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

3,429 篇 会议
27 篇 期刊文献
14 册 图书

馆藏范围

3,470 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,946 篇 工学
- 1,271 篇 计算机科学与技术...
- 955 篇 信息与通信工程
- 686 篇 软件工程
- 520 篇 电气工程
- 190 篇 光学工程
- 108 篇 生物工程
- 79 篇 电子科学与技术（可...
- 62 篇 生物医学工程（可授...
- 60 篇 仪器科学与技术
- 60 篇 控制科学与工程
- 54 篇 机械工程
- 33 篇 化学工程与技术
- 32 篇 网络空间安全
- 23 篇 动力工程及工程热...
- 23 篇 安全科学与工程
- 13 篇 土木工程
- 13 篇 交通运输工程
959 篇 医学
- 951 篇 临床医学
- 29 篇 基础医学(可授医学...
- 26 篇 药学(可授医学、理...
774 篇 理学
- 574 篇 物理学
- 192 篇 数学
- 114 篇 生物学
- 53 篇 统计学（可授理学、...
- 33 篇 化学
- 29 篇 系统科学
132 篇 管理学
- 71 篇 管理科学与工程(可...
- 69 篇 图书情报与档案管...
- 17 篇 工商管理
30 篇 法学
- 28 篇 社会学
11 篇 军事学
9 篇 文学
5 篇 经济学
5 篇 农学
4 篇 教育学

主题

418 篇 image coding
349 篇 visual communica...
308 篇 image processing
293 篇 visualization
222 篇 feature extracti...
177 篇 image segmentati...
147 篇 image compressio...
139 篇 training
136 篇 video coding
130 篇 image reconstruc...
117 篇 image color anal...
107 篇 cameras
103 篇 image quality
100 篇 deep learning
95 篇 image enhancemen...
88 篇 image edge detec...
85 篇 humans
83 篇 three-dimensiona...
77 篇 motion estimatio...
76 篇 decoding

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 andré kaup
14 篇 chen zhibo
13 篇 xie rong
13 篇 xiongkuo min
12 篇 gao wen
11 篇 heming sun
11 篇 zhibo chen
11 篇 zhenzhong chen
11 篇 gao zhiyong

语言

3,406 篇 英文
49 篇 土耳其文
22 篇 中文
7 篇 其他

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

共 3470 条记录，以下是481-490 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：

Microscopic Fluorescence In Situ Hybridization (FISH) image Synthesis with Generative Adversarial Networks 29

Microscopic Fluorescence In Situ Hybridization (FISH) Image ...

引用

29th IEEE conference on Signal processing and communications Applications (SIU)

作者： Dursun, Gizem Ozkaya, Ufuk Suleyman Demirel Univ Elekt Elekt Muhendisligi Isparta Turkey

ISBN: (纸本)9781665436496

One of the most important problems in biomedical image analysis is the low amount of data and the cost of accessing to the marked data by researchers. In order to provide a solution to this problem, microscopic fluorescence in situ hybridization (FISH) images are synthesized with generative adversarial network in this paper. The generative adversarial network is trained to synthesize FISH images from mask images. The trained model was implemented on 150 test images and the performance of the model both was presented with visual results and evaluated quantitatively by calculating the performance metrics. By evaluating the synthesized FISH images in terms of image quality and structural features, it is observed that they can be used to provide a solution to the problem of the lack of data.

关键词： generative adversarial networks image synthesis fluorescence in situ hybridization

来源：评论

学校读者我要写书评

暂无评论

ARITM: A Perceptual Quality Magnification of Noise Suppressed Digital images using Adaptive Recursion and image Transformation Model

ARITM: A Perceptual Quality Magnification of Noise Suppresse...

引用

2023 International conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2023

作者： Kannan, K. Divya, G. Chithra, L. Aruna, V. Mohanavel, V. College of Engineering and Technology Puduvoyal Department of ECER.M.K. Chennai India SRM Institute of Science and Technology Kattankulathur Faculty of Engineering and Technology Department of Networking and Communications Chennai India S.A.Engineering College Department of ECE Chennai India Panimalar Engineering College Department of ECE Chennai India Bharath Institute of Higher Education and Research Centre for Materials Engineering and Regenerative Medicine Tamil Nadu Chennai India Chandigarh University Department of Mechanical Engineering Punjab Mohali140413 India

ISBN: (纸本)9798350319200

In the realm of digital image processing and enhancement, the relentless pursuit of achieving higher perceptual quality in noise-suppressed images has remained a compelling challenge. This abstract presents a novel approach that leverages the synergy between adaptive recursion and a sophisticated image transformation model to magnify the perceptual quality of noise-suppressed digital images. The proliferation of digital imagery in various applications, from medical diagnostics to multimedia content, necessitates the development of advanced techniques to preserve and enhance image fidelity. While noise suppression techniques have made significant strides in reducing unwanted artifacts, they often introduce trade-offs between noise reduction and preservation of image details. Our proposed method begins by employing adaptive recursion, where the image is divided into local regions, each analyzed independently for noise characteristics and visual features. Adaptive recursion ensures that noise reduction is applied selectively, preserving important image details, even in challenging scenarios. The synergy between adaptive recursion and the image transformation model is a key highlight of our approach. By iteratively applying the transformation model within each local region, we adaptively enhance image features that contribute to perceptual quality, such as sharpness, contrast, and color fidelity. This adaptive enhancement process ensures that image details are magnified while suppressing noise artifacts, ultimately resulting in images of superior perceptual quality. Our experimental results, conducted on diverse datasets with various levels of noise, demonstrate significant improvements in perceptual quality compared to state-of-the-art methods. Additionally, we evaluate the computational efficiency of our approach, highlighting its feasibility for real-time and high-throughput image enhancement applications. © 2023 IEEE.

关键词： Adaptive Recursion Generative Adversarial Networks (GANs) Noise-suppressed images

来源：评论

学校读者我要写书评

暂无评论

Filling the Gap: Enhancing Ultra-Low Light image Brightness Through Multi-Band NIR Estimation

Filling the Gap: Enhancing Ultra-Low Light Image Brightness ...

引用

IEEE visual communications and image processing (VCIP)

作者： Jeong-Hyeok Park Tae-Sung Park Jong-Ok Kim School of Electrical Engineering Korea University Seoul Korea

We propose a method for capturing high-quality images in low-light environments using multi-band near-infrared (NIR) images, which offer robustness to brightness variations and provide structural information not present in RGB images. As multi-band NIR images are not commonly available in consumer cameras, an RGB-NIR conversion network is employed to estimate them. Training data comes from a new low-light dataset with NIR-RGB image pairs. Unlike single-band approaches, this method utilizes multi-band NIR images with peak wavelengths of 785nm, 850nm, and 940nm, resulting in enhanced quality. Integration of the RGB-NIR conversion network into an existing low-light enhancement (LLIE) network is achieved using the proposed cross-attention transformer. Experimental results validate the effectiveness of multi-band NIR estimation in enhancing low-light intensity. Moreover, the proposed RGB-NIR conversion network and cross-attention module can be applied to any existing deep LLIE networks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PTS-LIC: Pruning Threshold Searching for Lightweight Learned image Compression

PTS-LIC: Pruning Threshold Searching for Lightweight Learned...

引用

IEEE visual communications and image processing (VCIP)

作者： Ao Luo Heming Sun Jinming Liu Fangzheng Lin Jiro Katto Department of Computer Science and Communication Engineering Waseda University Tokyo Japan Faculty of Engineering Yokohama National University Kanagawa Japan Shanghai Jiao Tong University China Waseda Research Institute for Science and Engineering Tokyo Japan

Learned image Compression (LIC), which uses neural networks to compress images, has experienced significant growth in recent years. The hyperprior-module-based LIC model has achieved higher performance than classical codecs. However, the LIC models are too heavy (in calculation and parameter amounts) to apply to edge devices. To solve this problem, some former papers focus on structural pruning for LIC models. However, they either cause noticeable performance decrement or neglect the appropriate pruning threshold for each LIC model. These problems keep their pruning results sub-optimal. This paper proposes a Pruning Threshold Searching on the hyperprior module for different-quality LIC models. Our method removes most parameters and calculations while keeping the performance the same as the models before pruning. We removed at least 49.8% of parameters and 28.5% of calculations for the Channel-Wise-Context-Model-based models and 29.1% of parameters for the Cheng-2020 models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Portable Ticket Automatic Scanning Technology Based on Lightweight visual Recognition

Portable Ticket Automatic Scanning Technology Based on Light...

引用

Electronic communications, Internet of Things and Big Data (ICEIB), International conference on

作者： Fangyi Zhao Yuekang Yu Fan Yang School of Information and Communication Guilin University of Electronic Technology Guilin China Guilin University of Electronic Technology Guilin China

ISBN: (数字)9798350360721

ISBN: (纸本)9798350360738

In accounting and financial management, bills serve as vouchers for enterprises and government departments. The processing of bill information is fundamental to financial management with importance. We created a portable bill-scanning technique based on lightweight visual recognition. An image acquisition module was used to capture bill images, which are transmitted to a microprocessor. The microprocessor was used to grayscale the images using an improved Canny edge detection operator for bill edge scanning and correct the images using Hough transformation. Then, convolutional neural networks were utilized for financial data extraction, yielding high-quality financial data. The proposed bill-scanning method effectively reduced false alarm rates while maintaining high recall rates, addressing prevalent shortcomings in current bill-scanning technologies.

关键词： visualization image segmentation Power demand image edge detection Microprocessors Financial management Gray-scale

来源：评论

学校读者我要写书评

暂无评论

Multi-scale Parallax Attention for Stereo image Super-Resolution

Multi-scale Parallax Attention for Stereo Image Super-Resolu...

引用

IEEE visual communications and image processing (VCIP)

作者： Zilin Zhao Sumei Li Zhen Gao School of Electrical and Information Engineering Tianjin University Tianjin China

Stereo image super-resolution (SR) has achieved great progress in recent years. However, the existing methods are unable to obtain rich cross-view information at a low computational cost. In addition, these methods treat each pixel equally when fusing the cross-view information with the intra-view information, resulting in non-robustness of the fused information. In this work, we propose a multi-scale parallax attention stereo super-resolution network (MPASSRnet) to address these problems. Firstly, we design a multi-scale parallax attention module (MSPAM), which computes the similarity between stereo images on multiple scale images based on the introduction of pixel-to-patch matching, thus acquiring multi-scale cross-view information at a low computational cost. Second, we propose a pixel attention fusion module (PAFM), which introduces spatial attention (SA) by calculating the correlation between cross-view information and intra-view information, and combines channel attention (CA) to make the fused information more robust. Finally, extensive experiments show that our method achieves state-of-the-art performance on the benchmark datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Rate-Controllable and Target-Dependent JPEG-Based image Compression Using Feature Modulation

Rate-Controllable and Target-Dependent JPEG-Based Image Comp...

引用

2023 IEEE International conference on Multimedia and Expo Workshops, ICMEW 2023

作者： Jeong, Seongmoon Jeon, Kang Eun Ko, Jong Hwan Sungkyunkwan University Department of Artificial Intelligence Suwon-si Korea Republic of Convergence Research Institute Sungkyunkwan University Suwon-si Korea Republic of Sungkyunkwan University Department of Electrical and Computer Engineering Suwon-si Korea Republic of

ISBN: (纸本)9798350313154

While conventional image compression techniques are optimized for human visual perception, the rise of machine learning techniques has led to the emergence of image compression methods tailored for machine vision tasks. Although a few recent studies explored target-dependent reconfiguration of lightweight codecs such as JPEG, these approaches are limited to specific trained bitrates only. Moreover, existing deep learning-based compression frameworks entail a high computational cost, making them impractical for real-time compression on devices with limited resources. In this paper, we present a novel JPEG compression framework that can adaptively generate an optimal quantization table (QT) depending on both the target bitrate and the target metric (quality or accuracy). To provide fine controllability over a wide range of bitrates, we employ a feature modulation technique to a QT generator and bitrate predictor, which are trained by a novel training method called bitrate range partitioning. Our simulation results show that the proposed framework enhances the performance of standard JPEG by up to 2dB in PSNR and 10% in accuracy at the same bitrate, while incurring minimal computational overhead compared to JPEG. © 2023 IEEE.

关键词： image compression

来源：评论

学校读者我要写书评

暂无评论

Variable Bitrate Models For Learned image Compression with Multi-gain units and Weighted Probability Assignment

Variable Bitrate Models For Learned Image Compression with M...

引用

IEEE visual communications and image processing (VCIP)

作者： Ran Wang Wen Jiang Heming Sun Jiro Katto Department of Computer Science and Communication Engineering Waseda University Tokyo Japan Faculty of Engineering Yokohama National University Japan Department of Computer Science and Communication Engineering Waseda Research Institute for Science and Engineering Waseda University Tokyo Japan

ISBN: (数字)9798331529543

ISBN: (纸本)9798331529550

With the advancement of deep learning techniques, learned image compression (LIC) has surpassed traditional compression methods. However, these methods typically require training separate models to achieve optimal rate-distortion performance, leading to increased time and resource consumption. To tackle this challenge, we propose leveraging multi-gain and inverse multi-gain unit pairs to enable variable rate adaptation within a single model. Nevertheless, experiments have shown that rate-distortion performance may degrade at certain bitrates. Therefore, we introduce weighted probability assignment, where different selection probabilities are assigned during training based on lambda values, to increase the model’s training frequency under specific bitrate conditions. To validate our approach, extensive experiments were conducted on Transformer-based and CNN-based models. The experimental results validate the efficiency of our proposed method.

关键词： Training Degradation Deep learning Adaptation models image coding visual communication Bit rate Redundancy Rate-distortion Transformers

来源：评论

学校读者我要写书评

暂无评论

Feature Compression With 3D Sparse Convolution

Feature Compression With 3D Sparse Convolution

引用

IEEE visual communications and image processing (VCIP)

作者： Yifan Ma Changsheng Gao Qiaoxi Chen Li Li Dong Liu Xiaoyan Sun MOE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition University of Science and Technology of China Hefei China

ISBN: (数字)9798331529543

ISBN: (纸本)9798331529550

Feature compression is an important branch of video coding for machines (VCM). While existing methods draw inspiration from image compression, they have not fully utilized the unique characteristics of features. In this paper, we investigate feature characteristics in two key aspects: dimensionality and sparsity. Our analysis reveals that the low spatial dimensionality and high channel dimensionality of features make traditional 2D convolution-based methods, which usually downsample along spatial dimensions while increasing channels, unsuitable for feature compression. To address this, we propose compressing features using 3D convolution. Additionally, considering the sparsity characteristic, we propose applying sparse convolution to reduce model complexity. To thoroughly investigate the proposed 3D sparse convolution-based method, we verify it with various network structures and input features. Experimental results demonstrate the superiority of our proposed method over traditional 2D convolution-based approaches, highlighting its potential for effective feature compression.

关键词： Convolutional codes Video coding Solid modeling image segmentation image coding Three-dimensional displays Convolution visual communication Object detection Complexity theory

来源：评论

学校读者我要写书评

暂无评论

Coarse-to-fine Transformer For Lossless 3D Medical image Compression

Coarse-to-fine Transformer For Lossless 3D Medical Image Com...

引用

IEEE visual communications and image processing (VCIP)

作者： Xiaoxuan Yang Guo Lu Donghui Feng Zhengxue Cheng Guosheng Yu Li Song Shanghai Jiao Tong University Shanghai China Alibaba Group T-Head Semiconductor Co. Ltd Hangzhou China

ISBN: (数字)9798331529543

ISBN: (纸本)9798331529550

The rapid advancements in medical imaging have led to a growing demand for high-performance lossless compression of large 3D medical image datasets. Unlike natural images, medical images typically feature three-dimensional structures, and high bit-depth, necessitating specialized compression techniques. Based on a decoder-only transformer, we propose a learnable dual-decoder model for lossless compression of 3D medical images. Our approach packs voxels into patches, which are processed by a patch-level decoder to extract the patch feature. The voxels, along with the patch feature, are subsequently fed into a voxel-level decoder to model each voxel. This coarse-to-fine modeling strategy reduces the computational time for each voxel and enables long-range modeling dependencies. Experimental results demonstrate that our proposed model achieves state-of-the-art compression performance, with an approximately 15% improvement in compression performance over the traditional JP3D benchmark on various datasets.

关键词： Learning systems Solid modeling image coding Three-dimensional displays visual communication Computational modeling Transformers Feature extraction Decoding Biomedical imaging

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347页 << < 45 46 47 48 49 50 51 52 53 54 > >>

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：