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

1,414 篇 会议
20 篇 期刊文献

馆藏范围

1,434 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

869 篇 工学
- 588 篇 计算机科学与技术...
- 305 篇 软件工程
- 295 篇 电气工程
- 265 篇 信息与通信工程
- 82 篇 光学工程
- 56 篇 电子科学与技术（可...
- 42 篇 控制科学与工程
- 33 篇 生物医学工程（可授...
- 25 篇 测绘科学与技术
- 23 篇 机械工程
- 23 篇 仪器科学与技术
- 11 篇 生物工程
- 9 篇 材料科学与工程（可...
- 8 篇 航空宇航科学与技...
- 7 篇 动力工程及工程热...
- 7 篇 土木工程
- 7 篇 网络空间安全
379 篇 理学
- 251 篇 物理学
- 167 篇 数学
- 25 篇 统计学（可授理学、...
- 14 篇 生物学
- 10 篇 化学
- 10 篇 系统科学
229 篇 医学
- 221 篇 临床医学
- 23 篇 特种医学
- 11 篇 基础医学(可授医学...
- 9 篇 药学(可授医学、理...
47 篇 管理学
- 32 篇 管理科学与工程(可...
- 13 篇 图书情报与档案管...
7 篇 法学
- 6 篇 社会学
3 篇 农学
2 篇 经济学
2 篇 文学
2 篇 艺术学
1 篇 教育学

主题

440 篇 image compressio...
399 篇 image coding
190 篇 video compressio...
140 篇 transform coding
106 篇 data compression
76 篇 discrete cosine ...
71 篇 image reconstruc...
70 篇 decoding
61 篇 image quality
58 篇 quantization
58 篇 wavelet transfor...
56 篇 bit rate
55 篇 compression
55 篇 point cloud comp...
54 篇 discrete wavelet...
50 篇 video coding
46 篇 three-dimensiona...
42 篇 pixel
42 篇 psnr
42 篇 encoding

机构

5 篇 institute of cir...
5 篇 national key lab...
4 篇 pengcheng labora...
4 篇 peng cheng lab p...
4 篇 center for signa...
3 篇 univ sci & techn...
3 篇 harbin inst tech...
3 篇 department of co...
3 篇 electronic commu...
3 篇 univ stuttgart r...
3 篇 department of el...
3 篇 wangxuan institu...
3 篇 ricoh california...
2 篇 university of sc...
2 篇 institute of inf...
2 篇 tit&s coll bhiwa...
2 篇 school of inform...
2 篇 chongqing commun...
2 篇 dipartimento di ...
2 篇 fraunhofer insti...

作者

5 篇 richter thomas
5 篇 schelkens peter
5 篇 ebrahimi touradj
5 篇 y. altunbasak
5 篇 valenzise giusep...
5 篇 kountchev roumen
4 篇 w. kinsner
4 篇 battiato s
4 篇 yang yang
4 篇 baronti s
4 篇 deforges olivier
4 篇 alparone l
4 篇 mancuso m
4 篇 kountcheva roumi...
4 篇 ebrahimi t
4 篇 aiazzi b
3 篇 abir jaafar huss...
3 篇 k. k. mahapatra
3 篇 chun-shien lu
3 篇 bao youneng

语言

1,412 篇 英文
12 篇 中文
8 篇 其他
2 篇 土耳其文

检索条件"任意字段=Conference on Still-Image Compression"

共 1434 条记录，以下是1-10 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：

Cool-Chic: Perceptually Tuned Low Complexity Overfitted image Coder

Cool-Chic: Perceptually Tuned Low Complexity Overfitted Imag...

引用

Data compression conference (DCC)

作者： Ladune, Theo Philippe, Pierrick Clare, Gordon Henry, Felix Leguay, Thomas Orange Innovat Cesson Sevigne France

ISBN: (纸本)9798350385885;9798350385878

This paper summarises the design of the Cool-Chic candidate for the Challenge on Learned image compression. This candidate attempts to demonstrate that neural coding methods can lead to low complexity and lightweight image decoders while still offering competitive performance. The approach is based on the already published over fitted lightweight neural networks Cool-Chic, further adapted to the human subjective viewing targeted in this challenge.

关键词： image compression

来源：评论

学校读者我要写书评

暂无评论

TALKING-HEAD VIDEO compression WITH MOTION SEMANTIC ENHANCEMENT MODEL 31

TALKING-HEAD VIDEO COMPRESSION WITH MOTION SEMANTIC ENHANCEM...

引用

2024 International conference on image Processing

作者： Lei, Haobo Bie, Zhisong Jing, Zhao Bie, Hongxia Beijing Univ Posts & Telecommun Beijing Peoples R China

ISBN: (纸本)9798350349405;9798350349399

The continuously advancing image generation technology has been utilized for high-quality video reconstruction using low-bitrate feature representation. The motion semantic representations provided by existing models exhibit significant redundancy, indicating that their potential as video compression tools is still to be fully explored. In this work, we propose a motion semantic enhancement model called MSEM for ultra-low-bitrate talking-head video compression, aiming at improving semantic extraction effectiveness and compactness. Specifically, we enhance semantic extraction accuracy by introducing a deformable feature estimator with flexible receptive field shapes. Based on the straight-through gradient estimation, we construct a semantic encoding space that contains more compact semantic representations with low redundancy. Extensive experiments clearly demonstrate that i) compared to mainstream semantic compression models, our method has stronger semantic feature extraction capabilities benefiting from a more reasonable semantic feature impact range, and ii) our method provides an average bitrate reduction for the same visual quality of more than 50% compared to VVC.

关键词： video compression motion semantic representation deformable feature estimation

来源：评论

学校读者我要写书评

暂无评论

ENHANCED INTERPRETABILITY IN LEARNED image compression VIA CONVOLUTIONAL SPARSE CODING

ENHANCED INTERPRETABILITY IN LEARNED IMAGE COMPRESSION VIA C...

引用

IEEE International conference on Multimedia and Expo (ICME)

作者： Tu, Yiwen Tan, Wen Bao, Youneng Wang, Genhong Meng, Fanyang Liang, Yongsheng Harbin Inst Technol Shenzhen Peoples R China Peng Cheng Lab Shenzhen Peoples R China Shenzhen Technol Univ Shenzhen Peoples R China

ISBN: (纸本)9798350390155;9798350390162

Compared to traditional image compression methods, learned image compression (LIC) methods have demonstrated increasingly superior rate-distortion performance. However, LIC networks are often regarded as black boxes, still lacking a theoretical understanding. Sparse coding provides the sparse and interpretable modeling for analyzing or synthesizing natural images in various signal and image processing applications. Therefore, we introduce convolutional sparse coding (CSC) into transform network for enhancing the interpretability of LIC methods. In this paper, we first employ CSC layers to achieve certain theoretical modeling for LIC network, and adopt a weight sharing strategy in encoderdecoder pair and attention mechanism to balance the complexity and performance. Additionally, we analyze the model robustness against data input perturbations and consider the impact of sparsity trade-off parameter in the CSC layer optimization process. Experimental results demonstrate that our method achieves comparable performance with the corresponding baseline, and our model is more robust.

关键词： Learned image compression sparse coding interpretability robustness

来源：评论

学校读者我要写书评

暂无评论

RQAT-INR: Improved Implicit Neural image compression

RQAT-INR: Improved Implicit Neural Image Compression

引用

Data compression conference (DCC)

作者： Damodaran, Bharath Bhushan Balcilar, Muhammet Galpin, Franck Hellier, Pierre InterDigital Inc Rennes France

ISBN: (纸本)9798350347951

Deep variational autoencoders for image and video compression have gained significant attraction in the recent years, due to their potential to offer competitive or better compression rates compared to the decades long traditional codecs such as AVC, HEVC or VVC. However, because of complexity and energy consumption, these approaches are still far away from practical usage in industry. More recently, implicit neural representation (INR) based codecs have emerged, and have lower complexity and energy usage to classical approaches at decoding. However, their performances are not in par at the moment with state-of-the-art methods. In this research, we first show that INR based image codec has a lower complexity than VAE based approaches, then we propose several improvements for INR-based image codec and outperformed baseline model by a large margin.

关键词： implicit neural image compression implicit neural representation learning based compression low complexity neural image compression neural image compression quantization aware training

来源：评论

学校读者我要写书评

暂无评论

Overfitted image coding at reduced complexity 32

Overfitted image coding at reduced complexity

引用

32nd European Signal Processing conference (EUSIPCO)

作者： Blard, Theophile Ladune, Theo Philippe, Pierrick Clare, Gordon Jiang, Xiaoran Deforges, Olivier Orange Innovat Paris France IETR Rennes France

ISBN: (纸本)9789464593617;9798331519773

Overfitted image codecs offer compelling compression performance and low decoder complexity, through the overfitting of a lightweight decoder for each image. Such codecs include Cool-chic, which presents image coding performance on par with VVC while requiring around 2000 multiplications per decoded pixel. This paper proposes to decrease Cool-chic encoding and decoding complexity. The encoding complexity is reduced by shortening Cool-chic training, up to the point where no overfitting is performed at all. It is also shown that a tiny neural decoder with 300 multiplications per pixel still outperforms HEVC. A near real-time CPU implementation of this decoder is made available at https://***/Cool-Chic/.

关键词： image compression low-complexity neural coding overfitting

来源：评论

学校读者我要写书评

暂无评论

A Joint image Encryption and compression Algorithm Based on CycleGAN 36

A Joint Image Encryption and Compression Algorithm Based on ...

引用

36th Chinese Control and Decision conference (CCDC)

作者： You, Yue Mao, Yaobin Nanjing Univ Sci & Tech Sch Automat Nanjing Peoples R China

ISBN: (纸本)9798350387780;9798350387797

Digital images are easy to copy, spread, and tampering, therefore, protecting image contents in the digital era has emerged as a key focus of multimedia security research. Recently, researchers have introduced deep learning technology into cryptography, but how to reasonably integrate cipher keys into neural networks and how to combining compression with encryption are still a challenge work. This paper proposes a new image encryption-compression network based on CycleGAN, which is strictly in accordance with the principle of cryptography. In the encryption phase, the key and the plain image are fed into the encryption network to generate a one-channel cipher image. Conversely, in the decryption phase, the same key and the cipher image are fed into the decryption network to perform deciphering, while the cipher image cannot be deciphered when the incorrect key is used. Both encryption and decryption networks take use of CycleGAN, and a new auxiliary network is designed to ensure the key sensitivity to the encryptioncompression network, thus the security of the system is enhanced. Experimental results have demonstrated the feasibility of the proposed scheme.

关键词： image encryption CycleGAN multimedia security

来源：评论

学校读者我要写书评

暂无评论

Optimization of image compression and Decompression Performance Based on Genetic Algorithm

Optimization of Image Compression and Decompression Performa...

引用

2024 International conference on Interactive Intelligent Systems and Techniques, IIST 2024

作者： Li, Weishi Yin, Chun Fujian Polytechnic of Information Technology Fuzhou China

ISBN: (纸本)9798350374421

As one of the main carriers of information transmission and storage, image data need to be compressed in some application scenarios. Traditional image compression methods, although reducing the size of image files to a large extent, are still difficult to meet the performance requirements of massive, high-speed image data compression processing. In this paper, an image compression and decompression performance amelioration method based on genetic algorithm is proposed, aiming to ameliorate the efficiency and quality of image compression, while reducing the time and computational complexity of decompression. This paper first introduces the background and current status of image compression technology, and analyzes the progress of existing image compression research. Then, the basic principles of genetic algorithm and its application in image compression are introduced in detail. On this basis, an image compression algorithm based on genetic algorithm is proposed. The algorithm ameliorates the parameter settings in the image compression process through genetic algorithm to achieve efficient compression of images. At the same time, combined with the image decompression process, the decompression algorithm is ameliorated to reduce the consumption of computational resources. The research in this paper provides new ideas and methods for the performance amelioration of image compression and decompression technology, which has important theoretical and practical value. © 2024 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

EVENT DATA STREAM compression BASED ON POINT CLOUD REPRESENTATION 30

EVENT DATA STREAM COMPRESSION BASED ON POINT CLOUD REPRESENT...

引用

30th IEEE International conference on image Processing (ICIP)

作者： Huang, Bowen Ebrahimi, Touradj Ecole Polytech Fed Lausanne EPFL Multimedia Signal Proc Grp MMSPG CH-1012 Lausanne Switzerland

ISBN: (纸本)9781728198354

The Dynamic Vision System (DVS) is a novel image acquisition system that works only when there is a brightness change in a pixel, resulting in a stream of events including timestamps, spatial coordinates and the sign of the brightness change (increase or decrease). Although DVS's output data size is much smaller than conventional image systems, it still requires further compression, as the main applications of DVS are embedded systems with limited transmission and storage resources. In this paper, we propose a new method for lossless compression of event data streams based on point cloud representations. The event data stream is organized into a 3D point cloud to which a compression algorithm is applied. In addition, different generation strategies are devised in order to compare the compression performance of the proposed approach. Experimental results show an improved compression ratio of about 22% under lossless conditions.

关键词： Event camera data compression point cloud

来源：评论

学校读者我要写书评

暂无评论

EFFICIENT PRUNING METHOD FOR LEARNED LOSSY image compression MODELS BASED ON SIDE INFORMATION 30

EFFICIENT PRUNING METHOD FOR LEARNED LOSSY IMAGE COMPRESSION...

引用

30th IEEE International conference on image Processing (ICIP)

作者： Chen, Weixuan Yang, Qianqian Zhejiang Univ Coll Informat Sci & Elect Engn Hangzhou 310007 Peoples R China

ISBN: (纸本)9781728198354

In recent years, deep learning-based lossy image compression have achieved great success. However, the problem of their huge overhead in terms of computational and parametric costs has still not been adequately addressed. Inspired by the classical image compression methods, deep learning based models are usually combined with an entropy model to maintain the compression performance. Existing methods also introduce side information to serve as a prior on the parameters of the entropy model, which have achieved better rate-distortion performance. Based on the role of side information in learned image compression models, we propose an efficient pruning method for such models. In particular, the proposed pruning approach automatically searches for the optimal decoder architecture based on the extent to which each hidden layer in the decoder utilizes side information. The experiment results demonstrate the effectiveness of the proposed method and show that it outperforms all existing related studies in terms of compression performance.

关键词： Deep learning Lossy image compression Network pruning Side information

来源：评论

学校读者我要写书评

暂无评论

Comparative Evaluation of Various Wavelet Techniques for image compression 4

Comparative Evaluation of Various Wavelet Techniques for Ima...

引用

4th IEEE International conference on Applied Electromagnetics, Signal Processing, and Communication, AESPC 2024

作者： Nisa, Hidayat Un Mehraj, Samrah Parah, Shabir A. University of Kashmir Dept. of Electronics and Instrumentation Technology Srinagar India

ISBN: (纸本)9798331528171

image compression is a critical component of digital systems, as it reduces the file size of images while preserving quality, thereby facilitating minimal storage requirements and seamless transmission. Wavelet transforms have emerged as powerful tools in image compression for providing both time and frequency information, making them particularly effective in capturing essential image features. Despite numerous advancements, there is still significant demand for image compression techniques that achieve higher compression ratios with minimal loss of quality. This paper presents a comprehensive analysis of various lossy image compression techniques, focusing on the strengths of wavelet-based methods. Techniques such as Discrete Wavelet Transform, Lifting Wavelet Transform, and Integer Wavelet Transform are examined in detail, with key metrics including Peak Signal-to-Noise Ratio (PSNR), compression ratio, and time efficiency analyzed to provide a thorough understanding of each technique's effectiveness. The timing analysis is particularly crucial for assessing the practical applicability of these methods in real-world scenarios. This study aims to offer valuable insights for developing more advanced image compression methods that meet the growing demands of modern data management systems. © 2024 IEEE.

关键词： Information management

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144页 << < 1 2 3 4 5 6 7 8 9 10 > >>

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：