intra Codin...

引用

IEEE visual communications and image processing (VCIP)

作者： Kun Yang Dong Liu Feng Wu CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei China

ISBN: (数字)9781728180687

ISBN: (纸本)9781728180694

In the hybrid video coding framework, transform is adopted to exploit the dependency within the input signal. In this paper, we propose a deep learning-based nonlinear transform for intra coding. Specifically, we incorporate the directional information into the residual domain. Then, a convolutional neural network model is designed to achieve better decorrelation and energy compaction than the conventional discrete cosine transform. This work has two main contributions. First, we propose to use the intra prediction signal to reduce the directionality in the residual. Second, we present a novel loss function to characterize the efficiency of the transform during the training. To evaluate the compression performance of the proposed transform, we implement it into the High Efficiency Video Coding reference software. Experimental results demonstrate that the proposed method achieves up to 1.79% BD-rate reduction for natural videos.

关键词： Transforms Discrete cosine transforms Neural networks Transform coding Video coding image coding Decoding

来源：评论

学校读者我要写书评

暂无评论

Reduced-Reference Stereoscopic image Quality Assessment Based on Entropy of Gradient Primitives

Reduced-Reference Stereoscopic Image Quality Assessment Base...

引用

IEEE International conference on Signal and image processing (ICSIP)

作者： Jian Ma Xinxin Zhao Youxin Xu School of Internet Anhui University School of Electronics and Communications Engineering Anhui xinhua University Marvell Technology Group Ltd.

ISBN: (数字)9781728168968

ISBN: (纸本)9781728168975

Stereoscopic image quality assessment (SIQA) has always been challenging due to the remarkable distinction between human monocular and binocular vision. This paper proposes a novel gradient-based dictionary learning method for SIQA, which effectively integrates the gradients are sparser than the image itself. Specifically, we first compute the gradient maps of each view image of stereopair by applying contrast sensitivity of human visual system (HVS) and neighborhood gradient information to weight the gradient magnitudes in a locally adaptive manner. Afterwards, the binocular perceptual information of gradient (GBPI) is represented by the distribution statistics of visual primitives in gradient maps of left and right views' images, which are extracted by sparse representation. Furthermore, the entropy of gradient maps of each views' images are utilized to represent monocular cue. Their mutual information is used to represent binocular cue. The difference of the reference and distorted images' GBPIs is taken as quality-ware features. Finally, the kernel ridge regressing (KRR) is utilized to simulate a nonlinear relationship between the quality-ware features and human opinions. The performance of the proposed metric is evaluated over the LIVE 3D phase II asymmetric datasets, and shown to be competitive with the state-of-the-art SIQA algorithms.

关键词： image quality visualization Three-dimensional displays Stereo image processing Nonlinear distortion visual systems Entropy

来源：评论

学校读者我要写书评

暂无评论

News image Steganography: A Novel Architecture Facilitates the Fake News Identification

News Image Steganography: A Novel Architecture Facilitates t...

引用

IEEE visual communications and image processing (VCIP)

作者： Jizhe Zhou Chi-Man Pun Yu Tong University of Macao Macao China vivo AI Lab vivo Mobile Communication Co. Ltd ShenZhen China

ISBN: (数字)9781728180687

ISBN: (纸本)9781728180694

A larger portion of fake news quotes untampered images from other sources with ulterior motives rather than conducting image forgery. Such elaborate engraftments keep the inconsistency between images and text reports stealthy, thereby, palm off the spurious for the genuine. This paper proposes an architecture named News image Steganography (NIS) to reveal the aforementioned inconsistency through image steganography based on GAN. Extractive summarization about a news image is generated based on its source texts, and a learned steganographic algorithm encodes and decodes the summarization of the image in a manner that approaches perceptual invisibility. Once an encoded image is quoted, its source summarization can be decoded and further presented as the ground truth to verify the quoting news. The pairwise encoder and decoder endow images of the capability to carry along their imperceptible summarization. Our NIS reveals the underlying inconsistency, thereby, according to our experiments and investigations, contributes to the identification accuracy of fake news that engrafts untampered images.

关键词： Decoding Training Perturbation methods Gallium nitride Forgery Printers Media

来源：评论

学校读者我要写书评

暂无评论

Hybrid regularization with elastic net and linear discriminant analysis for zero-shot image recognition 34

Hybrid regularization with elastic net and linear discrimina...

引用

34th IEEE International conference on visual communications and image processing, VCIP 2019

作者： Qin, Zhen Li, Yan Beijing University of Posts and Telecommunications School of Information and Communication Engineering Beijing China Beijing Institute of Technology School of Information and Electronics Beijing China

ISBN: (纸本)9781728137230

Zero-shot learning (ZSL) is the process of recognizing unseen samples from their related classes. Generally, ZSL is realized with the help of some pre-defined semantic information via projecting high dimensional visual features of data samples and class-related semantic vectors into a common embedding space. Although classification can be simply decided through the nearest-neighbor strategy, it usually suffers from problems of domain shift and hubness. In order to address these challenges, majority of researches have introduced regularization with some existing norms, such as lasso or ridge, to constrain the learned embedding. However, the sparse estimation of lasso may cause underfitting of training data, while ridge may introduce bias in the embedding space. In order to resolve these problems, this paper proposes a novel hybrid regularization approach by leveraging elastic net and linear discriminant analysis, and formulates a unified objective function that can be solved efficiently via a synchronous optimization strategy. The proposed method is evaluated on several benchmark image datasets for the task of generalized ZSL. The obtained results demonstrate the superiority of the proposed method over simple regularized methods as well as several previous models. © 2019 IEEE.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Feature2Mass: visual Feature processing in Latent Space for Realistic Labeled Mass Generation 15th

Feature2Mass: Visual Feature Processing in Latent Space for ...

引用

15th European conference on Computer Vision (ECCV)

作者： Lee, Jae-Hyeok Kim, Seong Tae Lee, Hakmin Ro, Yong Man Korea Adv Inst Sci & Technol Sch Elect Engn Daejeon South Korea

ISBN: (纸本)9783030110246;9783030110239

This paper deals with a method for generating realistic labeled masses. Recently, there have been many attempts to apply deep learning to various bio-image computing fields including computer-aided detection and diagnosis. In order to learn deep network model to be well-behaved in bio-image computing fields, a lot of labeled data is required. However, in many bioimaging fields, the large-size of labeled dataset is scarcely available. Although a few researches have been dedicated to solving this problem through generative model, there are some problems as follows: (1) The generated bio-image does not seem realistic;(2) the variation of generated bio-image is limited;and (3) additional label annotation task is needed. In this study, we propose a realistic labeled bio-image generation method through visual feature processing in latent space. Experimental results have shown that mass images generated by the proposed method were realistic and had wide expression range of targeted mass characteristics.

关键词： Feature processing in latent space image synthesis Bio-image generation Medical mass generation

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 << < 121 122 123 124 125 126 127 128 129 130 > >>

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：