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

859 篇 会议
25 篇 期刊文献
6 册 图书
1 篇 学位论文

馆藏范围

891 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

613 篇 工学
- 397 篇 计算机科学与技术...
- 337 篇 电气工程
- 219 篇 信息与通信工程
- 134 篇 软件工程
- 87 篇 电子科学与技术（可...
- 72 篇 仪器科学与技术
- 41 篇 控制科学与工程
- 36 篇 机械工程
- 28 篇 光学工程
- 15 篇 生物医学工程（可授...
- 12 篇 测绘科学与技术
- 11 篇 动力工程及工程热...
- 7 篇 航空宇航科学与技...
- 7 篇 生物工程
- 6 篇 建筑学
- 6 篇 土木工程
- 5 篇 材料科学与工程（可...
- 5 篇 交通运输工程
230 篇 理学
- 146 篇 物理学
- 56 篇 系统科学
- 38 篇 数学
- 10 篇 统计学（可授理学、...
- 7 篇 化学
- 7 篇 生物学
93 篇 医学
- 88 篇 临床医学
- 8 篇 基础医学(可授医学...
- 5 篇 药学(可授医学、理...
30 篇 管理学
- 23 篇 管理科学与工程(可...
- 10 篇 图书情报与档案管...
5 篇 法学
- 4 篇 社会学
3 篇 艺术学
1 篇 教育学
1 篇 军事学

主题

82 篇 field programmab...
63 篇 image processing
59 篇 signal processin...
56 篇 algorithm design...
54 篇 computer archite...
50 篇 hardware
38 篇 estimation
37 篇 clocks
32 篇 ofdm
31 篇 modulation
30 篇 filtration
29 篇 image reconstruc...
28 篇 cameras
28 篇 digital signal p...
27 篇 optimization
23 篇 kernel
23 篇 fpga
22 篇 deep learning
21 篇 feature extracti...
20 篇 image coding

机构

6 篇 national mobile ...
6 篇 lab of efficient...
4 篇 yildiz tekn univ...
3 篇 effat univ elect...
3 篇 stmicroelectroni...
3 篇 agh univ sci & t...
3 篇 beihang univ sta...
3 篇 department of co...
3 篇 ecole polytechni...
3 篇 ietr insa rennes...
3 篇 singapore univ t...
3 篇 zhejiang univ co...
3 篇 tsinghua univ de...
3 篇 ecole polytechni...
3 篇 lodz univ techno...
2 篇 sutd zju idea pe...
2 篇 edinburgh napier...
2 篇 singapore univ t...
2 篇 univ sassari pol...
2 篇 sony lsi design ...

作者

8 篇 chuan zhang
7 篇 mattavelli marco
6 篇 xiaohu you
5 篇 hannig frank
5 篇 fey dietmar
5 篇 palumbo francesc...
5 篇 stabernack benno
4 篇 tomasz kryjak
4 篇 bilge hasan saki...
4 篇 pelcat maxime
4 篇 jean-françois ne...
4 篇 lacassagne lione...
4 篇 margala martin
4 篇 bilgin gokhan
4 篇 marco mattavelli
4 篇 dominique houzet
4 篇 wang yu
4 篇 gorgon marek
4 篇 paolo meloni
4 篇 raffo luigi

语言

829 篇 英文
42 篇 土耳其文
20 篇 中文

检索条件"任意字段=2017 Conference on Design and Architectures for Signal and Image Processing, DASIP 2017"

共 891 条记录，以下是301-310 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：

MULTI-SCALE CONVOLUTIONAL NEURAL NETWORKS FOR CROWD COUNTING 24

MULTI-SCALE CONVOLUTIONAL NEURAL NETWORKS FOR CROWD COUNTING

引用

24th IEEE International conference on image processing (ICIP)

作者： Zeng, Lingke Xu, Xiangmin Cai, Bolun Qiu, Suo Zhang, Tong South China Univ Technol Sch Elect & Informat Engn Guangzhou Guangdong Peoples R China

ISBN: (纸本)9781509021758

Crowd counting on static images is a challenging problem due to scale variations. Recently deep neural networks have been shown to be effective in this task. However, existing neural-networks-based methods often use the multi-column or multi-network model to extract the scale-relevant features, which is more complicated for optimization and computation wasting. To this end, we propose a novel multi-scale convolutional neural network (MSCNN) for single image crowd counting. Based on the multi-scale blobs, the network is able to generate scale-relevant features for higher crowd counting performances in a single-column architecture, which is both accuracy and cost effective for practical applications. Complemental results show that our method outperforms the state-of-the-art methods on both accuracy and robustness with far less number of parameters.

关键词： Multi-scale CNN scale-relevant architectures crowd counting

来源：评论

学校读者我要写书评

暂无评论

DISCRIMINATIVE CANONICAL CORRELATION ANALYSIS NETWORK FOR image CLASSIFICATION 24

DISCRIMINATIVE CANONICAL CORRELATION ANALYSIS NETWORK FOR IM...

引用

24th IEEE International conference on image processing (ICIP)

作者： Gatto, Bernardo B. dos Santos, Eulanda M. Univ Fed Amazonas Inst Comp ICOMP Manaus Amazonas Brazil

ISBN: (纸本)9781509021758

Recently, convolutional neural network has attracted an increasing amount of attention in machine learning and computer vision areas, improving the performance of several related applications. Currently, many deep learning network architectures such as principal component analysis network (PCANet), linear discriminant analysis network (LDANet) and canonical correlation analysis network (CCANet) have been proposed for object and face classification. These architecture solutions have demonstrated high efficiency, with a simple implementation, providing a fast prototyping of efficient image classification applications. However, these solutions take advantage of filters that may not extract high discriminative features in more complicated computer vision problems (e.g. containing high degree of overlap between the distributions of the data). To generate more discriminative information, we introduce a discriminative canonical correlation network (DCCNet), that employs filters constructed from discriminative canonical correlations analysis (DCC). Learning filters from DCC ensures that the network will produce discriminative features, generating more representative and discriminative information. We demonstrate the applicability of DCCNet through experiments on four datasets.

关键词： discriminative canonical correlations analysis PCA-based network image classification

来源：评论

学校读者我要写书评

暂无评论

High level design space exploration of RVC codec specifications for multi-core heterogeneous platforms

High level design space exploration of RVC codec specificati...

引用

conference on design and architectures for signal and image processing

作者： Christophe Lucarz Ghislain Roquier Marco Mattavelli Ecole Polytechnique Fédérale de Lausanne Lausanne Switzerland

Nowadays, the design flow of complex signal processing embedded systems starts with a specification of the application by means of a large and sequential program (usually in C/C++). As we are entering in the multicore era, sequential programs are no longer the most appropriate way to specify algorithms targeted to run on several processing units. The new ISO/MPEG Reconfigurable Video Coding (RVC) standard is proposing a new paradigm for specifying and designing complex signal processing systems. The RVC standard enables specifying new codecs by assembling blocks, or so called Functional Units (FUs) from a standard Video Tool Library (VTL). Flexibility, reusability, and modularity are the key features of RVC. This new way of specifying algorithms clearly simplifies the task of designing future video coding applications by allowing software and hardware reuse across multiple video coding standards. Specifications are provided in the form of an actor and dataflow-based language called CAL. Although the RVC standard does not imply any specific implementation design flow, it is an appropriate starting point for targeting multiple processing units platforms. This paper describes a new model-driven design flow which considers both algorithm and architecture to map RVC codec specifications onto heterogeneous and multi-core systems.

关键词： Algorithm design and analysis Processor scheduling Transform coding Software Throughput signal processing algorithms Measurement

来源：评论

学校读者我要写书评

暂无评论

Hardware/software co-design of H.264/AVC encoders for multi-core embedded systems

Hardware/software co-design of H.264/AVC encoders for multi-...

引用

conference on design and architectures for signal and image processing

作者： Tiago Dias Nuno Roma Leonel Sousa INESC-ID Lisbon ISEL-PI Lisbon Technical University of Lisbon IST Lisboa Portugal

This paper presents a multi-core H.264/AVC encoder suitable for implementations in small and medium complexity embedded systems. The proposed structure results from an efficient hardware/software co-design methodology, where the encoder software application is highly optimized and structured in a very modular and efficient manner, so as to allow its most complex and time consuming operations to be offloaded to dedicated hardware accelerators. The considered methodology adopts a simple and efficient core interconnection mechanism to easily allow the inclusion and the removal of such optimized processing cores. Experimental results obtained with the implementation in a Virtex4 FPGA of an H.264/AVC encoder using an ASIP IP core as a ME hardware accelerator have proven the advantages of this methodology. For the considered system, speedup factors greater than 15 were obtained with a very modest increase of the involved hardware resources.

关键词： Hardware Multicore processing Registers Automatic voltage control IP networks Embedded systems

来源：评论

学校读者我要写书评

暂无评论

A new algorithm for realization of FIR filters using multiple constant multiplications

A new algorithm for realization of FIR filters using multipl...

引用

conference on design and architectures for signal and image processing

作者： Mohsen Amiri Farahani Eduardo Castillo-Guerra Bruce G. Colpitts Department of Electrical and Computer engineering University of New Brunswick Canada

This paper presents a new common subexpression elimination (CSE) algorithm to realize FIR filters based on multiple constant multiplications (MCMs). This algorithm shares the maximum number of partial terms amongst minimal signed digit (MSD)-represented coefficients. It modifies the iterated matching (ITM) algorithm to share more partial terms in MCMs, which yields a significant logic and, consequently, chip area savings. The employment of the proposed algorithm results in efficient realizations of FIR filters with a fewer number of adders compared to the conventional CSE algorithms. Experimental results demonstrate a reduction up to 22% in the complexity of FIR filters over some conventional CSE algorithms. The proposed algorithm also addresses challenges encountered in resource-constrained applications, which require banks of high-order filters, such as in real-time distributed optical fiber sensor.

关键词： Adders Finite impulse response filter Algorithm design and analysis Pattern matching Filtering algorithms Optical fiber filters Filtering theory

来源：评论

学校读者我要写书评

暂无评论

SAR image Time Series Analysis in Vegetation Classification Using Global and Local Information Based Linear Discriminant Analysis 25

SAR Image Time Series Analysis in Vegetation Classification ...

引用

25th signal processing and Communications Applications conference (SIU)

作者： Sakarya, Ufuk Demirpolat, Caner TUBITAK UZAY TR-06800 Ankara Turkey

ISBN: (纸本)9781509064946

Vegetation classification using SAR images is one of the research topics in remote sensing. In this paper, SAR image time series analysis in vegetation classification using global and local information based linear discriminant analysis is presented. It is experimentally demonstrated that the use of local pattern information in addition to global pattern information has increased both accuracy and time performance in vegetation classification using time-series TerraSAR-X images.

关键词： linear discriminant analysis SAR image time series dimension reduction

来源：评论

学校读者我要写书评

暂无评论

signal Analysis on the Ball: design of Optimal Basis Functions with Maximal Multiplicative Concentration in Spatial and Spectral Domains 24

Signal Analysis on the Ball: Design of Optimal Basis Functio...

引用

24th International conference on Systems, signals and image processing (IWSSIP)

作者： Nafees, Wajeeha Khalid, Zubair Kennedy, Rodney A. Lahore Univ Management Sci Sch Sci & Engn Lahore Pakistan Australian Natl Univ Res Sch Engn Canberra ACT 2601 Australia

ISBN: (纸本)9781509063444

In this work, we design a set of complete orthonormal optimal basis functions for signals defined on the ball. We design the basis functions by maximizing the product of their energy concentration in some spatial region and that in some spectral region. The optimal basis functions are designed as a linear combination of space-limited functions with maximal concentration in the spectral region and band-limited functions with maximal concentration in the spatial region. The proposed optimal basis functions are shown to form a complete set for signal representation in a subspace formed by the vector sum of the subspaces spanned by space-limited and band-limited functions. We also formulate an integral operator which projects the signal to the joint subspace and maximizes the product of energy concentrations in harmonic and spatial domains. With the help of some properties of proposed optimal basis functions we show that these functions are the only eigenfunctions of the integral operator.

关键词： spatial-spectral concentration localized spectral analysis Slepian concentration problem ball optimal basis energy concentration

来源：评论

学校读者我要写书评

暂无评论

Low-Cost DNN Hardware Accelerator for Wearable, High-Quality Cardiac Arrythmia Detection 31

Low-Cost DNN Hardware Accelerator for Wearable, High-Quality...

引用

31st IEEE International conference on Application-Specific Systems, architectures and Processors (ASAP)

作者： Loh, Johnson Wen, Jianan Gemmeke, Tobias Rhein Westfal TH Aachen Chair Integrated Digital Syst & Circuit Design Aachen Germany

ISBN: (纸本)9781728171470

This work implements a digital signal processing (DSP) accelerator for ECG signal classification. Targeting the integration into wearable devices for 24/7 monitoring, low energy consumption per classification is a key requirement, while maintaining a high classification accuracy at the same time. Co-optimization on algorithm and hardware level led to an architecture consisting mostly of convolution operations in the processing pipeline. The realized discrete wavelet transform and convolutional neural network (CNN) is utilized for continuous time-sequence classification in a sliding-window approach moving away from sample/batch-based processing typical for CNNs. In contrast to previous hardware realizations in this domain, the proposed design was validated using the benchmark dataset from the demanding CinC challenge 2017. The architecture achieves a competitive 0.781 F1-score with only 5597 trainable parameters reducing the computational complexity of state-of-the-art ECG-DNN software solutions by three orders of magnitude. Synthesis in a 22-nm FDSOI-CMOS technology features 0.783 mu J per solution meeting requirements for edge device operation at high-end classification performance.

关键词： electrocardiogram (ECG) classification low energy per solution digital signal processing (DSP) application-specific integrated circuit (ASIC) discrete wavelet transform (DWT) 1D convolutional neural networks (CNN)

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral image Classification with Hybrid Kernel Extreme Learning Machine 25

Hyperspectral Image Classification with Hybrid Kernel Extrem...

引用

25th signal processing and Communications Applications conference (SIU)

作者： Ergul, Ugur Bilgin, Gokhan Yildiz Tekn Univ Bilgisayar Muhendisligi Bolumu TR-34220 Istanbul Turkey

ISBN: (纸本)9781509064946

Extreme learning machine, which has recently lead to gain popularity of single hidden layer feed-forward neural networks, provides a key solution for non-linear problems with least norm and least square solutions at a very low run time. In this work, it is intended to increase the success of hyperspectral image classification with using kernel extreme learning machine. For this purpose, a hybrid kernel is proposed by the convex combination of radial base and polynomial base kernels. In the simulations, Indian Pine hyperspectral image is used and obtained classification results of proposed method are presented with different kernels' results besides results of non-kernel extreme learning machines.

关键词： hyperspectral imaging extreme learning machine hybrid kernels classification

来源：评论

学校读者我要写书评

暂无评论

Parallelization of an ultrasound reconstruction algorithm for non destructive testing on multicore CPU and GPU

Parallelization of an ultrasound reconstruction algorithm fo...

引用

conference on design and architectures for signal and image processing

作者： Antoine Pédron Lionel Lacassagne Franck Bimbard Stéphane Le Berre LIST CEA Gif-sur-Yvette France Institut d'Electronique Fondamentale UMR 8622 Université Paris-Sud 11 Orsay France

The CIVA software platform developed by CEA-LIST offers various simulation and data processing modules dedicated to non-destructive testing (NDT). In particular, ultrasonic imaging and reconstruction tools are proposed, in the purpose of localizing echoes and identifying and sizing the detected defects. Because of the complexity of data processed, computation time is now a limitation for the optimal use of available information. In this article, we present performance results on parallelization of one computationally heavy algorithm on general purpose processors (GPP) and graphic processing units (GPU). GPU implementation makes an intensive use of atomic intrinsics. Compared to initial GPP implementation, optimized GPP implementation runs up to ×116 faster and GPU implementation up to ×631. This shows that, even with irregular workloads, combining software optimization and hardware improvements, GPU give high performance.

关键词： Graphics processing unit Instruction sets image reconstruction Software algorithms Kernel Testing Optimization

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90页 << < 27 28 29 30 31 32 33 34 35 36 > >>

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：