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

16,563 篇 会议
211 篇 期刊文献

馆藏范围

16,774 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

10,863 篇 工学
- 7,728 篇 计算机科学与技术...
- 4,145 篇 电气工程
- 3,546 篇 软件工程
- 3,192 篇 信息与通信工程
- 1,027 篇 控制科学与工程
- 818 篇 电子科学与技术（可...
- 614 篇 生物医学工程（可授...
- 479 篇 机械工程
- 477 篇 仪器科学与技术
- 456 篇 光学工程
- 305 篇 动力工程及工程热...
- 254 篇 生物工程
- 187 篇 交通运输工程
- 166 篇 航空宇航科学与技...
- 160 篇 网络空间安全
- 122 篇 材料科学与工程（可...
- 117 篇 石油与天然气工程
2,786 篇 理学
- 1,610 篇 数学
- 1,137 篇 物理学
- 414 篇 统计学（可授理学、...
- 295 篇 生物学
- 160 篇 系统科学
- 135 篇 化学
1,777 篇 医学
- 1,671 篇 临床医学
- 206 篇 基础医学(可授医学...
- 122 篇 药学(可授医学、理...
- 108 篇 特种医学
882 篇 管理学
- 611 篇 管理科学与工程(可...
- 325 篇 图书情报与档案管...
- 106 篇 工商管理
80 篇 法学
78 篇 农学
59 篇 经济学
38 篇 文学
28 篇 军事学
27 篇 教育学
19 篇 艺术学

主题

3,291 篇 data compression
1,747 篇 image coding
1,244 篇 image compressio...
1,138 篇 video compressio...
900 篇 point cloud comp...
647 篇 three-dimensiona...
571 篇 encoding
536 篇 compression
508 篇 transform coding
501 篇 decoding
450 篇 data mining
415 篇 compression algo...
369 篇 bandwidth
341 篇 video coding
268 篇 training
256 篇 streaming media
247 篇 computer science
245 篇 deep learning
238 篇 data models
232 篇 discrete cosine ...

机构

25 篇 tsinghua univers...
25 篇 univ chinese aca...
23 篇 ieee
23 篇 department of el...
22 篇 univ calif river...
22 篇 department of el...
22 篇 peng cheng lab p...
19 篇 peking univ peop...
19 篇 peking univ inst...
18 篇 university of ch...
17 篇 argonne natl lab...
16 篇 shanghai jiao to...
16 篇 univ sci & techn...
16 篇 harbin institute...
16 篇 signal and data ...
16 篇 hewlett packard ...
15 篇 department of au...
14 篇 penn state univ ...
14 篇 nanyang technolo...
14 篇 peng cheng labor...

作者

50 篇 w. kinsner
22 篇 liang xin
22 篇 tao dingwen
21 篇 xiong hongkai
18 篇 lukin vladimir
18 篇 pratas diogo
17 篇 wang shiqi
16 篇 klasky scott
15 篇 li li
13 篇 ma zhan
12 篇 wang ronggang
12 篇 jin sian
12 篇 moffat a
12 篇 zhou wang
12 篇 pinho armando j.
11 篇 wang jing
11 篇 ye yan
11 篇 liu zhi
11 篇 wang wei
11 篇 shapira dana

语言

16,327 篇 英文
298 篇 其他
116 篇 中文
28 篇 土耳其文
3 篇 俄文
1 篇 西班牙文
1 篇 葡萄牙文

检索条件"任意字段=IEEE Data Compression Conference"

共 16774 条记录，以下是671-680 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：

Big OLAP data Cube compression Algorithms in Column-Oriented Cloud/Edge data Infrastructures 9

Big OLAP Data Cube Compression Algorithms in Column-Oriented...

引用

9th ieee International conference on Multimedia Big data, BigMM 2023

作者： Cuzzocrea, Alfredo University of Calabria The Big Data Engineering and Analytics Laboratory Rende Italy University of Paris City Dept. of Computer Science Paris France

This paper provides a brief overview on the innovative problem of devising and implementing big OLAP data cube compression algorithms in column-oriented Cloud/Edge data infrastructures, an emerging need for next-gener... 详细信息

ISBN: (纸本)9798350360004

关键词： data Analytics

来源：评论

学校读者我要写书评

暂无评论

Compressing Multisets with Large Alphabets

Compressing Multisets with Large Alphabets

引用

data compression conference (DCC)

作者： Severo, Daniel Townsend, James Khisti, Ashish Makhzani, Alireza Ullrich, Karen Meta AI New York NY USA Univ Toronto Toronto ON Canada Vector Inst AI Toronto ON Canada UCL London England

ISBN: (纸本)9781665478939

Current methods which compress multisets at an optimal rate have computational complexity that scales linearly with alphabet size, making them too slow to be practical in many real-world settings. We show how to convert a compression algorithm for sequences into one for multisets, in exchange for an additional complexity term that is quasi-linear in sequence length. This allows us to compress multisets of independent and identically distributed symbols at an optimal rate, with computational complexity decoupled from the alphabet size. The key insight is to avoid encoding the multiset directly, and instead compress a proxy sequence, using a technique called `bits-back coding'. We demonstrate the method experimentally on two tasks which are intractible with previous optimal-rate methods: compression of multisets of images and JavaScript Object Notation (JSON) files. Code for our experiments is available at https://***/facebookresearch/multiset-compression.

关键词： Image coding Codes Symbols data compression Encoding Computational complexity Task analysis

来源：评论

学校读者我要写书评

暂无评论

Quantum Circuit Complexity of Genomic data Encoding 5

Quantum Circuit Complexity of Genomic Data Encoding

引用

2024 International conference on Quantum Computing and Engineering

作者： Ye, Orson Strelchuk, Sergii Univ Cambridge Dept Appl Math & Theoret Phys Wilberforce Rd Cambridge CB3 0WA England

ISBN: (纸本)9798331541378

data encoding is a key step in almost all applications of quantum computation, but one that is not very well understood in general. Extensively researched in quantum machine learning, it is pivotal to exploiting the speedups offered by quantum algorithms. Failure to efficiently represent data risks weakening or nullifying prospective quantum advantages. While naive methods, such as basis encoding, will almost always work, they are extremely inefficient in terms of qubit use, rendering them infeasible for near-term applications. We focus on data encoding for genomics, a deeply data-driven field with computationally intensive algorithms throughout, from the initial DNA sequencing to pangenome assembly and more. We first examine the compressibility of genomic data from an information-theoretic perspective and how compression affects the quantum state preparation complexity. Here, there are two opposing forces at work: compression reduces data size but at the cost of the beneficial structure within the data. We review some standard approaches to data encoding in the context of genomics data from considering both the preparation complexity in terms of gate counts, qubit use, and depth, as well as the usefulness of the resulting states. We also present some new data encoding methods designed specifically for genomics that have a low-depth preparation circuits while still maintaining the essential features the algorithms require.

关键词： Quantum Applications Quantum Circuit Complexity data Encoding Genomics State Preparation Quantum Information

来源：评论

学校读者我要写书评

暂无评论

On The Energy Statistics of Feature Maps in Pruning of Neural Networks with Skip-Connections

On The Energy Statistics of Feature Maps in Pruning of Neura...

引用

data compression conference (DCC)

作者： Soltani, Mohammadreza Wu, Suya Li, Yuerong Ding, Jie Tarokh, Vahid Duke Univ Dept Elect & Comp Engn Durham NC USA Univ Minnesota Sch Stat Minneapolis MN USA

ISBN: (纸本)9781665478939

We propose a new structured pruning framework for compressing Deep Neural Networks (DNNs) with skip-connections, based on measuring the statistical dependency of hidden layers and predicted outputs. The dependence measure defined by the energy statistics of hidden layers serves as a model-free measure of information between the feature maps and the output of the network. The estimated dependence measure is subsequently used to prune a collection of redundant and uninformative layers. Extensive numerical experiments on various architectures show the efficacy of the proposed pruning approach with competitive performance to state-of-the-art methods.

关键词： Deep learning Neural networks Energy measurement data compression Numerical models

来源：评论

学校读者我要写书评

暂无评论

The Art of Losing to Win: Using Lossy Image compression to Improve data Loading in Deep Learning Pipelines 39

The Art of Losing to Win: Using Lossy Image Compression to I...

引用

39th ieee International conference on data Engineering, ICDE 2023

作者： Behme, Lennart Thirumuruganathan, Saravanan Mahdiraji, Alireza Rezaei Quiane-Ruiz, Jorge-Arnulfo Markl, Volker Technische Universität Berlin Germany Qatar Computing Research Institute Qatar Glooko GmbH Dfki GmbH Germany

ISBN: (纸本)9798350322279

Training deep learning (DL) models often takes a significant amount of time and is thus typically performed on expensive GPUs to speed up the process. However, data loading has recently been identified as one of the main performance bottlenecks in DL, resulting in GPU under-utilization. Looking forward, the combination of larger datasets and faster GPUs will exacerbate the problem. The data management community has started to address this by proposing data loading optimization techniques, including lossy image compression. While lossy compression is a conceptually promising approach for mitigating data loading bottlenecks in DL, there is only limited understanding of its efficacy in terms of impact on model throughput and accuracy. In this paper, we present an extensive experimental analysis of lossy image compression as a means to improve the performance of neural network training. We find that lossy compression can improve both throughput and accuracy of DL pipelines if resources such as time or storage capacity are limited. Furthermore, the choice of compression quality and codec are important hyperparameters when training deep neural networks. © 2023 ieee.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

A Design of An Autoencoder-Based Audio compression and Decompression System 30

A Design of An Autoencoder-Based Audio Compression and Decom...

引用

30th ieee International conference on Electronics, Circuits and Systems, ICECS 2023

作者： Tawfik, Abdelrahman Hosny, Shehab Hisham, Sara Farouk, Ali Amr Mustafa, Doha Moaty, Samaa Abdel Gamal, Ahmed Salah, Khaled Ain Shams University Faculty of Engineering Department of Electronics and Communications Cairo Egypt Siemens Digital Industries Software Fremont United States

ISBN: (纸本)9798350326499

Multimedia compression is a fundamental and significant research topic in the industrial field in the past several decades attempting to improve compression techniques. It is always a trade-off between size and quality where the growth rate of image, audio and video data is far beyond the improvement of the compression ratios achieved so far. Here, we are aiming to explore the potential of neural networks to achieve audio compression, making use of multilayer neural networks providing a more generic and efficient solution. In this paper, we present a lossy compression architecture, which utilizes the advantages of convolutional autoencoder (CAE) to replace the conventional transforms. Experimental results demonstrate that our method outperforms traditional coding algorithms, by achieving better compression ratios over both the related work. We refer to and traditional methods. The compression ratio for audio is 20x faster than related work. Moreover, the distortion is negligible. © 2023 ieee.

关键词： Multilayer neural networks

来源：评论

学校读者我要写书评

暂无评论

Semantic Communications and Lossy compression with Side Information 15

Semantic Communications and Lossy Compression with Side Info...

引用

15th International conference on Information and Communication Technology Convergence, ICTC 2024

作者： Kim, Keunyoung Lee, Woo Yong Ko, Young-Jo Electronics and Telecommunications Research Institute Mobile Communication Research Division Daejeon Korea Republic of

ISBN: (纸本)9798350364637

Semantic communications aim to convey precise meanings efficiently rather than transmitting bits accurately. Inspired by lossy compression with side information, we propose a communication scheme that transmits only task-essential data while achieving desired outcomes. Our approach employs machine learning to construct contextual information and compress data into a finite set of latent vectors. © 2024 ieee.

关键词： Latent semantic analysis

来源：评论

学校读者我要写书评

暂无评论

Boosting neural video codecs by exploiting hierarchical redundancy 23

Boosting neural video codecs by exploiting hierarchical redu...

引用

23rd ieee/CVF Winter conference on Applications of Computer Vision (WACV)

作者： Pourreza, Reza Le, Hoang Said, Amir Sautiere, Guillaume Wiggers, Auke Qualcomm AI Res San Diego CA 92121 USA

ISBN: (纸本)9781665493468

In video compression, coding efficiency is improved by reusing pixels from previously decoded frames via motion and residual compensation. We define two levels of hierarchical redundancy in video frames: 1) first-order: redundancy in pixel space, i.e., similarities in pixel values across neighboring frames, which is effectively captured using motion and residual compensation, 2) second-order: redundancy in motion and residual maps due to smooth motion in natural videos. While most of the existing neural video coding literature addresses first-order redundancy, we tackle the problem of capturing second-order redundancy in neural video codecs via predictors. We introduce generic motion and residual predictors that learn to extrapolate from previously decoded data. These predictors are lightweight, and can be employed with most neural video codecs in order to improve their rate-distortion performance. Moreover, while RGB is the dominant colorspace in neural video coding literature, we introduce general modifications for neural video codecs to embrace the YUV420 colorspace and report YUV420 results. Our experiments show that using our predictors with a well-known neural video codec leads to 38% and 34% bitrate savings in RGB and YUV420 colorspaces measured on the UVG dataset.

关键词： Video coding Visualization Bit rate Termination of employment Rate-distortion Training data Video compression

来源：评论

学校读者我要写书评

暂无评论

DOA Estimation Algorithm for Array Error Self-calibration Based on Channel compression 12

DOA Estimation Algorithm for Array Error Self-calibration Ba...

引用

12th ieee Asia-Pacific conference on Antennas and Propagation, APCAP 2024

作者： Chen, Tao Hu, Xuejing Liu, Ziming Luo, Yihao Harbin Engineering University College of Information and Communication Engineering Harbin China

ISBN: (纸本)9798350351019

To enhance the efficiency and accuracy of direction of arrival (DOA) estimation, a novel self-calibrating algorithm is introduced, which incorporates channel compression to address array amplitude-phase errors. By initially compressing the received signal within the channels, the algorithm reduces complexity and computation time. Utilizing atomic norm minimization (ANM), the proposed method leverages signal sparsity to build a model that accommodates amplitude-phase errors, introducing a constraint term for the amplitude error trace. This innovation broadens the applicability of ANM to error-prone data. Simulation outcomes confirm the algorithm's superior estimation precision. © 2024 ieee.

关键词： Channel estimation

来源：评论

学校读者我要写书评

暂无评论

compression Method for Convolution Kernel with KCP-FGTD 12

Compression Method for Convolution Kernel with KCP-FGTD

引用

12th ieee International conference on Information and Communication Networks, ICICN 2024

作者： Lv, Rui Zheng, Jiangbin Tao, Siyu Zhang, Chenyu Hu, Chao School of Computer Science Northwestern Polytechnical University Shaanxi Xi'an China School of Information Science& Technology Northwest University Shaanxi Xi'an China School of Artificial Intelligence Xidian University Shaanxi Xi'an China

ISBN: (纸本)9798350355802

Convolutional neural networks (CNNs) possess strong expressive capabilities, but with the increasing size and cost of modern CNNs, deploying large-scale CNNs in resource-limited environments remains a challenge, making neural network compression a hot topic in contemporary research. Among various compression methods, tensor decomposition shows numerous unique advantages, such as regular data structure, solid mathematical foundation, convenience in training from scratch, and ideal compression rates. However, most existing tensor decompositions do not perform well in compressing CNNs, struggling to balance time and space complexity, and failing to accelerate CNNs in reality. To address these issues. In this paper, we propose a fine-grained KCP tensor decomposition for CNN convolution kernel compression with considerable compression rate and acceleration capability. First, convolution kernels are compressed using 2nd-order KCP decomposition. The decomposed factor tensors are then converted into a four-layer lightweight convolution kernel structure. This structure conducts continuous contraction computations with the input, transforming the convolution computations into a highly efficient lightweight layered matrix multiplication structure. Secondly, we conduct a comprehensive comparison with other methods and analyze the superiority of our method. Comparisons of computational complexity with other typical tensor compression methods, along with simulation experiments on CIFAR-10 and ImageNet datasets, demonstrate that our method can achieve more efficient comprehensive results. These include acceptable accuracy, significantly reduced model size, and real-world acceleration of network inference times. Finally, we further analyze how different combinations of KT rank and CP rank impact the compression effectiveness and expressive capacity of CNNs. © 2024 ieee.

关键词： Tensors

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 << < 64 65 66 67 68 69 70 71 72 73 > >>

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：