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

16,560 篇 会议
211 篇 期刊文献

馆藏范围

16,771 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

10,860 篇 工学
- 7,724 篇 计算机科学与技术...
- 4,144 篇 电气工程
- 3,544 篇 软件工程
- 3,191 篇 信息与通信工程
- 1,023 篇 控制科学与工程
- 816 篇 电子科学与技术（可...
- 614 篇 生物医学工程（可授...
- 478 篇 机械工程
- 474 篇 仪器科学与技术
- 457 篇 光学工程
- 303 篇 动力工程及工程热...
- 254 篇 生物工程
- 185 篇 交通运输工程
- 167 篇 航空宇航科学与技...
- 158 篇 网络空间安全
- 123 篇 材料科学与工程（可...
- 115 篇 石油与天然气工程
2,784 篇 理学
- 1,610 篇 数学
- 1,138 篇 物理学
- 413 篇 统计学（可授理学、...
- 295 篇 生物学
- 160 篇 系统科学
- 132 篇 化学
1,776 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
877 篇 管理学
- 608 篇 管理科学与工程(可...
- 323 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

3,289 篇 data compression
1,747 篇 image coding
1,242 篇 image compressio...
1,138 篇 video compressio...
900 篇 point cloud comp...
647 篇 three-dimensiona...
571 篇 encoding
534 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

16,325 篇 英文
297 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 16771 条记录，以下是951-960 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：

Causal-DFQ: Causality Guided data-free Network Quantization

Causal-DFQ: Causality Guided Data-free Network Quantization

引用

ieee/CVF International conference on Computer Vision (ICCV)

作者： Shang, Yuzhang Xu, Bingxin Liu, Gaowen Kompella, Ramana Rao Yan, Yan Illinois Inst Technol Chicago IL USA Cisco Res Austin TX USA

ISBN: (纸本)9798350307184

Model quantization, which aims to compress deep neural networks and accelerate inference speed, has greatly facilitated the development of cumbersome models on mobile and edge devices. There is a common assumption in quantization methods from prior works that training data is available. In practice, however, this assumption cannot always be fulfilled due to reasons of privacy and security, rendering these methods inapplicable in real-life situations. Thus, data-free network quantization has recently received significant attention in neural network compression. Causal reasoning provides an intuitive way to model causal relationships to eliminate data-driven correlations, making causality an essential component of analyzing datafree problems. However, causal formulations of data-free quantization are inadequate in the literature. To bridge this gap, we construct a causal graph to model the data generation and discrepancy reduction between the pre-trained and quantized models. Inspired by the causal understanding, we propose the Causality-guided data-free Network Quantization method, Causal- DFQ, to eliminate the reliance on data via approaching an equilibrium of causality-driven intervened distributions. Specifically, we design a contentstyle-decoupled generator, synthesizing images conditioned on the relevant and irrelevant factors;then we propose a discrepancy reduction loss to align the intervened distributions of the pre-trained and quantized models. It is worth noting that our work is the first attempt towards introducing causality to data-free quantization problem. Extensive experiments demonstrate the efficacy of Causal-DFQ. The code is available at Causal-DFQ.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AdaViT: Task Adaptive ViT compression Based on Module Replacement 10

AdaViT: Task Adaptive ViT Compression Based on Module Replac...

引用

10th International conference on Big data Computing and Communications, BIGCOM 2024

作者： Zhang, Weijian Guo, Xing Du, Haohua Anhui University School of Computer Science and Technology HeFei China Anhui University School of Computer Science and Technology USTC-DEQING Alpha Innovation Institute HeFei China Beihang University School of Cyber Science and Technology USTC-DEQING Alpha Innovation Institute Beijing China

ISBN: (纸本)9798331509538

Large pre-trained visual models, such as Vision Transformer (ViT), have shown excellent results in a variety of visual processing tasks. However, the large parameter sizes of these models make them difficult to deploy in applications that require limited resources for fast real-time inference. Existing model compression methods compress pre-trained ViTs into models of the same structure, but the compressed models fail to maximise performance on different tasks and consume significant computational and storage resources to adapt to downstream tasks. Pre-trained ViT models learn rich knowledge from large datasets and require different knowledge for different tasks, so removing task-specific redundant knowledge from pre-trained models is the key to achieve model compression while maximising model performance on different tasks. Based on this idea, we propose a novel ViT compression method, AdaViT. Firstly, a lightweight module is introduced, which adds less than 2% of extra parameters to realise the adaptive tuning of the model to different tasks to show the best prediction, and its effectiveness is proved by experiments. Second, inspired by the idea of knowledge distillation, we propose a new module replacement compression method, which effectively compresses the ViT by gradually replacing the Transformer module in the original ViT, and achieves task-oriented adaptive ViT compression through the combination of adaptive modules and model replacement methods. We evaluate AdaViT on several visual classification tasks and compare it with other ViT compression methods, demonstrating the effectiveness of task-adaptive ViT compression. © 2024 ieee.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

Centralized Control of a Multi-Agent System Via Distributed and Bit-Budgeted Communications

Centralized Control of a Multi-Agent System Via Distributed ...

引用

ieee Wireless Communications and Networking conference (WCNC)

作者： Mostaani, Arsham Vu, Thang X. Chatzinotas, Symeon Ottersten, Bjorn Univ Luxembourg Ctr Secur Reliabil & Trust Luxembourg Luxembourg

ISBN: (纸本)9781665491228

We consider a distributed quantization problem that arises when multiple edge devices, i.e., agents, are controlled via a centralized controller (CC). While agents have to communicate their observations to the CC for decision-making, the bit-budgeted communications of agent-CC links may limit the task-effectiveness of the system which is measured by the system's average sum of stage costs/rewards. As a result, each agent, given its local processing resources, should compress/quantize its observation such that the average sum of stage costs/rewards of the control task is minimally impacted. We address the problem of maximizing the average sum of stage rewards by proposing two different Action-Based State Aggregation (ABSA) algorithms that carry out the indirect and joint design of control and communication policies in the multi-agent system (MAS). While the applicability of ABSA-1 is limited to single-agent systems, it provides an analytical framework that acts as a stepping stone to the design of ABSA-2. ABSA-2 carries out the joint design of control and communication for an MAS. We evaluate the algorithms - with average return as the performance metric using numerical experiments performed to solve a multi-agent geometric consensus problem.

关键词： Task-oriented data compression distributed edge processing communications for machine learning multiagent systems semantic communications data-quantization

来源：评论

学校读者我要写书评

暂无评论

An Efficient and Privacy-Preserving Medical Image compression and Sharing Protocol 15

An Efficient and Privacy-Preserving Medical Image Compressio...

引用

15th International conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Singh, Surendra Tripathi, Shubham Jain, Tanya Rana, Saurabh Choudhary, Neelam Bennett University School of Computer Science Engineering & Technology Gautam Buddha Nagar India

ISBN: (纸本)9798350370249

The effective transmission and sampling of clinical images are important research areas in computer science, particularly in the healthcare industry. Methods such as personal area networking and body area networking are valuable for medical monitoring systems used in remote surgical guidance and early emergency detection. However, due to the sensitive nature of medical images, strong privacy protection and secure data aggregation/compression techniques are needed. In this study, we use compressive sensing theory to address these challenges with a novel approach. Our technique reduces the size of medical photos by 10 %, while maintaining strong secrecy through the use of additive homomorphic encryption. © 2024 ieee.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

IFHE: Intermediate-Feature Heterogeneity Enhancement for Image Synthesis in data-Free Knowledge Distillation 60

IFHE: Intermediate-Feature Heterogeneity Enhancement for Ima...

引用

60th ACM/ieee Design Automation conference (DAC)

作者： Chen, Yi Liu, Ning Ren, Ao Yang, Tao Liu, Duo Chongqing Univ Sch Comp Sci Chongqing Peoples R China Midea Grp Beijing Peoples R China

ISBN: (纸本)9798350323481

data-free knowledge distillation (DFKD) explores training a compact student network only by a pre-trained teacher without real data. Prevailing DFKD methods mainly consist of image synthesis and knowledge distillation. The synthesized images are crucial to enhance the student network performance. However, the images synthesized by existing methods cause high homogeneity on intermediate features, incurring undesired distillation performance. To address this problem, we propose the Intermediate-Feature Heterogeneity Enhancement (IFHE) method, which effectively enhances the heterogeneity of synthesized images by minimizing the loss between intermediate features and pre-set labels of the synthesized images Our IFHE outperforms the SOTA results on CIFAR-10/100 datasets of representative networks.

关键词： Knowledge distillation model compression

来源：评论

学校读者我要写书评

暂无评论

Fast and Accurate: Video Enhancement Using Sparse Depth 23

Fast and Accurate: Video Enhancement Using Sparse Depth

引用

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

作者： Feng, Yu Hansen, Patrick Whatmough, Paul N. Lu, Guoyu Zhu, Yuhao Univ Rochester Rochester NY 14627 USA Tenstorrent Inc Austin TX USA Arm Res Austin TX USA Univ Georgia Athens GA USA

ISBN: (纸本)9781665493468

This paper presents a general framework to build fast and accurate algorithms for video enhancement tasks such as super-resolution, deblurring, and denoising. Essential to our framework is the realization that the accuracy, rather than the density, of pixel flows is what is required for high-quality video enhancement. Most of prior works take the opposite approach: they estimate dense (per-pixel)-but generally less robust-flows, mostly using computationally costly algorithms. Instead, we propose a lightweight flow estimation algorithm;it fuses the sparse point cloud data and (even sparser and less reliable) IMU data available in modern autonomous agents to estimate the flow information. Building on top of the flow estimation, we demonstrate a general framework that integrates the flows in a plug-and-play fashion with different task-specific layers. Algorithms built in our framework achieve 1.78x - 187.41x speedup while providing a 0.42 dB - 6.70 dB quality improvement over competing methods.

关键词： Point cloud compression Computer vision Laser radar Fuses Superresolution Noise reduction Buildings

来源：评论

学校读者我要写书评

暂无评论

Efficient Privacy-Preserving Federated Learning with Byzantine Robustness

Efficient Privacy-Preserving Federated Learning with Byzanti...

引用

2024 ieee International conference on Cognitive Computing and Complex data

作者： Jin, Chunhua Li, Lulu Wang, Jiahao Sun, Youwang Jin, Ying Chen, Guanhua Huaiyin Inst Technol Fac Comp & Software Engn Huaian Peoples R China

ISBN: (纸本)9798350352900;9798350352894

Federated learning is a distributed machine learning paradigm. It entails training a global model across diverse organizations while ensuring privacy constraints are upheld. Despite its promising potential, challenges arise when adversaries attempt to infer private information from exchanged parameters or compromise the global model. Although the development of multiple protocols to mitigate security threats, safeguarding the privacy of individual participants while countering Byzantine adversaries remains a challenge. Furthermore, the frequent transmission of gradients between the master server and participants results in significant c ommunication overhead, thereby limiting the training efficiency o f f ederated l earning. In this study, We propose an efficient p rivacy-preserving federated learning scheme with Byzantine robustness (EFL-PB). For privacy protection and Byzantine robustness, we propose a novel aggregation strategy based on the multi-message shuffle protocol in differential privacy. For enhancing communication efficiency, we develop an adaptive gradient compression scheme. Theoretical analysis demonstrates that our multi-message shuffle protocol can satisfy differential privacy. Experimental results on the MNIST, FashionMNIST, and CIFAR-10 datasets validate the robustness and efficiency o f t he E FL-PB s cheme. A s w ell, t he EFL-PB scheme exhibits strong performance on non-iid datasets.

关键词： fedetated learning differential privacy byzantine robustness adaptive gradient compression

来源：评论

学校读者我要写书评

暂无评论

Lung Image Segmentation and compression Using Deep Learning

Lung Image Segmentation and Compression Using Deep Learning

引用

2024 International conference on Advances in Computing Research on Science Engineering and Technology, ACROSET 2024

作者： Tiwari, Puneet Phulre, Sunil Lnct University Bhopal Department of Computer Science & Engineering India

ISBN: (纸本)9798350388800

Lung image compression and segmentation are essential diagnostic and monitoring techniques for a variety of respiratory ailments. We present a novel deep learning-based technique for segmenting and compressing lung images in this paper. To ascertain lung sections precisely in medical images, it is imperative to initially train a convolutional neural network (CNN) model. By understanding intricate patterns and features present in lung images, the CNN model is designed to identify and extract certain lung regions. This segmentation process saves medical staff a great deal of time and reduces the possibility of human error by eliminating the need for manual annotation. Following segmentation, lung image storage requirements are reduced without compromising diagnostic quality by employing a deep learning-based compression technique. The compression model's goal is to remove irrelevant and uninformative content while extracting the most important information. By employing deep learning, our compression technique achieves notable compression ratios while preserving essential information for accurate diagnosis. We conducted extensive trials with many lung imaging datasets to evaluate our proposed approach. When compared to traditional image processing methods, the results demonstrate increased segmentation accuracy and compression efficiency. We assessed the effectiveness of our method using several metrics, such as the compression ratio, mean squared error and coefficient of rolls. The proposed architecture for lung image segmentation and compression has great promise for enhancing respiratory illness identification and treatment. When segmentation is automated and lung picture compression is done rapidly, medical data may be sent, stored, and analyzed more efficiently, leading to better healthcare outcomes. © 2024 ieee.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Unsupervised 4D LiDAR Moving Object Segmentation in Stationary Settings with Multivariate Occupancy Time Series 23

Unsupervised 4D LiDAR Moving Object Segmentation in Stationa...

引用

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

作者： Kreutz, Thomas Muehlhaeuser, Max Guinea, Alejandro Sanchez Tech Univ Darmstadt Telekooperat Lab Darmstadt Germany

ISBN: (纸本)9781665493468

In this work, we address the problem of unsupervised moving object segmentation (MOS) in 4D LiDAR data recorded from a stationary sensor, where no ground truth annotations are involved. Deep learning-based state-of-the-art methods for LiDAR MOS strongly depend on annotated ground truth data, which is expensive to obtain and scarce in existence. To close this gap in the stationary setting, we propose a novel 4D LiDAR representation based on multivariate time series that relaxes the problem of unsupervised MOS to a time series clustering problem. More specifically, we propose modeling the change in occupancy of a voxel by a multivariate occupancy time series (MOTS), which captures spatio-temporal occupancy changes on the voxel level and its surrounding neighborhood. To perform unsupervised MOS, we train a neural network in a self-supervised manner to encode MOTS into voxel-level feature representations, which can be partitioned by a clustering algorithm into moving or stationary. Experiments on stationary scenes from the Raw KITTI dataset show that our fully unsupervised approach achieves performance that is comparable to that of supervised state-of-the-art approaches.

关键词： Point cloud compression Computer vision Laser radar Annotations Time series analysis Neural networks Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

CSTs for Terabyte-Sized data

CSTs for Terabyte-Sized Data

引用

data compression conference (DCC)

作者： Oliva, Marco Cenzato, Davide Rossi, Massimiliano Liptak, Zsuzsanna Gagie, Travis Boucher, Christina Univ Florida Dept Comp & Info Sci & Engn Gainesville FL 32611 USA Univ Verona Dept Comp Sci Verona Italy Dalhousie Univ Fac Comp Sci Halifax NS Canada

ISBN: (纸本)9781665478939

Generating pangenomic datasets is becoming increasingly common but there are still few tools able to handle them and even fewer accessible to non-specialists. Building compressed suffix trees (CSTs) for pangenomic datasets is still a major challenge but could be enormously beneficial to the community. In this paper, we present a method, which we refer to as RePFP-CST, for building CSTs in a manner that is scalable. To accomplish this, we show how to build a CST directly from VCF files without decompressing them, and to prune from the prefix-free parse (PFP) phrase boundaries whose removal reduces the total size of the dictionary and the parse. We show that these improvements reduce the time and space required for the construction of the CST, and the memory footprint of the finished CST, enabling us to build a CST for a terabyte of DNA for the first time in the literature.

关键词： Dictionaries Buildings Memory management data compression DNA

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 << < 92 93 94 95 96 97 98 99 100 101 > >>

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：