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

16,594 篇 会议
212 篇 期刊文献

馆藏范围

16,806 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

10,897 篇 工学
- 7,754 篇 计算机科学与技术...
- 4,161 篇 电气工程
- 3,558 篇 软件工程
- 3,214 篇 信息与通信工程
- 1,047 篇 控制科学与工程
- 823 篇 电子科学与技术（可...
- 615 篇 生物医学工程（可授...
- 482 篇 机械工程
- 480 篇 仪器科学与技术
- 459 篇 光学工程
- 309 篇 动力工程及工程热...
- 255 篇 生物工程
- 192 篇 交通运输工程
- 174 篇 网络空间安全
- 167 篇 航空宇航科学与技...
- 124 篇 材料科学与工程（可...
- 124 篇 石油与天然气工程
2,795 篇 理学
- 1,614 篇 数学
- 1,141 篇 物理学
- 414 篇 统计学（可授理学、...
- 295 篇 生物学
- 160 篇 系统科学
- 139 篇 化学
1,783 篇 医学
- 1,672 篇 临床医学
- 206 篇 基础医学(可授医学...
- 122 篇 药学(可授医学、理...
- 109 篇 特种医学
893 篇 管理学
- 622 篇 管理科学与工程(可...
- 325 篇 图书情报与档案管...
- 107 篇 工商管理
82 篇 法学
78 篇 农学
59 篇 经济学
40 篇 文学
28 篇 军事学
27 篇 教育学
19 篇 艺术学

主题

3,292 篇 data compression
1,747 篇 image coding
1,250 篇 image compressio...
1,138 篇 video compressio...
903 篇 point cloud comp...
650 篇 three-dimensiona...
570 篇 encoding
532 篇 compression
508 篇 transform coding
503 篇 decoding
449 篇 data mining
415 篇 compression algo...
368 篇 bandwidth
341 篇 video coding
268 篇 training
256 篇 streaming media
248 篇 computer science
246 篇 deep learning
239 篇 data models
234 篇 discrete cosine ...

机构

25 篇 univ chinese aca...
24 篇 tsinghua univers...
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 ...
15 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
11 篇 wang jing
11 篇 ye yan
11 篇 liu zhi
11 篇 wang wei
11 篇 shapira dana
11 篇 pinho armando j.

语言

15,857 篇 英文
802 篇 其他
116 篇 中文
27 篇 土耳其文
3 篇 俄文
1 篇 西班牙文

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

共 16806 条记录，以下是1231-1240 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：

Fuzzy Knowledge Distillation Model for Incomplete Multi-modality data and Its Application to Brain Network Analysis

Fuzzy Knowledge Distillation Model for Incomplete Multi-moda...

引用

2024 ieee International conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Qi, Xiaoyu Huang, Jiashuang Cheng, Xueyun Wang, Mingliang Ding, Weiping Nantong University School of Information Science and Technology Nantong China Nanjing University of Information Science and Technology School of Computer and Software Nanjing China

ISBN: (纸本)9798350386226

Knowledge distillation (KD) techniques have been employed to tackle the issue of incomplete multi-modality data, aiming to enhance the performance of the student model (i.e., using unimodal data) as close as possible to the teacher model (i.e., using multimodal data) through information transfer between the two models. However, directly using the traditional KD model will lead to the problem of mismatched model capacities. The teacher model typically receives a greater amount of information compared to the student model. If the learned information from the teacher model is directly transferred, it will impact the performance of the student model. To this end, this paper proposes a novel fuzzy knowledge distillation (fuzzy-KD) model for brain network analysis of incomplete multi-modality data. Specifically, we design a fuzzy-KD module to reduce the information gap between the teacher and student models through two operations: fuzzy processing and feature selection. The fuzzy processing applies an affiliation function to each channel of the feature maps learned by the teacher model to improve the generalization of representations. The feature selection employs channel compression to compel the student model to focus on crucial information within the teacher model. Experiments on real epilepsy datasets show that our method outperforms several state-of-the-art methods in the field of epilepsy recognition. © 2024 ieee.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Cross-Modality Feature Fusion Network for Few-Shot 3D Point Cloud Classification 23

Cross-Modality Feature Fusion Network for Few-Shot 3D Point ...

引用

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

作者： Yang, Minmin Chen, Jiajing Velipasalar, Senem Syracuse Univ Elect Engn & Comp Sci Dept Syracuse NY 13244 USA

ISBN: (纸本)9781665493468

Recent years have witnessed significant progress in the field of few-shot image classification while few-shot 3D point cloud classification still remains under-explored. Real-world 3D point cloud data often suffers from occlusions, noise and deformation, which make the few-shot 3D point cloud classification even more challenging. In this paper, we propose a cross-modality feature fusion network, for few-shot 3D point cloud classification, which aims to recognize an object given only a few labeled samples, and provides better performance even with point cloud data with missing points. More specifically, we train two models in parallel. One is a projection-based model with ResNet-18 as the backbone and the other one is a point-based model with a DGCNN backbone. Moreover, we design a Support-Query Mutual Attention (sqMA) module to fully exploit the correlation between support and query features. Extensive experiments on three datasets, namely ModelNet40, ModelNet40-C and ScanObjectNN, show the effectiveness of our method, and its robustness to missing points. Our proposed method outperforms different state-of-the-art baselines on all datasets. The margin of improvement is even larger on the ScanObjectNN dataset, which is collected from real-world scenes and is more challenging with objects having missing points.

关键词： Point cloud compression Representation learning Computer vision Three-dimensional displays Correlation Fuses Robustness

来源：评论

学校读者我要写书评

暂无评论

Attention-Based Generative Neural Image compression on Solar Dynamics Observatory 21

Attention-Based Generative Neural Image Compression on Solar...

引用

21st ieee International conference on Machine Learning and Applications (ieee ICMLA)

作者： Zafari, Ali Khoshkhahtinat, Atefeh Mehta, Piyush M. Nasrabadi, Nasser M. Thompson, Barbara J. da Silva, Daniel Kirk, Michael S. F. West Virginia Univ Dept Comp Sci & Elect Engn Morgantown WV 26506 USA West Virginia Univ Dept Mech & Aerosp Engn Morgantown WV 26506 USA NASA Goddard Space Flight Ctr Greenbelt MD USA

ISBN: (纸本)9781665462839

NASA's Solar Dynamics Observatory (SDO) mission gathers 1.4 terabytes of data each day from its geosynchronous orbit in space. SDO data includes images of the Sun captured at different wavelengths, with the primary scientific goal of understanding the dynamic processes governing the Sun. Recently, end-to-end optimized artificial neural networks (ANN) have shown great potential in performing image compression. ANN-based compression schemes have outperformed conventional hand-engineered algorithms for lossy and lossless image compression. We have designed an ad-hoc ANN-based image compression scheme to reduce the amount of data needed to be stored and retrieved on space missions studying solar dynamics. In this work, we propose an attention module to make use of both local and non-local attention mechanisms in an adversarially trained neural image compression network. We have also demonstrated the superior perceptual quality of this neural image compressor. Our proposed algorithm for compressing images downloaded from the SDO spacecraft performs better in rate-distortion trade-off than the popular currently-in-use image compression codecs such as JPEG and JPEG2000. In addition we have shown that the proposed method outperforms state-of-the art lossy transform coding compression codec, i.e., BPG.

关键词： Learned lossy image compression solar dynamics observatory generative adversarial network attention

来源：评论

学校读者我要写书评

暂无评论

Masked Autoencoder for Self-Supervised Pre-training on Lidar Point Clouds

Masked Autoencoder for Self-Supervised Pre-training on Lidar...

引用

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

作者： Hess, Georg Jaxing, Johan Svensson, Elias Hagerman, David Petersson, Christoffer Svensson, Lennart Chalmers Univ Technol Gothenburg Sweden Zenseact Gothenburg Sweden

ISBN: (纸本)9798350320565

Masked autoencoding has become a successful pretraining paradigm for Transformer models for text, images, and, recently, point clouds. Raw automotive datasets are suitable candidates for self-supervised pre-training as they generally are cheap to collect compared to annotations for tasks like 3D object detection (OD). However, the development of masked autoencoders for point clouds has focused solely on synthetic and indoor data. Consequently, existing methods have tailored their representations and models toward small and dense point clouds with homogeneous point densities. In this work, we study masked autoencoding for point clouds in an automotive setting, which are sparse and for which the point density can vary drastically among objects in the same scene. To this end, we propose VoxelMAE, a simple masked autoencoding pre-training scheme designed for voxel representations. We pre-train the backbone of a Transformer-based 3D object detector to reconstruct masked voxels and to distinguish between empty and non-empty voxels. Our method improves the 3D OD performance by 1.75 mAP points and 1.05 NDS on the challenging nuScenes dataset. Further, we show that by pre-training with Voxel-MAE, we require only 40% of the annotated data to outperform a randomly initialized equivalent. Code is available at https://***/georghess/ voxel-mae.

关键词： Point cloud compression Training Three-dimensional displays Laser radar Annotations Tracking Computational modeling

来源：评论

学校读者我要写书评

暂无评论

ECG compression Using Machine Learning Technique with Wavelet Transform 2

ECG Compression Using Machine Learning Technique with Wavele...

引用

2nd International conference on Ambient Intelligence in Health Care, ICAIHC 2023

作者： Baliarsingh, Sudeshna Panda, Prakash Kumar Mohanty, Mihir Narayan Dept.of ECE ITER Odisha Bhubaneswar51003 India

ISBN: (纸本)9798350344882

ECG (Electrocardiogram) is the graphical representation of heart activities. As the number of heart patients increases day by day and no definite solution is found except death data. The data storage demands a large space to acquire all the data of the patients. The storage can be optimal when the signal is compressed. Through different techniques that have been approached Machine Learning technology for ECG data compression is explored a little. The authors of this article have used the machine learning technique. as a Neural Network model to compress the ECG signal. However, the model is modified with weight modification. The initial weights are considered wavelet coefficients and are further modified through hidden layers. The use of wavelet transform helps us to suppress the noise and decompose it with relevant information. To train the model, a back propagation learning technique is used. The training accuracy is 99.2 and the PRD (Percent Root Mean Square Difference) and CR (compression Ratio) of SVDB (Supraventricular Arrhythmia database) are 98.2 and 1.24 and for MIT-BIH arrhythmia it is 97.72 with 1.19 which is shown in the result section. © 2023 ieee.

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

Compatible Sliding-Windows Algorithm for Vessel Trajectory compression 5

Compatible Sliding-Windows Algorithm for Vessel Trajectory C...

引用

5th International conference on Information Communication and Signal Processing, ICICSP 2022

作者： Hua, Li Xiaojun, Zhang Science & Technology on Underwater Acoustic Antagonizing Laboratory Zhanjiang China

ISBN: (纸本)9781665485890

With the development of marine economy and data positioning technology, A large amount of vessel trajectory data has been generated. data compression has become the key issue in the research of vessel trajectory big data. Since the compression rate of the existing vessel trajectory compression algorithms was not adjustable, we proposed a vessel trajectory compression algorithm with adjustable compression rate based on Sliding-Windows(SW) algorithm. The main idea was to adjust the compression rate by dynamically updating the vertical Euclidean distance threshold. The proposed algorithm could adapt to the dynamic change of channel capacity by dynamically adjusting the compression rate in online compression. The simulation results showed that compared with the traditional SW algorithm, the proposed algorithm not only realized the dynamic adjustment of compression rate, but also the compression error was less than that of the SW algorithm. Meanwhile the increase of computational complexity was almost negligible. This algorithm could also be used for online compression of other kinds of trajectory data. © 2022 ieee.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

TRELLIS-CODED QUANTIZATION FOR END-TO-END LEARNED IMAGE compression 29

TRELLIS-CODED QUANTIZATION FOR END-TO-END LEARNED IMAGE COMP...

引用

ieee International conference on Image Processing (ICIP)

作者： Suhring, Karsten Schafer, Michael Pfaff, Jonathan Schwarz, Heiko Marpe, Detlev Wiegand, Thomas Fraunhofer Inst Telecommun Heinrich Hertz Inst Berlin Germany Free Univ Berlin Inst Comp Sci Berlin Germany Tech Univ Berlin Dept Telecommun Syst Berlin Germany

ISBN: (数字)9781665496209

ISBN: (纸本)9781665496209

The performance of variational auto-encoders (VAE) for image compression has steadily grown in recent years, thus becoming competitive with advanced visual data compression technologies. These neural networks transform the source image into a latent space with a channel-wise representation. In most works, the latents are scalar quantized before being entropy coded. On the other hand, vector quantizers generally achieve denser packings of high-dimensional data regardless of the source distribution. Hence, low-complexity variants of these quantizers are implemented in the compression standards JPEG 2000 and Versatile Video Coding. In this paper we demonstrate coding gains by using trellis-coded quantization (TCQ) over scalar quantization. For the optimization of the networks with regard to TCQ, we employ a specific noisy representation of the features during the training stage. For variable-rate VAEs, we obtained 7.7% average BD-rate savings on the Kodak images by using TCQ over scalar quantization. When different networks per target bitrate are optimized, we report a relative coding gain of 2.4% due to TCQ.

关键词： Deep Learning Auto-Encoder Rate-Distortion-Optimization Trellis-Coded Quantization

来源：评论

学校读者我要写书评

暂无评论

A Dynamic compression Technique for Efficient Offloading of Computation Between Mobile Devices and Cloud

A Dynamic Compression Technique for Efficient Offloading of ...

引用

2023 International Technical conference on Circuits/Systems, Computers, and Communications, ITC-CSCC 2023

作者： Choi, Sunghern Lee, Hayun Shin, Dongkun Sungkyunkwan University Department of Electrical and Computer Engineering Suwon Korea Republic of

ISBN: (纸本)9798350326413

There has been a recent trend in developing applications that use deep learning models on mobile devices. However, using deep learning models that require a large amount of computation solely on mobile devices is limited by their hardware constraints. In order to solve this problem, there are studies that have performed partitional computations in which a part of the computation is processed on a mobile device and the remaining computation is processed in the cloud. These studies primarily focus on proposing the optimal partition points between mobile devices and clouds, as well as data compression techniques for transmitting data from mobile devices to the cloud. However, achieving optimal performance while maintaining latency and accuracy that meet the application's requirements remains challenging. In this paper, we propose a Dynamic compression Technique that can reduce latency according to network conditions and minimize accuracy loss due to compression. Mobile device transmits data to cloud server by dynamically finding the optimal compression rate based on the changing network bandwidth at runtime. In order to minimize the loss of accuracy when transmitting compressed data, a model considering various compression rates is trained. data is compressed using the Slicing + Top-k pruning method proposed in this paper. In the experiment, a NVDIA Geforce GTX 1080 Ti was used as a cloud server and a Jetson TX2 board was used as a mobile device. When compression is performed using the Slicing + Top-k method, the accuracy is higher than 2% at a compression rate of more than 10x compared to the method using Only Slicing. And we shows that the change in latency is minimized even when the network bandwidth changes. © 2023 ieee.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Edge Storage Management Recipe with Zero-Shot data compression for Road Anomaly Detection 14

Edge Storage Management Recipe with Zero-Shot Data Compressi...

引用

14th International conference on Information and Communication Technology Convergence, ICTC 2023

作者： Park, YeongHyeon Gim, Uju Kim, Myung Jin Sk Planet Co. Ltd. Seongnam Korea Republic of

ISBN: (纸本)9798350313277

Recent studies show edge computing-based road anomaly detection systems which may also conduct data collection simultaneously. However, the edge computers will have small data storage but we need to store the collected audio samples for a long time in order to update existing models or develop a novel method. Therefore, we should consider an approach for efficient storage management methods while preserving high-fidelity audio. A hardware-perspective approach, such as using a low-resolution microphone, is an intuitive way to reduce file size but is not recommended because it fundamentally cuts off high-frequency components. On the other hand, a computational file compression approach that encodes collected high-resolution audio into a compact code should be recommended because it also provides a corresponding decoding method. Motivated by this, we propose a way of simple yet effective pre-trained autoencoder-based data compression method. The pre-trained autoencoder is trained for the purpose of audio super-resolution so it can be utilized to encode or decode any arbitrary sampling rate. Moreover, it will reduce the communication cost for data transmission from the edge to the central server. Via the comparative experiments, we confirm that the zero-shot audio compression and decompression highly preserve anomaly detection performance while enhancing storage and transmission efficiency. © 2023 ieee.

关键词： anomaly detection data compression edge computing storage management transmission efficiency

来源：评论

学校读者我要写书评

暂无评论

Efficient data compression Algorithms for Cloud-Based Medical Imaging 1

Efficient Data Compression Algorithms for Cloud-Based Medica...

引用

1st International conference on Artificial Intelligence for Innovations in Healthcare Industries, ICAIIHI 2023

作者： Sharma, Himanshu Pundir, Sumit Deepak, A. Mayuri, K. Dwivedi, Shashi Prakash Kumar, Navneet Gla University Department of Computer Engineering and Applications Mathura India Graphic Era Deemed to Be University Department of Computer Science & Engineering Dehradun India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Tamilnadu Chennai India Institute of Aeronautical Engineering Department of Computer Science and Engineering Telangana Hyderabad India Lloyd Institute of Engineering and Technology Greater Noida India Lloyd Law College Greater Noida India

ISBN: (纸本)9798350330915

The storage as well as access of health-related imaging have been revolutionized by cloud-based systems. Algorithms for effective compression of information are essential for controlling the growing number of high-resolution photographs. The performance of compression techniques is assessed in this work using a deductive methodology employing a descriptive design, which is based on the interpretivist philosophy. For thorough analysis, secondary data gathering from several medical picture datasets is used. The study looks into well-known compression methodologies such wavelet-based methodologies, predictive computer programming, along with deep learning-based strategies. The results show wide variability in compression metrics, with wavelet-based techniques showing excellent spatial redundancies reduction performance. The tight equilibrium among compression overall diagnostic precision is highlighted by the slight artifacts introduced by some methods. The examination of computational resources reveals trade-offs between computing speed and memory needs, guiding real-world implementation. Statistical comparison highlights algorithmic differences and offers fact-based conclusions. The use of deep learning integration, specialized algorithm improvement, and dynamic compression methods are suggested. Future studies on telemedicine applications should investigate real-time compressing and hybrid methodologies. data privacy and security must continue to be guided by moral and legal principles. With implications for better storage and availability for health care providers, this study enhances the field by providing an in-depth comprehension of compression algorithms within stored in the cloud medical images. © 2023 ieee.

关键词： compression methods CT scans data transfer medical imaging radical

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 << < 120 121 122 123 124 125 126 127 128 129 > >>

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：