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

7,415 篇 会议
343 篇 期刊文献
57 册 图书
13 篇 学位论文

馆藏范围

7,828 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

4,446 篇 工学
- 3,415 篇 计算机科学与技术...
- 1,715 篇 软件工程
- 1,078 篇 电气工程
- 715 篇 信息与通信工程
- 343 篇 控制科学与工程
- 338 篇 电子科学与技术（可...
- 308 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
- 151 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...
- 48 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...
1,591 篇 理学
- 781 篇 物理学
- 690 篇 数学
- 175 篇 生物学
- 142 篇 系统科学
- 142 篇 统计学（可授理学、...
- 78 篇 化学
549 篇 医学
- 454 篇 临床医学
- 103 篇 特种医学
- 76 篇 基础医学(可授医学...
445 篇 管理学
- 287 篇 管理科学与工程(可...
- 176 篇 图书情报与档案管...
- 74 篇 工商管理
37 篇 法学
35 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

872 篇 parallel process...
691 篇 image processing
327 篇 image segmentati...
299 篇 concurrent compu...
273 篇 distributed comp...
266 篇 computational mo...
256 篇 feature extracti...
253 篇 computer archite...
216 篇 image reconstruc...
201 篇 image edge detec...
184 篇 image coding
177 篇 graphics process...
170 篇 iterative method...
165 篇 hardware
164 篇 neural networks
164 篇 algorithm design...
162 篇 deep learning
158 篇 computer science
142 篇 pixel
141 篇 graphics process...

机构

47 篇 national laborat...
25 篇 college of compu...
20 篇 natl univ def te...
19 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 institute of inf...
10 篇 national univers...
9 篇 natl univ def te...
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 cyber ...

作者

37 篇 dou yong
28 篇 luo zhigang
27 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 pesquet jean-chr...
11 篇 eyas el-qawasmeh

语言

7,541 篇 英文
231 篇 其他
54 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 7828 条记录，以下是1901-1910 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：

How to Avoid Zero-Spacing in Fractionally-Strided Convolution? A Hardware-Algorithm Co-Design Methodology

How to Avoid Zero-Spacing in Fractionally-Strided Convolutio...

引用

International conference on High Performance Computing

作者： Yuan Meng Sanmukh Kuppannagari Rajgopal Kannan Viktor Prasanna University of Southern California US Army Research Lab

ISBN: (纸本)9781665410175

Fractionally Strided Convolution (FSC) is a key operation in popular image-based Deep Learning models, for example, back propagation in CNN training, the decoding stage of convolutional auto-encoders and generative CNNs (GAN), etc. FSC typically performs up-convolution on a 2-D grid image, i.e., expands it to a larger one, as compared to conventional (down)-convolution, resulting in more complex computation patterns. Specifically, it introduces additional interleaved zero-spacing (i.e. insertion and padding of zeros) in feature maps that impose excessive computation and memory access overheads on traditional convolution methods such as im2col. The resulting hardware under-utilization is especially severe in layers with large kernels and large strides, commonly seen in typical CNNs and Generative CNNs. In this paper, we propose a methodology to address this challenge using a multi-channel-multi-kernel parallel algorithm, kn2row, to eliminate zero-computations in FSC. We further develop a unified accelerator for kn2row-based convolution and FSC operations in High-Level Synthesis (HLS). Benefiting from the compute-reduction of kn2row, we achieve up to 14.6x improvement in effective resource utilization in typical convolutional auto-decoding layers, GAN layers and backward pass of Nature-CNN, a reinforcement learning bench-marking model. These lead to overall speedup of up to 3.8x in the complete forward or backward propagation phases of the above benchmarks. Our methodology leads up to 8x speedup and 11x better power efficiency than general-purpose processors. Compared with existing GAN accelerators, our methodology achieves higher normalized throughput with high portability.

关键词： Backpropagation Convolution Computational modeling Graphics processing units Benchmark testing Throughput Hardware

来源：评论

学校读者我要写书评

暂无评论

Fast Nonlocal Diffusion by Stacking Local Filters for image Denoising 5th

Fast Nonlocal Diffusion by Stacking Local Filters for Image ...

引用

5th International conference of Pioneer Computer Scientists, Engineers and Educators, ICPCSEE 2019

作者： Qiao, Peng Sun, Weichu Dou, Yong Li, Rongchun Science and Technology on Parallel and Distributed Laboratory National University of Defense Technology ChangshaHunan410073 China University of South China HengyangHunan421000 China

ISBN: (纸本)9789811501203

Many image denoising methods achieve state-of-the-art performance with little consideration of computation efficiency. With the popularity of high-definition imaging devices, these denoising methods do not scale well to the high-definition images. Therefore, a fast image denoising method is proposed to meet the demand of processing high-definition images. Based on the analysis of the distribution of the distance distrs between the similar patches and their reference patches from a semantic aspect, the large distrs s was found to occur while their contribution to the overall distribution was small. Therefore, the nonlocal filters was replaced in trainable non-local reaction diffusion (TNLRD) with local filters. For image with 4096 X 4096 resolution, the proposed method runs about 6 times faster than TNLRD via a single-thread CPU implementation. And the GPU implementation of the proposed method is about 10 times faster than the CPU implementation. Furthermore, the proposed model achieves competing denoising performance compared with TNLRD in terms of PSNR and SSIM. © Springer Nature Singapore Pte Ltd. 2019.

关键词： image denoising

来源：评论

学校读者我要写书评

暂无评论

A Fast and Efficient FPGA-based Level Set Hardware Accelerator for image Segmentation

A Fast and Efficient FPGA-based Level Set Hardware Accelerat...

引用

IEEE International conference on Integrated Circuits, Technologies and Applications (ICTA)

作者： Ye Liu Yin Wang Liang Chang Jun Zhou School of lnformation and Communication Engineering University of Electronic Science and Technology of China Chengdu Sichuan China

ISBN: (数字)9781728180328

ISBN: (纸本)9781728180335

Level set algorithm has been widely used for image segmentation due to its high accuracy. In addition, compared to the deep learning-based image segmentation methods, the level set algorithm can be implemented without training data, which significantly reduce the labelling efforts. However, the normal level set algorithm is still developed using software, involving complex computation with a large number of pixels and iterations. Also, the software implementation induces long processing time and large power consumption. In this work, we propose a FPGA-based level set hardware accelerator for image segmentation. The proposed hardware accelerators contain four design components: task-level parallel processing, image splitting processing, fully-pipelined processing architecture, and time multiplexed gradient and divergence processing engine. Based on the experimental results, our proposed hardware accelerator achieves up to 10.7× acceleration compared to the level set algorithm executing on CPU, with only 2.2 W power consumption.

关键词： image segmentation Power demand Level set Software algorithms Hardware Software Task analysis

来源：评论

学校读者我要写书评

暂无评论

Addressing Skewness in Iterative ML Jobs with Parameter Partition

Addressing Skewness in Iterative ML Jobs with Parameter Part...

引用

IEEE conference on Computer Communications (IEEE INFOCOM)

作者： Wang, Shaoqi Chen, Wei Zhou, Xiaobo Chang, Sang-Yoon Ji, Mike Univ Colorado Dept Comp Sci Colorado Springs CO 80907 USA Univ Edinburgh Sch Informat Edinburgh Midlothian Scotland

ISBN: (纸本)9781728105154

Computational skewness is a significant challenge in multi-tenant data-parallel clusters that introduce dynamic heterogeneity of machine capacity in distributed data processing. Previous efforts to addressing skewness mostly focus on hatch jobs based on the assumption that processing time is linearly dependent on the size of partitioned data. However, they are ill-suited for iterative machine learning (ML) jobs, which (1) exhibit a non-linear relationship between the size of partitioned parameters and processing time within each iteration, and (2) show an explicit binding relationship between input data and parameters for parameter update. In this paper, we present FlexPara, a parameter partition approach that leverages the non-linear relationship and provisions adaptive tasks to match the distinct machine capacity so as to address the skewness in iterative ML jobs on data parallel clusters. FlexPara first predicts task processing time based on a capacity model designed for iterative ML jobs without the linear assumption. It then partitions parameters to parallel tasks through proactive parameter reassignment. Such reassignment can significantly reduce network transmission cost incurred by input data movement due to the binding relationship. We implement FlexPara in Spark and evaluate it with various ML jobs. Experimental results show that compared to hash partition, FlexPara speeds up the execution by up to 54% and 43% in private and NSF Chameleon clusters, respectively.

关键词： Task analysis Sparks Adaptation models Predictive models Computational modeling Iterative methods Data processing

来源：评论

学校读者我要写书评

暂无评论

CNN and RNN-based Deep Learning methods for Digital Signal Demodulation 2019

CNN and RNN-based Deep Learning Methods for Digital Signal D...

引用

International conference on image, Video and Signal processing (IVSP)

作者： Wu, Tian Beijing Univ Posts & Telecommun Beijing Key Lab Network Syst Architecture & Conve Beijing Peoples R China

ISBN: (纸本)9781450361750

In this paper we presented a neural network-based method to demodulate digital signals. After training with different modulation schemes, the learning-based receiver can perform demodulation without changing receiver hardware by loading certain parameters based on the modulation scheme. Combining CNN's ability to extract local features and RNN's time series modeling ability, we designed a mixed neural network model with parallel architecture and simulate FSK, PSK, QAM demodulation over AWGN and Raleigh-faded channels. The results show that the mixed neural network model can equal or even exceed the performance of the conventional demodulation method (matched filter or correlation-based demodulation). With this kind of receiver, we can intelligently process multiple types of digital modulated signals with flexibility.

关键词： Demodulation Neural network receiver Deep Learning AWGN channel Rayleigh-fading channel

来源：评论

学校读者我要写书评

暂无评论

Multiple Balance Subsets Stacking for Imbalanced Healthcare Datasets

Multiple Balance Subsets Stacking for Imbalanced Healthcare ...

引用

International conference on parallel and distributed Systems (ICPADS)

作者： Yachao Shao Tao Zhao Xiaoning Wang Xiaofeng Zou Xiaoming Fu Institute of Computer Science University of Göttingen Göttingen Germany National University of Defense Technology Changsha Hunan China First Affiliated Hospital of Gannan Medical University Ganzhou Jiangxi China

ISBN: (数字)9781728190747

ISBN: (纸本)9781728183824

Accurate prediction is highly important for clinical decision making and early treatment. In this paper, we study the imbalanced data problem in prediction, a key challenge existing in the healthcare area. Imbalanced datasets bias classifiers towards the majority class, leading to an unsatisfied classification prediction performance on the minority class, which is known as imbalance problem. Existing imbalance learning methods may suffer from issues like information loss, overfitting, and high training time cost. To tackle these issues, we propose a novel ensemble learning method called Multiple bAlance Subsets Stacking (MASS) by exploiting a multiple balance subsets construction strategy. Furthermore, we improve MASS with introducing parallelism (parallel MASS) to reduce the training time cost. We evaluate MASS on three real-world healthcare datasets, and experimental results demonstrate that its prediction performance outperforms the state-of-art methods in terms of AUC, F1-score and MCC. Through the speedup analysis, parallel MASS reduces the training time cost greatly on large dataset, and its speedup increases as the data size grows.

关键词： Training Learning systems conferences Stacking Decision making Medical services parallel processing

来源：评论

学校读者我要写书评

暂无评论

One-Class Feature Learning Using Intra-Class Splitting 27

One-Class Feature Learning Using Intra-Class Splitting

引用

27th European Signal processing conference (EUSIPCO)

作者： Schlachter, Patrick Liao, Yiwen Yang, Bin Univ Stuttgart Inst Signal Proc & Syst Theory Stuttgart Germany

ISBN: (纸本)9789082797039

This paper proposes a novel generic one-class feature learning method based on intra-class splitting. In one class classification, feature learning is challenging, because only samples of one class are available during training. Hence, state-of-the-art methods require reference multi-class datasets to pretrain feature extractors. In contrast, the proposed method realizes feature learning by splitting the given normal class into typical and atypical normal samples. By introducing closeness loss and dispersion loss, an intra-class joint training procedure between the two subsets after splitting enables the extraction of valuable features for one-class classification. Various experiments on three well-known image classification datasets demonstrate the effectiveness of our method which outperformed other baseline models in average.

关键词： Training Dispersion Feature extraction image reconstruction Measurement Learning systems distributed databases

来源：评论

学校读者我要写书评

暂无评论

A gaussian recursive filter parallel implementation with overlapping 15

A gaussian recursive filter parallel implementation with ove...

引用

15th International conference on Signal image Technology and Internet Based Systems, SISITS 2019

作者： De Luca, Pasquale Galletti, Ardelio Marcellino, Livia Department of Computer Science University of Salerno Fisciano Italy Department of Science and Technology University of Naples Parthenope Naples Italy

ISBN: (纸本)9781728156866

Gaussian convolutions computation is required in several scientific fields and, to this aim, efficient approximation methods, based on Recursive Filters (RFs), have been developed recently. Among them, Gaussian Recursive Filters (RFs) are designed to approximate the Gaussian convolution in a very efficient way. The accuracy of these methods, as is well known, can be improved by means of the use of the so-called K-iterated Gaussian recursive filters, that is in the repeated application of the basic RF. To improve the provided accuracy, K-iterated versions of these methods are also considered. Since it is often necessary to handle large size one-dimensional input signals, a parallel approach becomes mandatory. Recently, we proposed a parallel algorithm for the implementation of the K-iterated first-order Gaussian RF on multicore architectures. Here, using a similar parallelization strategy, based on a domain decomposition with overlapping, we propose a new implementation that would exploit, in terms of both accuracy and performance, the GPU (Graphics processing Unit) capabilities on CUDA environment. Tests and experiments confirm the reliability and the efficiency of the proposed implementation. © 2019 IEEE.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

image Denoising Based on Wavelet Transform and BM3D Algorithm 4

Image Denoising Based on Wavelet Transform and BM3D Algorith...

引用

4th IEEE International conference on Signal and image processing (ICSIP)

作者： Su, Qinning Wang, Yong Li, Yiyao Zhang, Chengyan Lang, Ping Fu, Xiongjun Beijing Inst Technol Sch Informat & Elect Beijing Peoples R China

ISBN: (纸本)9781728136608

image denoising as a key method is innovating continuously. Since the Block matching and 3D (BM3D) algorithm is superior to other methods in suppressing Gaussian noise, it has become the current state-of-the-art of denoising. Nevertheless, the image detail information will be partially lost during eliminating image additive noise, there is still room for improvement. Aiming at the existing problems of BM3D algorithm, an improved BM3D algorithm is designed by a combination of wavelet transform and BM3D algorithm. The method applies the principle that wavelet denoising preserves fine edge information to compensate the missing edge details caused by BM3D algorithm. The wavelet threshold denoising runs in parallel with the BM3D algorithm. Firstly, the wavelet threshold denoising method is used to obtain the preprocessed image. Meanwhile, the BM3D algorithm is applied to the corrupted image, including the basic estimate and the final estimate operation, to get another denoising preprocessed image. Finally, the final result comes out from pixel-level averaging of the two preprocessed images. Experimental analysis on three images of Lena, Barbara and Cameraman illustrate that denoising, using the proposed algorithm, can provide largest value of peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM). The qualitative and quantitative research results illuminate that the improved algorithm is effective and robust.

关键词： digital image image denoising wavelet BM3D

来源：评论

学校读者我要写书评

暂无评论

Graphical Model Transformation Analysis for Cognitive Computing and Machine Learning on the SpiNNaker Chip Multiprocessor 22

Graphical Model Transformation Analysis for Cognitive Comput...

引用

45th Euromicro conference on Software Engineering and Advanced Applications (SEAA) / 22nd Euromicro conference on Digital System Design (DSD)

作者： Andreou, Andreas G. Mendat, Daniel R. Johns Hopkins Univ Dept Elect & Comp Engn Baltimore MD 21218 USA Univ Cyprus Dept Elect & Comp Engn Nicosia Cyprus

ISBN: (纸本)9781728128610

The SpiNNaker is a parallel neuromorphic hardware architecture that enables a wide variety of computations to be performed in a distributed, event-based manner. The authors have previously shown large speedups for performing MCMC inference using spiking neurons on the SpiNNaker as well as the parallella, an open-source parallel computing device. Both architectures provide platforms for performing innovative low-power computations, and there are other massively parallel chip multiprocessor platforms arriving in the future. This paper explores a complexity analysis for the algorithms in the automated framework developed to take a binary Bayesian network the whole way from reading in its text file description and transforming the network for parallel MCMC sampling to performing sampling on the SpiNNaker. Although it is focused on the SpiNNaker, many of these principles apply when using other neuromorphic chip multiprocessors, as this algorithmic flow has already been used with the parallella after some modifications.

关键词： Markov processes Complexity theory image color analysis Color Hardware Performance evaluation Bayes methods

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 << < 187 188 189 190 191 192 193 194 195 196 > >>

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：