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

20,200 篇 会议
163 篇 期刊文献
80 册 图书
3 篇 学位论文

馆藏范围

20,446 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

12,718 篇 工学
- 8,282 篇 计算机科学与技术...
- 4,996 篇 软件工程
- 4,960 篇 信息与通信工程
- 4,631 篇 电气工程
- 1,443 篇 控制科学与工程
- 1,317 篇 电子科学与技术（可...
- 1,214 篇 光学工程
- 897 篇 生物医学工程（可授...
- 867 篇 机械工程
- 824 篇 仪器科学与技术
- 811 篇 生物工程
- 318 篇 网络空间安全
- 287 篇 交通运输工程
- 280 篇 安全科学与工程
- 277 篇 化学工程与技术
- 244 篇 动力工程及工程热...
- 187 篇 建筑学
- 178 篇 土木工程
4,646 篇 理学
- 2,146 篇 数学
- 2,061 篇 物理学
- 874 篇 生物学
- 667 篇 统计学（可授理学、...
- 522 篇 系统科学
- 324 篇 化学
1,519 篇 医学
- 1,405 篇 临床医学
- 383 篇 基础医学(可授医学...
- 269 篇 药学(可授医学、理...
1,361 篇 管理学
- 820 篇 管理科学与工程(可...
- 612 篇 图书情报与档案管...
- 208 篇 工商管理
204 篇 法学
136 篇 农学
78 篇 经济学
69 篇 军事学
63 篇 教育学
40 篇 文学
24 篇 艺术学
1 篇 哲学
1 篇 历史学

主题

1,117 篇 image segmentati...
1,059 篇 signal processin...
1,059 篇 image coding
1,007 篇 image processing
987 篇 internet of thin...
952 篇 feature extracti...
826 篇 image reconstruc...
631 篇 internet
553 篇 signal processin...
495 篇 signal to noise ...
476 篇 image edge detec...
474 篇 deep learning
456 篇 training
423 篇 image color anal...
400 篇 cameras
397 篇 robustness
391 篇 image enhancemen...
306 篇 image resolution
292 篇 image recognitio...
289 篇 visualization

机构

58 篇 school of inform...
39 篇 university of sc...
37 篇 signal processin...
29 篇 microsoft resear...
27 篇 university of ch...
26 篇 institute of sig...
26 篇 signal processin...
25 篇 center for signa...
24 篇 university of el...
23 篇 school of electr...
21 篇 ieee
21 篇 college of big d...
20 篇 school of cyber ...
20 篇 department of si...
20 篇 school of inform...
20 篇 signal and infor...
20 篇 school of electr...
19 篇 hsch darmstadt d...
19 篇 peng cheng labor...
19 篇 harbin institute...

作者

31 篇 li zhuo
27 篇 zhuo li
25 篇 sridharan sridha
23 篇 yang yang
23 篇 r.m. mersereau
20 篇 jing zhang
20 篇 wei li
20 篇 gabbouj moncef
19 篇 mansouri majdi
18 篇 zhang lei
18 篇 busch christoph
18 篇 m. gabbouj
17 篇 m.j.t. smith
17 篇 bouzrara kais
17 篇 clinton fookes
17 篇 zhang yan
16 篇 wang lei
16 篇 takahiro ogawa
16 篇 ghassan alregib
15 篇 mellouk abdelham...

语言

20,127 篇 英文
233 篇 其他
75 篇 中文
7 篇 俄文
6 篇 土耳其文
1 篇 西班牙文

检索条件"任意字段=IEEE International Conference on Signal Image Technology and Internet Based Systems"

共 20446 条记录，以下是4881-4890 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：

Deep Learning based CSI Reconstruction with Limited Feedback for Massive MIMO systems 13

Deep Learning based CSI Reconstruction with Limited Feedback...

引用

13th international conference on Mobile Computing and Ubiquitous Network (ICMU)

作者： Wang, Xin Hou, Xiaolin Chen, Lan Kishiyama, Yoshihisa Asai, Takahiro DOCOMO Beijing Commun Labs Co Ltd Beijing Peoples R China NTT DOCOMO INC Tokyo Japan

ISBN: (纸本)9784907626488

Channel state information (CSI) acquisition is one of the major challenges for massive MIMO systems to enable high efficiency MIMO transmissions. Limited feedback schemes, which quantize CSI into limited number of bits and feed these bits back to the base station (BS), are widely used in real-life mobile networks for BSs to obtain downlink CSI. Practical limited feedback schemes usually have large feedback granularity and introduce severe nonlinear quantization error due to the constraint on feedback overhead. It is hard for legacy signal processing technologies to reconstruct CSI accurately for high efficiency downlink transmissions. Different from the legacy signal processing technologies, deep neural networks trained with big data have strong abilities to fit any nonlinear functions and learn the complex signal model behind the big data, which is a useful tool to solve problems that are nonlinear or hard to be described mathematically. Motivated by these observations, we consider a deep learning based approach for BS receivers to reconstruct CSI based on the limited feedback bits from user equipment (UE). The CSI reconstruction is similar with the image super-resolution which reconstructs a high resolution image from a low resolution one based on the structure information learned by the neural network itself. Performance evaluations demonstrate that the proposed method outperforms the legacy algorithms. The improvement on spectrum efficiency is about 25%. It can also reconstruct the CSI with lower density reference signal (RS) than that in current specification, e.g., the RS density can be 1/32 of current one. Therefore, the reference signal and feedback overhead can be reduced with our method. These results show the potential gain of applying deep learning to physical layer signal processing at the receiver side only, which has little air-interface impact and does not require much effort on enhancing network specifications. Therefore, it is feasible to be deploy

关键词： Deep learning Quantization (signal) Receivers Massive MIMO Big Data Physical layer Downlink

来源：评论

学校读者我要写书评

暂无评论

An Efficient Squirrel Search Algorithm based Vector Quantization for image Compression in Unmanned Aerial Vehicles

An Efficient Squirrel Search Algorithm based Vector Quantiza...

引用

2021 international conference on Artificial Intelligence and Smart systems, ICAIS 2021

作者： Minu, M.S. Aroul Canessane, R. Sathyabama Institute of Science and Technology Computer Science and Engineering Chennai India

ISBN: (纸本)9781728195377

Unmanned aerial vehicles (UAVs) typically fly at low altitudes for capturing high-resolution images covering smaller areas. Since short flights also and high-resolution cameras lead to the generation of massive gigabytes (GBs) of data regions, image compression is essential to compress the data to a compact form resulted in shorter file size without any loss of quality. The vector quantization (VQ) is an effective type of image compression and the conventionally employed technique namely Linde-Buzo-Gray (LBG) algorithm continually created local optimal codebook. The codebook design process can be considered as a high dimensional optimization problem and can be resolved by the use of swarm intelligence algorithms. This paper designs a novel squirrel search algorithm (SSA) with LBG based image compression technique, called SSA-LBG for UAVs. The SSA is applied for the construction of codebooks for VQ and it makes use of LBG model as the initialization of the SSA for VQ. The application of SSA-LBG results in effective compression with low computation time (CT) and high peak signal to noise ratio (PSNR). An extensive set of simulations were performed on benchmark test images and the results are examined with respect to CT and PSNR undervarying bit rates and codebook sizes. © 2021 ieee.

关键词： Vector quantization

来源：评论

学校读者我要写书评

暂无评论

Clustering-Enhanced Reinforcement Learning for Adaptive Offloading in Resource-Constrained Devices

Clustering-Enhanced Reinforcement Learning for Adaptive Offl...

引用

international conference on Smart Computing (SMARTCOMP)

作者： Tran Anh Khoa Minh-Son Dao Do-Van Nguyen Koji Zettsu Big Data Integration Research Center National Institute of Information and Communications Technology Tokyo Japan

ISBN: (数字)9798350349948

ISBN: (纸本)9798350349955

The Federated Edge Artificial Intelligence (Edge AI) deploys AI applications on internet-of-Things (IoT) devices, addressing data privacy concerns in the real world. To achieve effective Federated Learning (FL), three challenges must be addressed: i) limited computing power on devices, ii) non-uniform impacts on devices, and iii) adaptability to changing network conditions. This study introduces a new algorithm called Adaptive Offloading Point (AOP), designed to accelerate local training on constrained devices. It decomposes deep neural network (DNN) layer blocks, enabling training on both client and server sides. The novelty of the proposed method lies in using a reinforcement learning-based Gaussian mixture model (GMM) clustering to dynamically determine DNN layer offloading, addressing nullability, computation uniformity, training time, and network bandwidth variation issues. Experimental results on real devices, using vision transformer (ViT) models with an identification image dataset, show that AOP's training time is significantly faster than that of previous baseline methods.

关键词： Training Performance evaluation Adaptation models Privacy image edge detection Edge AI Artificial neural networks

来源：评论

学校读者我要写书评

暂无评论

image Hiding Scheme based on Dense Residual Network

Image Hiding Scheme Based on Dense Residual Network

引用

Computer Science, Electronic Information Engineering and Intelligent Control technology (CEI), ieee international conference on

作者： Lifeng Chen Jia Liu Weina Dong Wenquan Sun College of Cryptography Engineering Engineering University of PAP Xi 'an China

ISBN: (数字)9798350372052

ISBN: (纸本)9798350372069

A new encoder-decoder steganography scheme, which is based on dense residual connections, is proposed in this paper to address the problem of low image quality in stego-image and message images generated by image steganography schemes relying on encoder-decoder networks. Unlike existing end-to-end image steganography networks, this scheme does not necessitate image preprocessing and utilizes dense residual connections to facilitate the transportation of features from shallow networks to each layer of deep network structures. Consequently, the detailed information of the feature map is effectively preserved. Furthermore, channel and spatial attention modules are employed to filter features, thus enhancing the attention of the encoder-decoder towards complex texture areas in the image. The experimental results obtained from LFW, PASCAL-VOC12, and imageNet datasets demonstrate the effective enhancement of image quality and algorithm security facilitated by the proposed method. The stego-image and carrier images achieve an average peak signal-to-noise ratio (PSNR) of up to 36.2dB and a structural similarity (SSIM) of 0.98, respectively.

关键词： image quality Steganography PSNR Transportation Feature extraction Information filters image preprocessing

来源：评论

学校读者我要写书评

暂无评论

Short-Segment Speaker Verification Using ECAPA-TDNN with Multi-Resolution Encoder

Short-Segment Speaker Verification Using ECAPA-TDNN with Mul...

引用

international conference on Acoustics, Speech, and signal Processing (ICASSP)

作者： Sangwook Han Youngdo Ahn Kyeongmuk Kang Jong Won Shin School of Electrical Engineering and Computer Science Gwangju Institute of Science and Technology Gwangju Korea

Time-domain approaches have shown the potential to improve the performance of speaker verification, but still predominant approaches utilize hand-crafted features such as the mel filterbank energies. Although these features are based on speech perception models and exhibited impressive performances, the fixed frame size does not allow good temporal and spectral resolutions at the same time and there is information loss when taking the magnitude spectrum and during frequency rescaling. In this paper, we propose to incorporate multi-resolution time-domain information into the ECAPA-TDNN speaker verification system. We construct a multi-resolution encoder to extract multiple features in different temporal resolutions, and let the extracted features drive the adapter modules. Experimental results showed that the proposed method outperformed other recently proposed approaches when the input length was 2 seconds or shorter for the VoxCeleb dataset. The proposed approach also showed superior performance on the Google Speech Commands dataset v2.

关键词： Time-frequency analysis Convolution Filter banks Feature extraction Acoustics internet Data mining

来源：评论

学校读者我要写书评

暂无评论

Overview of image encryption based on chaotic system 2

Overview of image encryption based on chaotic system

引用

2nd international conference on Computing and Data Science, CDS 2021

作者： Bu, Yu Tandon School of Engineering New York University New York United States

ISBN: (纸本)9781665404280

The upload and download of image data is a huge flow of traffic among internet, which means sensitive information are more vulnerable to be stolen and to be attacked by attackers. Therefore, it is urgently needed an image protection mechanism, namely image encryption schemes. Many image encryption schemes have been developed. Most of them adopt confusion-diffusion model by separating adjacent pixels and then spreading random substitution through all encrypted images. In particular, chaos-based algorithms are supportive to this structure. It is attractive to researchers owing to the unsteadiness and ramification structures. Chaotic maps are increasingly important in secure telecommunication because the security level of chaos-based algorithms are easily affected by the characteristic of chaotic maps. Generally, chaotic maps can be classified into one-dimensional (1D) and hyperdimensional (HD). In this paper, various kind of 1D and HD chaotic maps and their corresponding image encryption schemes have been reviewed. based on the comparison results, related fields within the image encryption schemes have been discussed to promote practical application and make clear of the optimization direction in the sections of conclusion and future work. © 2021 ieee.

关键词： Chaotic systems

来源：评论

学校读者我要写书评

暂无评论

Log-euclidean kernel sparse representation on DR-spectral SPD matrices for signal detection 6

Log-euclidean kernel sparse representation on DR-spectral SP...

引用

6th international conference on Communication, image and signal Processings, CCISP 2021

作者： Feng, Sheng Zhu, Xiaoqian Zhu, Zijie College of Computer Science National University of Defense Technology Chang Sha China College of Meteorology and Oceanography National University of Defense Technology Chang Sha China

ISBN: (纸本)9781665432795

In this paper, we propose a novel signal detection method in the framework of matrix information geometry and apply it to target detection in complex clutter. The sample data is first assumed to be constructed as a high-dimensional spectral SPD matrix by extracting the SIFT feature from the spectrogram obtained by STFT procedure. In this case, a high-dimensional SPD manifold is naturally modeled, which yields rich information from signal data. To eliminate the redundancy while preserve the original structure of the data, we first employ the dimensionality reduction (DR) method on the high-dimensional SPD manifold, then through Log-Euclidean Kernel sparse representation for the DR-spectral SPD matrices lying on a lower-dimensional SPD manifold, we finally perform a binary classification (the absence or presence of the objective signal) on a discriminative Reproducing Kernel Hilbert Space with low computational complexity. Similar researches, for instance, directly identify the spectral line or peak in the spectrogram, however, provide a poor description for signal data, which results in unsatisfactory detection performance. Experimental results based on real sea clutter show great information for complex signal detection tasks from signal data analysis with matrix information geometry, which can be widely used in signal processing. © 2021 ieee

关键词： signal detection

来源：评论

学校读者我要写书评

暂无评论

Localization Method of Optic Disc in Retinal image based on Texture Feature and Shape Feature 6

Localization Method of Optic Disc in Retinal Image Based on ...

引用

6th international conference on signal and image Processing, ICSIP 2021

作者： Zhao, Shu Chen, Weiyang Qilu University of Technology Shandong Academy of Sciences College of Computer Science and Technology Jinan China

ISBN: (纸本)9780738133737

The most important work of retinal image processing is blood vessel segmentation and optic disc location. The fovea in the retina image, as well as the bright spots and blood oozing caused by the disease will hinder the detection of optic disk. It is important for ophthalmology to locate the optic disc accurately. This method makes use of standard deviation in texture features and circular in shape feature. In this paper, we have screened the optic disc area, and then the angle information is used to detect the circle. The accuracy of our method to locate the optic disc can reach 100% on DRIVE dataset. © 2021 ieee.

关键词： Ophthalmology

来源：评论

学校读者我要写书评

暂无评论

Application of Virtual Data technology in Computer Graphics Scene Reconstruction under the Background of 'internet+' 5

Application of Virtual Data Technology in Computer Graphics ...

引用

5th international conference on Electronics, Communication and Aerospace technology, ICECA 2021

作者： Du, Chan Animation and Digital College of Nanjing Media College Jiangsu Province Nanjing210000 China

ISBN: (纸本)9781665435246

With the wide application of virtual reality technology, computer graphics and multimedia technology in various fields, people are paying more and more attention to the research on modeling and rendering methods of highly realistic 3D models, while traditional modeling methods are cost-effective There are unavoidable shortcomings in terms of speed and applicability. Under this premise, because image-based 3D reconstruction technology can directly extract texture from images, it can easily and quickly reconstruct a highly realistic 3D model. Received extensive attention. based on virtual data technology, this paper studies the application of computer graphics scene reconstruction. © 2021 ieee.

关键词： Cost effectiveness

来源：评论

学校读者我要写书评

暂无评论

MLNet: Mutual Learning Network to Improve Self-Supervised Representation for Fine-Grained Visual Recognition

MLNet: Mutual Learning Network to Improve Self-Supervised Re...

引用

international conference on Acoustics, Speech, and signal Processing (ICASSP)

作者： Peipei Zhao Jiaxuan Wang Zixiang Lu Qiguang Miao School of Computer Science and Technology Xidian University Xi’an China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

High-quality annotation of fine-grained visual categorization requires extensive professional knowledge, which is time-consuming and laborious. Therefore, learning fine-grained visual representations from a large number of unlabeled images through self-supervised learning has become a popular alternative solution recently. However, the existing self-supervised learning methods are not effective in fine-grained visual categorization since many features helpful for optimizing self-supervised learning objectives are unsuited to characterize the subtle differences in fine-grained viusal recognition. To deal with this issue, we propose a mutual learning network to enhance the model’s attention towards discriminative semantic features. The key idea is to consider semantic consistency between different augmented views within same image and capture discriminative semantic information. For semantic consistency, our research demonstrates that cross-view attention module between different augmented views can guide our model to capture similar semantic features. based on this, we further build a GradCAM-guided multi-dimension loss that utilize GradCAM to control our model from different dimensions to discriminative semantic information that are beneficial to fine-grained visual recognition. Experiments on CUB-200-2011, Stanford Cars and Aircrafts datasets demonstrate that the mutual learning network outperforms previous self-supervised learning methods in linear probing and image retrieval.

关键词： Training Visualization Atmospheric modeling Semantics Self-supervised learning signal processing Predictive models Feature extraction Speech processing Testing

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 << < 485 486 487 488 489 490 491 492 493 494 > >>

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：