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781-790 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：

Second-Order Statistic Deviation to Model Anomalies in the Design of Unsupervised Detectors 48

Second-Order Statistic Deviation to Model Anomalies in the D...

引用

48th ieee International conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Enttsel, Andriy Martinini, Filippo Marchioni, Alex Mangia, Mauro Rovatti, Riccardo Setti, Gianluca Dei Arces University of Bologna Italy Det Politecnico di Torino Italy

ISBN: (纸本)9781728163277

Anomaly Detection is a challenging task due to the limited knowledge about possible anomalies. This issue can be tackled by modeling anomalies through domain expertise or collecting sufficient anomalous data. However, some domains, such as monitoring systems, require detectors that are capable of detecting any potential alteration in the observed phenomenon. Hereby we propose a tool to generate anomalies as a statistical deviation from the characterization of the signal representing the normal behavior. Two families of deviation models are presented, and the effectiveness of the tool is proven using well-known unsupervised detectors. The effects of a possible intermediate data compression stage on the detection capabilities are also considered. © 2023 ieee.

关键词： anomaly sets lossy compression Outlier detection principal component analysis

来源：评论

学校读者我要写书评

暂无评论

A Novel Artistic Image compression Algorithm Based on Multi-Scale Adaptive Discrete Wavelet Transform

A Novel Artistic Image Compression Algorithm Based on Multi-...

引用

2025 International conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Li, Yijun China Academy of Art Yuhang District Zhejiang Hangzhou311100 China

ISBN: (纸本)9798331509828

How to compress information is a challenge in the digital age, and the image compression has a wide range of application scenarios. In order to solve the challenges of low compression efficiency and high loss rate of the traditional algorithms, this study proposes a compression algorithm based on multi-scale adaptive discrete wavelet transform. The core of the proposed algorithm is to make reasonable use of the multiresolution analysis characteristics of discrete wavelet transform. Based on the feature extraction, the image information is decomposed into high-frequency and low-frequency parts. This operation can stably and effectively implement frequency domain threshold processing and reduce redundant data. The proposed algorithm optimizes the encoding efficiency of image features to the greatest extent by introducing block difference features and designing a new iterative function system. In view of the high redundancy and high complexity of the artistic images, the traditional wavelet analysis is improved and optimized, and a multi-scale adaptive model is introduced. In the experiment, the test used multiple sets of artistic image test sets and compared them with mainstream algorithms (JPEG, VAE, etc.). In PSNR analysis, the proposed algorithm achieves better performance. © 2025 ieee.

关键词： Discrete wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

An Improved Delta compression Technique for NoC Packets

An Improved Delta Compression Technique for NoC Packets

引用

2023 ieee International conference on Next Generation Electronics, NEleX 2023

作者： Nafsiya, C.A. Viswanathan, Daleesha M. James, Rekha K. School of Engineering CUSAT Division of Information Technology Kerala Cochin India School of Engineering CUSAT Division of Electronics and Communication Engineering Kerala Cochin India

ISBN: (纸本)9798350319088

The traditional way of implementing delta compression is by finding the difference in the data chunks with respect to a base value. Once all the differences are found, if the differences are with a range in which, then they can be represented by a lesser number of bits with respect to base flit. The data will be then compressed so that the base value and delta are the compressed data contents. In this paper, an improved way of finding the delta values is proposed. By implementing the proposed method the time for finding the delta values can be reduced. The proposed method also reduces the number of bits in the base value. © 2023 ieee.

关键词： Network-on-chip

来源：评论

学校读者我要写书评

暂无评论

Multi-modal Dynamic Point Cloud Geometric compression Based on Bidirectional Recurrent Scene Flow

Multi-modal Dynamic Point Cloud Geometric Compression Based ...

引用

2025 ieee International conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Nan, Fangzhe Li, Frederick Wang, Zhuoyue Tam, Gary K.L. Jiang, Zhaoyi Zheng, Dong Yang, Bailin School of Statistics and Mathematics Zhejiang Gongshang University China School of Computer Science and Technolgy Zhejiang Gongshang University China University of Durham United Kingdom University of California Berkeley United States Swansea University United Kingdom Universal Ubiquitous Technology Co. Ltd.

ISBN: (纸本)9798350368741

Deep learning methods have recently shown significant promise in compressing the geometric features of point clouds. However, challenges arise when consecutive point clouds contain holes, resulting in incomplete information that complicates motion estimation. To our knowledge, most existing dynamic point cloud compression methods have largely overlooked this critical issue. Moreover, these methods typically employ a multi-scale single-pass approach for motion estimation, performing only one estimation at each scale. This limits accuracy and adversely impacts compression performance. To address these challenges, we propose a dynamic point cloud compression model called M2BRDPCC (Multi-Modal Multi-Scale Bidirectional Recursion for Dynamic Point Cloud compression). Our method introduces two key innovations. First, we integrate both point cloud and image data as inputs, leveraging a multi-modal feature representation completion (MFRepC) approach to align information across modalities. This addresses the issue of missing data in point clouds by using complementary information from images. Second, we implement a multi-scale bidirectional recursive (MSBR) motion estimation method. This module iteratively refines motion flows in both forward and backward directions, progressively enhancing point cloud features and improving motion estimation accuracy. Experimental results on widely used datasets, including MVUB and 8iVFB, demonstrate the effectiveness of our approach. Compared to existing methods, M2BR-DPCC achieves superior performance, with an average BD-rate improvement of 95.23% over V-PCC, 12.92% over D-DPCC, and 16.16% over patchDPCC. These results underscore the potential of leveraging multi-modal data and bidirectional refinement for dynamic point cloud compression. © 2025 ieee.

关键词： Dynamic point cloud geometric compression Multi-modal Multi-scale bidirectional recurrent

来源：评论

学校读者我要写书评

暂无评论

RIDDLE: Lidar data compression with Range Image Deep Delta Encoding

RIDDLE: Lidar Data Compression with Range Image Deep Delta E...

引用

ieee/CVF conference on Computer Vision and Pattern Recognition (CVPR)

作者： Zhou, Xuanyu Qi, Charles R. Zhou, Yin Anguelov, Dragomir Waymo LLC Mountain View CA 94043 USA

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Lidars are depth measuring sensors widely used in autonomous driving and augmented reality. However, the large volume of data produced by lidars can lead to high costs in data storage and transmission. While lidar data can be represented as two interchangeable representations: 3D point clouds and range images, most previous work focus on compressing the generic 3D point clouds. In this work, we show that directly compressing the range images can leverage the lidar scanning pattern, compared to compressing the unprojected point clouds. We propose a novel data-driven range image compression algorithm, named RIDDLE (Range Image Deep DeLta Encoding). At its core is a deep model that predicts the next pixel value in a raster scanning order, based on contextual laser shots from both the current and past scans (represented as a 4D point cloud of spherical coordinates and time). The deltas between predictions and original values can then be compressed by entropy encoding. Evaluated on the Waymo Open dataset and KITTI, our method demonstrates significant improvement in the compression rate (under the same distortion) compared to widely used point cloud and range image compression algorithms as well as recent deep methods.

关键词： Point cloud compression Solid modeling Image coding Laser radar Three-dimensional displays Predictive models Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

Reconstruction of Medical Images from Sparse data: A Deep Learning Approach 5

Reconstruction of Medical Images from Sparse Data: A Deep Le...

引用

5th International conference on Mobile Computing and Sustainable Informatics, ICMCSI 2024

作者： Saravanan, S. Bruntha, P.Malin Joseph S, Iwin Thanakumar Subramanian, Suresh Sundar, G. Naveen Narmadha, D. VIT School of Design Vellore Institute of Technology Department of Multimedia Vellore India Karunya Institute of Technology and Sciences Department of Electronics and Communication Engineering Coimbatore India Koneru Lakshmaiah Education Foundation Department of CSE Andhrapradesh Vaddeswaram India Saveetha School of Engineering Saveetha Institute of Medical and Technical Science Department of Electronics and Communication Engineering Chennai India Karunya Institute of Technology and Sciences Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350395235

For diagnosis, medical imaging technology plays a significant role in today's scenario. Accordingly, enormous amounts of medical data are generated daily on research centers and hospitals. Storing the medical images needs a lot of space where in 3D (Three dimensional) medical data acquires a huge space over it. All the medical image details need to be stored digitally for efficient diagnosis. The Digital Imaging and Communications in Medicine (DICOM) standard was established as the global norm for digitally storing patient images from diverse medical imaging modalities. Efficient compression over medical images is required to maintain efficacy in storage space. compression over images like JPEG, PNG, etc. may not be efficient in bringing an effective lossless image compression in all the types of imaging modalities. Hence, an efficient methodology of Image compression over medical images are required in today's scenario. This research study compares the performance of different methods of compression standard for medical images with the proposed method called DL Based Compressive sensing on Medical Image compression. The primary aim of Compressive Sensing (CS) is to achieve compression of a sparse signal at a sampling rate below the Nyquist rate. Results are analyzed using performance metrics like PSNR, MSE, BPP and CR. And it proves that the proposed algorithm achieves a higher PSNR value and states that it is efficient in bringing a lossless medical image compression. © 2024 ieee.

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

C4ECC: data compression for Bandwidth Efficiency Under ECC Protection in GPUs

C4ECC: Data Compression for Bandwidth Efficiency Under ECC P...

引用

2025 International conference on Electronics, Information, and Communication, ICEIC 2025

作者： Park, Sanghyun Choi, Boyeol Kim, Jungrae Sungkyunkwan University Semiconductor Convergence Engineering Suwon Korea Republic of Semiconductor Systems Engineering Sungkyunkwan University Suwon Korea Republic of

ISBN: (纸本)9798331510756

Modern GPUs using Graphics DDR DRAM rely on in-band Error Correcting Code (ECC) for memory protection, but this reduces effective bandwidth and increases latency. This paper introduces data compression for Bandwidth Efficiency under ECC Protection in GPUs, called C4ECC. C4ECC compresses 32B blocks to fit both data and redundancy within a single transfer between the GPU's Last Level Cache and device memory. Our evaluation shows that while traditional in-band ECC increases memory traffic by 68%, C4ECC reduces this overhead to an average of just 1.4 %. This reduction significantly lowers the performance overhead caused by in-band ECC from 34% to 3%, particularly in memory-intensive workloads. © 2025 ieee.

关键词： Bandwidth compression

来源：评论

学校读者我要写书评

暂无评论

Complementary Bi-directional Feature compression for Indoor 360° Semantic Segmentation with Self-distillation 23

Complementary Bi-directional Feature Compression for Indoor ...

引用

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

作者： Zheng, Zishuo Lin, Chunyu Nie, Lang Liao, Kang Shen, Zhijie Zhao, Yao Beijing Jiaotong Univ Inst Informat Sci Beijing Peoples R China Beijing Key Lab Adv Informat Sci & Network Techno Beijing Peoples R China

ISBN: (纸本)9781665493468

Semantic segmentation on 360 degrees images is a vital component of scene understanding due to the rich surrounding information. Recently, horizontal representation-based approaches outperform projection-based solutions, because the distortions can be effectively removed by compressing the spherical data in the vertical direction. However, these methods ignore the distortion distribution prior and are limited to unbalanced receptive fields, e.g., the receptive fields are sufficient in the vertical direction and insufficient in the horizontal direction. Differently, a vertical representation compressed in another direction can offer implicit distortion prior and enlarge horizontal receptive fields. In this paper, we combine the two different representations and propose a novel 360 degrees semantic segmentation solution from a complementary perspective. Our network comprises three modules: a feature extraction module, a bi-directional compression module, and an ensemble decoding module. First, we extract multi-scale features from a panorama. Then, a bi-directional compression module is designed to compress features into two complementary low-dimensional representations, which provide content perception and distortion prior. Furthermore, to facilitate the fusion of bi-directional features, we design a unique self distillation strategy in the ensemble decoding module to enhance the interaction of different features and further improve the performance. Experimental results show that our approach outperforms the state-of-the-art solutions on quantitative evaluations while displaying the best performance on visual appearance.

关键词： Visualization Computer vision Image coding Semantic segmentation Bidirectional control Distortion Feature extraction

来源：评论

学校读者我要写书评

暂无评论

The Conglomerate compression Approach for Visual Pattern Recognition Networks in Edge AI Applications 6

The Conglomerate Compression Approach for Visual Pattern Rec...

引用

6th ieee Pune Section International conference, PuneCon 2023

作者： Bhalgaonkar, Seema Munot, Mousami Anuse, Alwin SCTR's Pune Institute of Computer Technology & PES's Mcoe Sppu Dept of E&tc Pune India SCTR's Pune Institute of Computer Technology Sppu Dept of E&tc Pune India School of Ece Dr. Vishwanath Karad MIT-WPU Pune411038 India

ISBN: (纸本)9798350324204

Deep Neural Networks have shown remarkable performance in various applications of Visual Pattern Recognition (VPR). This field continues to grow due to emergence of new architectures, availability of huge data, and powerful computing resources. However, because of their high computational complexity that subsequently demands higher memory requirements, and power consumption, the deployment of such DNN-based Visual Pattern Recognition Networks (VPRN) models in edgeAI applications is hindered. Such overheads necessitate the compression of VPRN models while retaining their performance. This paper explores multiple compression techniques which combines Knowledge Distillation (KD), pruning and quantization that are applied to DNNs to achieve higher compression ratio. © 2023 ieee.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

FCC: Feature Clusters compression for Long-Tailed Visual Recognition

FCC: Feature Clusters Compression for Long-Tailed Visual Rec...

引用

ieee/CVF conference on Computer Vision and Pattern Recognition (CVPR)

作者： Li, Jian Meng, Ziyao Shi, Daqian Song, Rui Diao, Xiaolei Wang, Jingwen Xu, Hao Jilin Univ Changchun Peoples R China Univ Minho Braga Portugal Univ Toronto Toronto ON Canada

ISBN: (纸本)9798350301298

Deep Neural Networks (DNNs) are rather restrictive in long-tailed data, since they commonly exhibit an under-representation for minority classes. Various remedies have been proposed to tackle this problem from different perspectives, but they ignore the impact of the density of Backbone Features (BFs) on this issue. Through representation learning, DNNs can map BFs into dense clusters in feature space, while the features of minority classes often show sparse clusters. In practical applications, these features are discretely mapped or even cross the decision boundary resulting in misclassification. Inspired by this observation, we propose a simple and generic method, namely Feature Clusters compression (FCC), to increase the density of BFs by compressing backbone feature clusters. The proposed FCC can be easily achieved by only multiplying original BFs by a scaling factor in training phase, which establishes a linear compression relationship between the original and multiplied features, and forces DNNs to map the former into denser clusters. In test phase, we directly feed original features without multiplying the factor to the classifier, such that BFs of test samples are mapped closer together and do not easily cross the decision boundary. Meanwhile, FCC can be friendly combined with existing long-tailed methods and further boost them. We apply FCC to numerous state-of-the-art methods and evaluate them on widely used longtailed benchmark datasets. Extensive experiments fully verify the effectiveness and generality of our method. Code is available at https://***/lijian16/FCC.

关键词： detection Recognition: Categorization retrieval

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 << < 75 76 77 78 79 80 81 82 83 84 > >>

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：