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2001-2010 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：

Study on Visual Detection Device of Plant Leaf Disease 16

Study on Visual Detection Device of Plant Leaf Disease

引用

16th IEEE International conference on Mechatronics and Automation (IEEE ICMA)

作者： Fu, Ning Wang, Chong Ji, Xiaowen JiLin Agr Sci & Technol Univ Jilin Jilin 132101 Jilin Peoples R China

ISBN: (纸本)9781728116976

In order to resist the erosion of corn diseases, researchers have done many experiments and accumulated a lot of experiences. These experiences are not only practical, which used embedded system technology, computational reasoning technology, parallel computing, fuzzy reasoning technology, image recognition, internet of things technology, database technology and other related technologies are combined together, these acquired professional knowledge can effectively prevent and treat corn diseases. Therefore, it is necessary to widely spread these knowledges in order to truly treat corn diseases effectively for prevention and control. However, in many corn disease identification methods, only one type of disease in corn lesions can be identified. When corns are infected with multiple lesions, the lesions that appear after the superposition are not accurately recognized and thus delayed. The treatment of corn diseases caused a reduction in the production of corn and caused serious economic losses to farmers.

关键词： Corn Mathematical Morphology Embedded system Digital image processing

来源：评论

学校读者我要写书评

暂无评论

Towards Making Unsupervised Graph Hashing Robust

Towards Making Unsupervised Graph Hashing Robust

引用

IEEE International conference on Multimedia and Expo (ICME)

作者： Xuesong Gu Guohua Dong Xiang Zhang Long Lan Zhigang Luo Science and Technology on Parallel and Distributed Laboratory NUDT NUDT Institute for Quantum Information & HPCL

ISBN: (数字)9781728113319

ISBN: (纸本)9781728113326

Unsupervised hashing without supervision easily deteriorates in the case of grossly corrupted data. Motivated by robust optimization, this paper proposes a dual-graph regularized robust hashing (DGRH) based on both manifold smoothness and robust estimators in a more intuitive manner. Orthogonal to existing robust hashing methods, DGRH directly removes the outliers of datasets with M-estimator to exert robustness. In specific, it intends to recover low-rank representation from corrupted data via l 1 loss while preserving neighborhood relationships among samples with dual-graph regularization. Although DGRH seems a simple extension of robust PCA on graphs with hashing trick, it is easy to implement yet effective. Theory analysis is provided to support our claim. Experiments of image retrieval on three popular benchmark datasets show the efficacy of DGRH as compared to several well-behaved representative counterparts.

关键词： Robustness Binary codes image retrieval Optimization Manifolds Principal component analysis Measurement

来源：评论

学校读者我要写书评

暂无评论

Fast depth decision in Light field compression

Fast depth decision in Light field compression

引用

Data Compression conference (DCC)

作者： Amirpour, Hadi Pinheiro, Antonio Pereira, Manuela Ghanbari, Mohammad Inst Telecomunicacoes Covilha Portugal Univ Beira Interior Covilha Portugal Univ Tehran Sch Elect & Comp Engn Tehran Iran Univ Essex Sch Comp Sci & Elect Engn Colchester Essex England

ISBN: (纸本)9781728106571

Pseudo-sequence based light field compression methods are a highly efficient solution to compress light field images. They use state-of-the-art video encoders like HEVC to encode the image views. HEVC exploits Coding Tree Unit (CTU) structure which is flexible and highly efficient but it is computationally demanding. Each CTU is examined in various depths, prediction and transformation modes to find an optimal coding structure. Efficiently predicting depth of the coding units can reduce complexity significantly. In this paper, a new depth decision method is introduced which exploits the minimum and maximum of previously encoded co-located coding units in spatially closer reference images. Minimum and maximum depths of these co-located CTUs are computed for each coding unit and are used to limit the depth of the current coding unit. Experimental results show up to 55% and 85% encoding time reduction with serial and parallel processing respectively, at negligible degradations.

关键词： image coding Data compression Copper Computer science Video sequences Encoding Complexity theory

来源：评论

学校读者我要写书评

暂无评论

App-Net: A Hybrid Neural Network for Encrypted Mobile Traffic Classification

App-Net: A Hybrid Neural Network for Encrypted Mobile Traffi...

引用

IEEE conference on Computer Communications Workshops, INFOCOM Wksps

作者： Xin Wang Shuhui Chen Jinshu Su College of Computer Science and Technology National University of Defense Technology National Key Laboratory for Parallel and Distributed Processing National University of Defense Technology

ISBN: (数字)9781728186955

ISBN: (纸本)9781728186962

With the exponential growth of mobile traffic data, mobile traffic classification is in a great need. It is an essential step to improve the performance of network services such as QoS and security monitoring. However, the widespread use of encrypted protocols, especially the TLS protocol, has posed great challenges to traditional traffic classification techniques. As the rule-based deep packet inspection approaches are ineffective for encrypted traffic classification, various machine learning methods have been studied and used. Recently, deep learning solutions which enable automatic feature extraction are also proposed to classify encrypted traffic. In this paper we propose App-Net, an end-to-end hybrid neural network, to learn effective features from raw TLS flows for mobile app identification. App-Net is designed by combining RNN and CNN in a parallel way. So that it can learn a joint flow-app embedding to characterize both flow sequence patterns and unique app signatures. We evaluate App-Net on a real-world dataset that covering 80 apps. The results show that our method can achieve an excellent performance and outperform the state-of-the-art methods.

关键词： Cryptography Feature extraction Payloads Recurrent neural networks Machine learning Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Eigan: Enhanced Inpainting Generative Adversarial Network

Eigan: Enhanced Inpainting Generative Adversarial Network

引用

IEEE International conference on Multimedia and Expo (ICME)

作者： Feiyu Chen Wei Deng Chuanfa Zhang Kangzheng Gu Wenqiang Zhang Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University China

ISBN: (数字)9781728113319

ISBN: (纸本)9781728113326

Generating coherent texture in a repaired region, especially at the boundary, is one of the challenges in image inpainting. To maintain the coherence in the edge transitional region, we propose an efficient framework, enhanced inpainting generative adversarial network (EIGAN). EIGAN is composed of a multi-resolution intersection encoder, a dual decoder, and an adversarial patch discriminator. The encoder and the decoder are used to process multi-resolution semantic information in a parallel and cross-connected fashion. Specially, we utilize a soft-contextual attention module embedded into the decoder to capture contextual information so that the attention module can help the decoder to generate coherent texture and content. Moreover, to improve the details, we introduce an advanced patch discriminator with relativistic adversarial loss named adversarial patch discriminator. Experimental results show that our improvements can enhance the coherence and quality of the completed image, and enable EIGAN to outperform the state-of-the-art image inpainting methods.

关键词： Convolution Decoding Semantics Feature extraction Generative adversarial networks Coherence Generators

来源：评论

学校读者我要写书评

暂无评论

On parallelizing Geometrical PCA Approximation 18

On Parallelizing Geometrical PCA Approximation

引用

18th Annual RoEduNet conference on Networking in Education and Research (RoEduNet)

作者： Machidon, Alina Luminita Ciobanu, Catalin Bogdan Machidon, Octavian Mihai Ogrutan, Petre Lucian Transilvania Univ Brasov Brasov Romania Delft Univ Technol Delft Netherlands

ISBN: (纸本)9781728153445

Remote sensing data has known an explosive growth in the past decade. This has led to the need for efficient dimensionality reduction techniques, mathematical procedures that transform the high-dimensional data into a meaningful, reduced representation. Principal Component Analysis (PCA) is a well-known dimensionality reduction technique used in the field of hyperspectral satellite images. However, PCA suffers from high computational costs and increased complexity, an issue that led to elaborating PCA adaptations capable of running on multi-core computing architectures. This paper proposes a parallel implementation of the geometrical PCA approximation (gaPCA) algorithm. Three parallel implementations are studied: two on multi-core CPUs and a NVIDIA Graphics processing Units (GPU) CUDA accelerated implementation. Our results show significant speedups of the parallel implementations when applied on hyperspectral image datasets. Our results show that on the Intel Core i5 CPU, Python multi-core implementation is up to 2.01 x faster than its Matlab equivalent. Our GPU PyCUDA implementation is considerably faster than both our Python multi-core CPU implementations: up to 1.76 x faster than Intel Core i5-6200U and up to 5.72x faster than the NVIDIA Jetson Nano quad-core ARM A53 CPU. We performed data analysis on the output data for the three methods and the maxim relative error was less than 0.001%.

关键词： Principal Component Analysis Multicore CPU GPU CUDA Python parallel Computing

来源：评论

学校读者我要写书评

暂无评论

An image processing method for characterizing diffusivity in brain's parenchyma: A case study of significantly non-uniform structures 4

An image processing method for characterizing diffusivity in...

引用

4th International conference on Intelligent Informatics and Biomedical Sciences, ICIIBMS 2019

作者： Postnikov, Eugene B. Postnov, Dmitry E. Kursk State University Department of Theoretical Physics Kursk Russia Saratov State National Research University Department of Optics and Biophotonics Saratov Russia

ISBN: (纸本)9781728133805

We present a simple method, based on the principle of diffusion imaged processing, for revealing the type and quantitative characteristic of transport processes in brain tissue from fluorescent microscopy data. We consider a general form of the diffusion kernel, which covers both normal and hindered anomalous diffusion in media with complex microstructure as well as its practical correlation-based implementation. Our method overcomes restrictions of the conventional methods, which require extracting small areas with a high degree of symmetry and allows to process the large scale images, when solute leakage sources are distributed along the branched vascular structure. © 2019 IEEE.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

Implementation of Moving Target Detection and Tracking Algorithms Based on FPGA 6

Implementation of Moving Target Detection and Tracking Algor...

引用

conference on Optical Metrology and Inspection for Industrial Applications VI

作者： Xing Kai Li Binhua Tao Yong Wang Jinliang He Chun Kunming Univ Sci & Technol Fac Informat Engn & Automat Kunming 650504 Yunnan Peoples R China

ISBN: (纸本)9781510630963

In order to improve the real-time and portability of the moving target detection and tracking (MTDT) system, a compact FPGA-based MTDT system is built in this paper by using the parallel computing and flexible programming of Field Programmable Gate Array (FPGA). In order to realize the detection and tracking of moving targets on resource -constrained FPGA, some MTDT algorithms is analyzed firstly, and appropriate modifications were made without changing the basic principles to make it adapt to the limited logical resources of the Xilinx Spartan -6 series of FPGA chip selected in this design. Then the FPGA system is composed of four units: the image acquisition unit, the image storage unit, the image pre-and post- processing unit and the image display unit. Two image difference methods, an inter-frame and a background difference method, are implemented in the system. Finally, the moving target can be directly indicated on a video graphics array (VGA) displayer in the image display unit. The test results show that the system can detect and track a single target in real time in various resolutions at various frame rates, i.e. VGA @30fps and 15fps, 720p @15fps.

关键词： Moving target image detection Target tracking FPGA

来源：评论

学校读者我要写书评

暂无评论

distributed Feature Extraction on Apache Spark for Human Action Recognition

Distributed Feature Extraction on Apache Spark for Human Act...

引用

International conference on Ubiquitous Information Management and Communication (IMCOM)

作者： Nguyen Anh Tu Thien Huynh-The Kok-Seng Wong Dinh-Mao Bui Young-Koo Lee Dept. Computer Science Nazarbayev University Nur-Sultan Republic of Kazakhstan ICT Convergence Research Center Kumoh National Institute of Technology Gumi South Korea Dept. Computer Science & Engineering Kyung Hee University Yongin South Korea

ISBN: (数字)9781728154534

ISBN: (纸本)9781728154541

Local feature extraction is one of the most important tasks to build robust video representation in human action recognition. Recent advances in computing visual features, especially deep-learned features, have achieved excellent performance on a variety of action datasets. However, the extraction process is computing-intensive and extremely time-consuming when conducting it on large-scale video data. Consequently, to extract video features over big data, most of the existing methods that run on single machine become inefficient due to the limit of computation power and memory capacity. In this paper, we propose the elastic solutions for feature extraction based on the Spark framework. Particularly, exploiting the in-memory computing capability of Spark, the process of computing features are parallelized by partitioning video data into videos or frames and place them into resilient distributed datasets (RDDs) for the subsequent processing. Then, we present the parallel algorithms to extract the state-of-the-art deep-learned features on the Spark cluster. Subsequently, using the distributed encoding, the extracted features are aggregated into the global representation which is fed into the learned classifier to recognize actions in videos. Experimental results on a benchmark dataset demonstrate that our proposed methods can significantly speed up the extraction process and achieve the promising scalability performance.

关键词： Feature extraction Sparks Trajectory Task analysis Liquid crystal displays Visualization Streaming media

来源：评论

学校读者我要写书评

暂无评论

Accelerating Atrous Convolution with Fetch-and-Jump Architecture for Activation Positioning

Accelerating Atrous Convolution with Fetch-and-Jump Architec...

引用

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

作者： Zhuo Wang Zheng Wang Bo Dong Chao Chen Yongkui Yang Zhibin Yu Shenzhen Institutes of Advanced Technology Chinese Academy of Science Shenzhen China School of Microelectronics Xidian University Xi’an China

ISBN: (数字)9781728180328

ISBN: (纸本)9781728180335

Recent advancements in abundant applications of computer vision (CV) have attributed to convolutional neural network, which plays the primary role in feature extraction. For specific CV tasks such as semantic image segmentation, aggregation of multi-scale contextual information is demanded which leads to the adoption of atrous convolution. However, atrous convolution introduces extra performance overheads for conventional CPU and GPU machines, mainly due to inconstant latency of memory access caused by holes in atrous kernels. Such deterioration gets exaggerated especially during parallel processing of pixels in the output feature map. In this work, we first assemble continuous datastream by overlapping adjacent atrous kernels to avoid frequent update of memory access locations. By referring various patterns of atrous kernels, we introduce distributed fetch pointers to extract individual elements from assembled datastream while adaptively update pointer positions. A prototype dataflow accelerator has been designed with a demonstration on MobileNet-SSD network involving atrous kernels. The benchmarking result proves that our design achieves even slight speed-up for atrous convolution compared to conventional convolution, other than visible performance degradation for mainstream CPU and GPU.

关键词： Convolution Graphics processing units Computer architecture Benchmark testing Feature extraction Central processing Unit Kernel

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 << < 197 198 199 200 201 202 203 204 205 206 > >>

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：