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

7,385 篇 会议
347 篇 期刊文献
57 册 图书
17 篇 学位论文

馆藏范围

7,806 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

4,437 篇 工学
- 3,413 篇 计算机科学与技术...
- 1,714 篇 软件工程
- 1,071 篇 电气工程
- 711 篇 信息与通信工程
- 342 篇 控制科学与工程
- 337 篇 电子科学与技术（可...
- 302 篇 光学工程
- 233 篇 机械工程
- 222 篇 生物医学工程（可授...
- 177 篇 仪器科学与技术
- 154 篇 生物工程
- 90 篇 测绘科学与技术
- 59 篇 化学工程与技术
- 56 篇 航空宇航科学与技...
- 49 篇 材料科学与工程（可...
- 47 篇 土木工程
- 41 篇 动力工程及工程热...
- 40 篇 力学（可授工学、理...
1,593 篇 理学
- 778 篇 物理学
- 686 篇 数学
- 181 篇 生物学
- 143 篇 统计学（可授理学、...
- 142 篇 系统科学
- 78 篇 化学
554 篇 医学
- 455 篇 临床医学
- 101 篇 特种医学
- 80 篇 基础医学(可授医学...
444 篇 管理学
- 287 篇 管理科学与工程(可...
- 175 篇 图书情报与档案管...
- 73 篇 工商管理
37 篇 法学
36 篇 农学
23 篇 经济学
20 篇 文学
17 篇 教育学
7 篇 艺术学
6 篇 军事学

主题

866 篇 parallel process...
693 篇 image processing
324 篇 image segmentati...
297 篇 concurrent compu...
273 篇 distributed comp...
259 篇 computational mo...
252 篇 computer archite...
251 篇 feature extracti...
215 篇 image reconstruc...
194 篇 image edge detec...
186 篇 image coding
177 篇 graphics process...
170 篇 iterative method...
166 篇 hardware
165 篇 algorithm design...
164 篇 neural networks
159 篇 computer science
158 篇 deep learning
142 篇 pixel
140 篇 graphics process...

机构

47 篇 national laborat...
25 篇 college of compu...
21 篇 natl univ def te...
20 篇 natl univ def te...
19 篇 science and tech...
14 篇 natl univ def te...
13 篇 school of comput...
12 篇 univ chinese aca...
11 篇 king saud univer...
11 篇 university of ch...
11 篇 natl univ def te...
10 篇 national univers...
9 篇 natl univ def te...
9 篇 institute of inf...
9 篇 national laborat...
8 篇 natl univ def te...
8 篇 department of co...
8 篇 national laborat...
8 篇 college of compu...
8 篇 school of comput...

作者

37 篇 dou yong
28 篇 luo zhigang
26 篇 yong dou
21 篇 zhang xiang
19 篇 zhigang luo
18 篇 li dongsheng
17 篇 naiyang guan
17 篇 qiao peng
15 篇 huang xuhui
15 篇 jie liu
14 篇 niu xin
13 篇 yijie wang
13 篇 lan long
13 篇 wang huaimin
12 篇 anon
11 篇 xiang zhang
11 篇 yang yang
11 篇 liu jie
11 篇 wang yijie
11 篇 pesquet jean-chr...

语言

7,687 篇 英文
63 篇 其他
49 篇 中文
7 篇 土耳其文
3 篇 俄文

检索条件"任意字段=Conference on Parallel and Distributed Methods for Image Processing"

共 7806 条记录，以下是371-380 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：

A Method of image Denoising via Dense Attention DnCNN 7th

A Method of Image Denoising via Dense Attention DnCNN

引用

7th International conference on Innovative Computing, IC 2024

作者： An, MingShou Lim, Hye-Youn Kang, Dae-Seong School of Computer Science and Engineering Xi’an Technological University No. 2 Xuefu Zhonglu Weiyang District Shaanxi Xi’an China Department of Electronics Engineering Dong-A University 37 Nakdong-Daero 550 Beon-Gil Saha-gu Busan Korea Republic of

ISBN: (纸本)9789819741816

Many models with deep learning exhibit good performance, but due to the noise generated during the dataset or image generation and transmission used for learning, it may include noise and cannot achieve the desired results and performance. The representative denoising technique of applying deep neural networks, DnCNN, forcibly generates noisy images by adding Gaussian noise to the original image and learning to be the same as the original image. Applying deep neural network denoising techniques to perform learning and denoising in this way. However, when performance depends on depth and simply increases depth to improve performance, deep neural networks will experience performance saturation. To improve this issue, this paper proposed an image processing system with a attention mechanism. This method improves the image processing method by applying the attention unit to the representative denoising deep learning model DnCNN, and converting it into an outburst structure. It is divided into two parts: focusing on internal relationships based on given input values and focusing on spatial information. These two parts are executed in a parallel structure and then combined. Focusing attention mechanism identifies and compresses important features, and quickly adding these features by highlighting the structure can effectively eliminate noise. In addition, by applying it to image processing methods that require noise removal, various applications can be carried out. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Subsampling Decomposition based k-Space Refinement for Accelerated MRI Reconstruction

Subsampling Decomposition based k-Space Refinement for Accel...

引用

2025 IEEE International conference on Acoustics, Speech, and Signal processing, ICASSP 2025

作者： Qiao, Xiaoyu Li, Weisheng Xiao, Bin Huang, Yuping Yang, Lijian Chongqing Key Laboratory of Image Cognition Chongqing University of Posts and Telecommunications Chongqing China Key Laboratory of Cyberspace Big Data Intelligent Security Chongqing University of Posts and Telecommunications Ministry of Education Chongqing China

ISBN: (纸本)9798350368741

In accelerated MRI reconstruction problem, directly recovering all the missing k-space data from undersampled measurements is highly ill-posed and often leads to suboptimal performance. To address the problem, we propose a novel deep unfolding network (DUN) with subsampling decomposition (SD) based k-space refinement to mitigate the ill-posedness. Our method employs a parallel network architecture with a primary branch unfolded by gradient descent-inspired optimization process (GD-PB) for reconstruction. Additionally, we introduce an SD-based auxiliary branch (SD-AB) that decompose the inverse problem into moderately corrupted subproblems. We design a novel subsampling mask predictor that captures both global and local spatial correlations in k-space, ensuring the SD-AB effectively preserves the most well-reconstructed subsets as reliable region (RR). The RR in SD-AB is used to periodically refine the intermediate outputs of the GD-PB, achieving improved accuracy. Experimental results reveal that our method significantly outperforms conventional and SD-based DUN techniques, achieving superior PSNR and SSIM results compared with cutting-edge methods. © 2025 IEEE.

关键词： compressed sensing deep unfolded network MRI reconstruction parallel imaging subsampling decomposition

来源：评论

学校读者我要写书评

暂无评论

Aperiodic Local SGD: Beyond Local SGD 51

Aperiodic Local SGD: Beyond Local SGD

引用

51st International conference on parallel processing (ICPP)

作者： Zhang, Hao Wu, Tingting Cheng, Siyao Liu, Jie Harbin Inst Technol Harbin Peoples R China Harbin Inst Technol Shenzhen Shenzhen Peoples R China

ISBN: (纸本)9781450397339

Variations of stochastic gradient decedent (SGD) methods are at the core of training deep neural network models. However, in distributed deep learning, where multiple computing devices and data segments are employed in the training process, the performance of SGD can be significantly limited by the overhead of gradient communication. Local SGD methods are designed to overcome this bottleneck by averaging individual gradients trained over parallel workers after multiple local iterations. Currently, both for theoretical analyses and for practical applications, most studies employ periodic synchronization scheme by default, while few of them focus on the aperiodic schemes to obtain better performance models with limited computation and communication overhead. In this paper, we investigate local SGD with an arbitrary synchronization scheme to answer two questions: (1) Is the periodic synchronization scheme best? (2) If not, what is the optimal one? First, for any synchronization scheme, we derive the performance boundary with fixed overhead, and formulate the performance optimization under given computation and communication constraints. Then we find a succinct property of the optimal scheme that the local iteration number decreases as training continues, which indicates the periodic one is suboptimal. Furthermore, with some reasonable approximations, we obtain an explicit form of the optimal scheme and propose Aperiodic Local SGD (ALSGD) as an improved substitute for local SGD without any overhead increment. Our experiments also confirm that with the same computation and communication overhead, ALSGD outperforms local SGD in performance, especially for heterogeneous data.

关键词： distributed learning local SGD data heterogeneity federated learning computation and communication cost

来源：评论

学校读者我要写书评

暂无评论

Multi-Terminal Collaborative distributed Garden Planning System Integrating CG Technology 3

Multi-Terminal Collaborative Distributed Garden Planning Sys...

引用

3rd International conference on Pervasive Computing and Social Networking, ICPCSN 2023

作者： Wang, Ye Liu, Qi School of Art Design and Media Sanda University Shanghai201209 China

ISBN: (纸本)9798350322842

The fast distributed garden planning system in colleges and universities is one of the mainstream applications of contemporary computers. The latest traditional methods usually use the GPU full virtualization technology as an entry point to improve the problem of a single user and a single computer, so that a physical computer can shared by multiple users without interfering with each other. With this basis, this research study designs the novel multi-terminal collaborative distributed garden planning system integrating CG technology. Key innovations are: (1) The parallel SSOR-AI preconditioning combined with the CG algorithm is proposed to improve the traditional CG model. (2) The designed multi-terminal collaboration model considers the heterogeneous structure that will be more robust for the complex data. (3) The virtual image model is designed to finish the whole work flow. In the experiment part, the data is collected from Baidu search engine with the size of more than 1000000, the various tests are conducted to validate the performance. © 2023 IEEE.

关键词： Search engines

来源：评论

学校读者我要写书评

暂无评论

Speech Privacy Leakage from Shared Gradients in distributed Learning 48

Speech Privacy Leakage from Shared Gradients in Distributed ...

引用

48th IEEE International conference on Acoustics, Speech and Signal processing, ICASSP 2023

作者： Li, Zhuohang Zhang, Jiaxin Liu, Jian University of Tennessee Knoxville United States Intuit Ai Research United States

ISBN: (纸本)9781728163277

distributed machine learning paradigms, such as federated learning, have been recently adopted in many privacy-critical applications for speech analysis. However, such frameworks are vulnerable to privacy leakage attacks from shared gradients. Despite extensive efforts in the image domain, the exploration of speech privacy leakage from gradients is quite limited. In this paper, we explore methods for recovering private speech/speaker information from the shared gradients in distributed learning settings. We conduct experiments on a keyword spotting model with two different types of speech features to quantify the amount of leaked information by measuring the similarity between the original and recovered speech signals. We further demonstrate the feasibility of inferring various levels of side-channel information, including speech content and speaker identity, under the distributed learning framework without accessing the user's data. © 2023 IEEE.

关键词： distributed learning privacy leakage speech processing

来源：评论

学校读者我要写书评

暂无评论

Research on Low Dose CBCT image Reconstruction Algorithm Based on Deep Learning 4

Research on Low Dose CBCT Image Reconstruction Algorithm Bas...

引用

4th International conference on Information Science, parallel and distributed Systems, ISPDS 2023

作者： Liu, Xiangyu Dong, Jiwen Zhu, Jian School of Information Science and Engineering University of Jinan Jinan250022 China Shandong Cancer Hospital and Institute Shandong First Medical University Shandong Academy of Medical Sciences Department of Radiation Physics Technology Jinan250117 China

ISBN: (纸本)9798350337181

Radiation therapy, along with surgery and internal medicine therapy, is one of the three major methods of tumor treatment. To ensure that the actual treatment process is consistent with the radiotherapy plan and make the radiation accurately strikes the tumor, it is necessary to use the Cone Beam Computed Tomography (CBCT) device onboard the medical linear accelerator to quickly obtain CBCT images of the patient's treatment site before implementing radiotherapy. On the one hand, it is used to correct the patient's posture, and on the other hand, it can be used to observe the changes in the patient's tumor and normal tissue structure around the tumor, so as to timely revise the radiotherapy plan. Compared with CT images, CBCT has the characteristics of lower dose and more convenient access. At present, CBCT only has single level ray imaging, and the commonly used CBCT imaging energy is 80 keV, which can avoid patients receiving additional radiation exposure. However, the organ tissue edges of the 80keVCBCT image are relatively blurry and cannot effectively suppress the generation of metal artifacts, making it limited in observing changes in the patient's target area. The use of 140keV imaging can significantly suppress artifacts in the image, improve image quality, and thus improve radiotherapy accuracy, but at the same time, it increases the burden on patients. Therefore, we propose a deep learning method. By collecting low-dose 80keVCBCT images, we can reconstruct and generate images closer to 140keV energy level, reduce the radiation exposure received by patients, and at the same time provide radiotherapy technicians with higher quality CBCT images, so as to improve the observation effect of tumors and their surrounding normal tissues, and achieve the purpose of improving the accuracy of radiotherapy. © 2023 IEEE.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

No-reference stereo image quality evaluation method integrating monocular and binocular features 4

No-reference stereo image quality evaluation method integrat...

引用

4th International conference on Artificial Intelligence and Computer Engineering, ICAICE 2023

作者： Bai, Jinxin Hu, Xiaojuan School of Computer Science and Technology Changchun University of Science and Technology Jilin Changchun130000 China

ISBN: (纸本)9798400708831

In recent years, the widespread adoption of 3D technology has created a need for accurate and efficient stereoscopic image quality assessment methods. Such methods aim to automatically supervise and optimize stereoscopic image and video processing systems. Based on the characteristics of human vision, we propose a method that integrates monocular and binocular features. Initially, monocular quality-sensitive features are extracted separately for the left and right views through two parallel CNN sub-networks. Subsequently, a third CNN sub-network extracts binocular quality-sensitive features for stereo image pairs. Quality scores are then computed based on both monocular and binocular features, and the final predicted quality score is obtained through quality fusion. The proposed method is validated on the Waterloo dataset, achieving a PLCC value of 0.979 and SROCC value of 0.975 on Waterloo P-I, and a PLCC value of 0.973 and SROCC value of 0.970 on Waterloo P-II. The results demonstrate that the predicted scores obtained by the proposed method exhibit excellent consistency with subjective evaluation scores. © 2023 ACM.

关键词： Binoculars

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Optimized Resource Low-Power SoC Multi-Soft-Processor FPGA Hardware Acceleration Architecture for Fast Digital image processing

Design and Implementation of Optimized Resource Low-Power So...

引用

2023 IEEE National Aerospace and Electronics conference, NAECON 2023

作者： Namou, L. Megherbi, D.B. University of Massachusetts Cminds Research Center Department of Electrical and Computer Engineering LowellMA01854 United States

ISBN: (纸本)9798350338782

This paper focuses on designing, implementing, and optimizing a distributed multi-soft-processor SoC low-power FPGA-based software-hardware co-design architecture for fast digital image processing computing acceleration. The paper demonstrates an on and off-the-chip augmented hardware architecture implementation to overcome Memory, Cost, Size, and Power prohibitive resource constraints. This implementation experimentally achieves an optimized accelerated digital image processing and digital filtering execution time. The method achieves 80 times computational speedup with the proposed augmented hardware-accelerated optimization scheme compared to an initial practical implementation without hardware acceleration. This design is implemented on an SoC Altera Cyclone- V FPGA. In this design, an FPGA Multi Softcore Processor is instantiated in the fabric and interfaced with an external SDRAM via a 16-bit Memory Controller Intellectual Property (IP) core. An 8-bit intensity resolution image (up to 1280 x 1280 pixels, but not limited) was imported from a PC (via Serial Communication) to the FPGA for Sobel spatial filter processing. Each Soft Core was memory mapped to each image segment to create a parallel multiprocessing architecture. Multiple Sobel Filters are written and synthesized in the fabric. The Register Transfer Logic (RTL) code is written in VHDL and Verilog as a Hardware Description Language (HDL) to accelerate the design implementation. A different number of Softcore Processors in conjuncture with accelerated hardware are tested to compare the resulting computational efficiency. The timings between accessing the on-chip SRAM and the off-chip SDRAM can also be compared. In the final analysis, understanding that the FPGA Softcore using C is quick to implement and flexible to interface with, but it is a non-deterministic and sequentially executed process, and that the FPGA Fabric using HDL is rigid and constraint-driven, but no overhead, implemented in fabric, det

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

CNN-LSTM for Secure distributed Demand Response in Smart Grid 7

CNN-LSTM for Secure Distributed Demand Response in Smart Gri...

引用

7th International conference on image Information processing, ICIIP 2023

作者： Tirulo, Aschalew Chauhan, Siddhartha National Institute of Technology Departemet of Computer Science And Engineering HP Hamirpur India

ISBN: (纸本)9798350371406

Integrating cyber and physical elements in smart grids amplifies susceptibility to false data injection attacks (FDIAs), jeopardizing home automation and energy infrastructure. Traditional security strategies often underperform in FDIA detection due to varied data origins. We propose an advanced anomaly detection framework using CNN-LSTM, tailored to detect FDIAs in the grid's demand response. Our model employs supervised learning for improved precision when enriched with label information. Empirical tests with genuine energy data from Austin, Texas, demonstrate our model's superiority over existing methods, with metrics like accuracy, precision, recall, F1 score, and false positive rate consistently affirming its robustness and real-world applicability. © 2023 IEEE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Combined RNN Approach for Addressing Morphological, Syntactical, and Semantic Challenges in image Captioning 5th

Combined RNN Approach for Addressing Morphological, Syntacti...

引用

5th International conference on Computing, Communications, and Cyber Security, IC4S 2023

作者： Gaware, Ishaan Rajendra Khandelwal, Rishabh Rajpal, Dev Tyagi, Arnav Das, Sanchali School of Computer Science Engineering and Technology Bennett University Uttar Pradesh Greater Noida India

ISBN: (纸本)9789819725496

image caption generation is an emerging field that combines deep learning and natural language processing (NLP) techniques to generate descriptive and accurate captions for images automatically. This not only facilitates the efficient organization of digital files but also aids visually impaired individuals in understanding the context of images. This research investigates the application of state-of-the-art deep learning and NLP methods for image caption generation, specifically focusing on the InceptionV3 and GloVe (global vectors for word representation) models. The InceptionV3 model, a convolutional neural network (CNN) architecture designed for image classification tasks, has demonstrated a high level of accuracy in the imageNet Large Scale Visual Recognition Challenge (78.3%). The Keras sequential model was utilized to create four dense layers for the image and caption models, employing the InceptionV3 architecture for image classification. This modular design allows for stacking multiple layers to create a highly effective model for classifying images. In parallel, this research explores the GloVe model, an unsupervised approach for generating word embeddings that capture semantic and syntactic meaning. GloVe achieved an accuracy of 75.0%, surpassing the scores of competing methods such as Word2Vec (72.3%) and FastText (69.3%). Through our investigation, the research analyzes the effectiveness of these methods in generating descriptive and accurate captions for images. Additionally, the paper also identifies the challenges and limitations of current approaches, such as handling rare words and improving the diversity and coherence of generated captions. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： image classification

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 << < 34 35 36 37 38 39 40 41 42 43 > >>

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：