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

2,840 篇 会议
134 篇 期刊文献
75 册 图书

馆藏范围

3,049 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,381 篇 工学
- 1,102 篇 计算机科学与技术...
- 830 篇 软件工程
- 266 篇 电气工程
- 134 篇 光学工程
- 134 篇 电子科学与技术（可...
- 93 篇 机械工程
- 93 篇 控制科学与工程
- 88 篇 信息与通信工程
- 62 篇 生物医学工程（可授...
- 45 篇 仪器科学与技术
- 33 篇 生物工程
- 24 篇 材料科学与工程（可...
- 18 篇 建筑学
- 14 篇 土木工程
- 14 篇 航空宇航科学与技...
- 13 篇 交通运输工程
451 篇 医学
- 438 篇 临床医学
- 44 篇 特种医学
- 25 篇 基础医学(可授医学...
- 19 篇 药学(可授医学、理...
368 篇 理学
- 192 篇 数学
- 176 篇 物理学
- 40 篇 生物学
- 24 篇 系统科学
- 23 篇 统计学（可授理学、...
- 19 篇 化学
- 12 篇 地球物理学
65 篇 管理学
- 35 篇 图书情报与档案管...
- 31 篇 管理科学与工程(可...
20 篇 农学
- 13 篇 作物学
11 篇 教育学
7 篇 法学
4 篇 经济学
3 篇 艺术学
2 篇 文学
2 篇 历史学
2 篇 军事学

主题

429 篇 computer graphic...
372 篇 image segmentati...
367 篇 rendering (compu...
367 篇 image processing
244 篇 image reconstruc...
223 篇 graphics process...
195 篇 feature extracti...
183 篇 image color anal...
176 篇 cameras
174 篇 visualization
167 篇 shape
166 篇 graphics process...
164 篇 computer archite...
164 篇 computer vision
157 篇 image analysis
150 篇 layout
141 篇 graphics
139 篇 pixel
124 篇 hardware
123 篇 application soft...

机构

17 篇 lawrence berkele...
17 篇 nasa ames resear...
17 篇 desert research ...
16 篇 universidade de ...
15 篇 universidade fed...
12 篇 univ estadual ca...
10 篇 institute of com...
9 篇 univ fed minas g...
9 篇 department of co...
9 篇 univ fed rio gra...
8 篇 instituto de inf...
8 篇 univ sao paulo i...
7 篇 impa rio de jane...
7 篇 institute of com...
7 篇 department of co...
6 篇 departamento de ...
6 篇 universidade est...
5 篇 department of co...
5 篇 inst for image p...
5 篇 univ sao paulo i...

作者

25 篇 l. velho
18 篇 velho luiz
17 篇 bahram parvin
17 篇 luiz velho
17 篇 darko koracin
17 篇 wu shin-ting
17 篇 george bebis
17 篇 richard boyle
14 篇 falcao alexandre...
13 篇 waldemar celes
12 篇 r. de alencar lo...
12 篇 william robson s...
12 篇 thomas lewiner
11 篇 aldo von wangenh...
11 篇 menotti david
11 篇 velho l
11 篇 n.d.a. mascarenh...
11 篇 luis gustavo non...
11 篇 silvio jamil f. ...
11 篇 von wangenheim a...

语言

3,019 篇 英文
13 篇 葡萄牙文
12 篇 其他
3 篇 中文
1 篇 西班牙文
1 篇 土耳其文

检索条件"任意字段=Brazilian Symposium on Computer Graphics and Image Processing"

共 3049 条记录，以下是321-330 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：

Exploration of System Configuration in Effective Training of CNNs on GPGPUs

Exploration of System Configuration in Effective Training of...

引用

IEEE International Conference on Consumer Electronics (ICCE)

作者： Zhang, Li Cheng, Xianwei Zhao, Hui Mohanty, Saraju P. Fang, Juan Univ North Texas Comp Sci & Engn Dept Denton TX 76203 USA Beijing Univ Technol Fac Informat Technol Beijing Peoples R China

ISBN: (纸本)9781538679104

Convolutional Neural Networks (CNNs) have shown a great potential in different application domains including object detection, image classification, natural language processing, and speech recognition. Since the depth of the neural network architectures keep growing and the requirement of the large-scale dataset, to design a high-performance computing hardware for training CNNs is very necessary. In this paper, we measure the performance of different configuration on GPU platform and learning the patterns through training two CNNs architectures, LeNet and MiniNet, both perform the image classification. Observe the results of measurements, we indicate the correlation between LAD cache and the performance of GPUs during the training process. Also, we demonstrate that L2D cache slightly influences the performance. The network traffic intensity with both CNN models shows that each layer has distinct patterns of traffic intensity.

关键词： Training computer architecture Backpropagation graphics processing units Deep learning Mesh networks image classification

来源：评论

学校读者我要写书评

暂无评论

A study on tooth segmentation and numbering using end-to-end deep neural networks

A study on tooth segmentation and numbering using end-to-end...

引用

brazilian symposium on computer graphics and image processing (SIBGRAPI)

作者： Bernardo Silva Laís Pinheiro Luciano Oliveira Matheus Pithon Intelligent Vision Research Lab Universidade Federal da Bahia Salvador Bahia Universidade Estadual do Sudoeste da Bahia Jequié Bahia

ISBN: (数字)9781728192741

ISBN: (纸本)9781728192758

Shape, number, and position of teeth are the main targets of a dentist when screening for patient's problems on X-rays. Rather than solely relying on the trained eyes of the dentists, computational tools have been proposed to aid specialists as decision supporter for better diagnoses. When applied to X-rays, these tools are specially grounded on object segmentation and detection. In fact, the very first goal of segmenting and detecting the teeth in the images is to facilitate other automatic methods in further processing steps. Although researches over tooth segmentation and detection are not recent, the application of deep learning techniques in the field is new and has not reached maturity yet. To fill some gaps in the area of dental image analysis, we bring a thorough study on tooth segmentation and numbering on panoramic X-ray images by means of end-to-end deep neural networks. For that, we analyze the performance of four network architectures, namely, Mask R-CNN, PANet, HTC, and ResNeSt, over a challenging data set. The choice of these networks was made upon their high performance over other data sets for instance segmentation and detection. To the best of our knowledge, this is the first study on instance segmentation, detection, and numbering of teeth on panoramic dental X-rays. We found that (i) it is completely feasible to detect, to segment, and to number teeth by through any of the analyzed architectures, (ii) performance can be significantly boosted with the proper choice of neural network architecture, and (iii) the PANet had the best results on our evaluations with an mAP of 71.3% on segmentation and 74.0% on numbering, raising 4.9 and 3.5 percentage points the results obtained with Mask R-CNN.

关键词： Teeth Dentistry image segmentation X-rays Neural networks Detectors Deep learning

来源：评论

学校读者我要写书评

暂无评论

A lightweight 2D Pose Machine with attention enhancement

A lightweight 2D Pose Machine with attention enhancement

引用

brazilian symposium on computer graphics and image processing (SIBGRAPI)

作者： Luiz Schirmer Djalma Lúcio Alberto Raposo Luiz Velho Hélio Lopes PUC-Rio-Pontifícia Universidade Católica do Rio de Janeiro Brazil IMPA-Instituto Nacional de Matemática Pura e Aplicada Brazil

ISBN: (数字)9781728192741

ISBN: (纸本)9781728192758

Pose estimation is a challenging task in computer vision that has many applications, as for example: in motion capture, in medical analysis, in human posture monitoring, and in robotics. In other words, it is a main tool to enable machines do understand human patterns in videos or images. Performing this task in real-time while maintaining accuracy and precision is critical for many of these applications. Several papers propose real time approaches considering deep neural networks for pose estimation. However, in most cases they fail when considering run-time performance or do not achieve the precision needed. In this work, we propose a new model for real-time pose estimation considering attention modules for convolutional neural networks (CNNs). We introduce a two-dimensional relative attention mechanism for feature extraction in pose machines leading to improvements in accuracy. We create a single shot architecture where both operations to infer key points and part affinity fields share the information. Also, for each stage, we use tensor decompositions to not only reduce dimensionality, but also to improve performance. This allows us to factorize each convolution and drastically reduce the number of parameters in our network. Our experiments show that, with this factorized approach, it is possible to achieve state-of-art performance in terms of run-time while we have a small reduction in accuracy.

关键词： Tensors Pose estimation computer architecture Task analysis Neural networks Mathematical model Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Face Recognition Using LBP on an image Transformation Based on Complex Network Degrees

Face Recognition Using LBP on an Image Transformation Based ...

引用

brazilian symposium on computer graphics and image processing (SIBGRAPI)

作者： Murilo Villas Boas da Costa Cynthia Martins Villar Couto Leandro Nogueira Couto Uberlandia Federal University Sao Paulo University

The following topics are dealt with: image segmentation; learning (artificial intelligence); convolutional neural nets; medical image processing; data visualisation; image classification; feature extraction; object de... 详细信息

关键词： Complex networks Face recognition image edge detection Histograms Microsoft Windows computer vision Gray-scale

来源：评论

学校读者我要写书评

暂无评论

A Practical Review on Medical image Registration: from Rigid to Deep Learning based Approaches 31

A Practical Review on Medical Image Registration: from Rigid...

引用

31st Conference on graphics, Patterns and images (SIBGRAPI)

作者： Andrade, Natan Faria, Fabio A. Cappabianco, Fabio A. M. Univ Fed Sao Paulo GIBIS Inst Ciencia & Tecnol Sao Jose Dos Campos SP Brazil

ISBN: (纸本)9781538692646

The large variety of medical image modalities (e.g. Computed Tomography, Magnetic Resonance Imaging, and Positron Emission Tomography) acquired from the same body region of a patient together with recent advances in computer architectures with faster and larger CPUs and GPUs allows a new, exciting, and unexplored world for image registration area. A precise and accurate registration of images makes possible understanding the etiology of diseases, improving surgery planning and execution, detecting otherwise unnoticed health problem signals, and mapping functionalities of the brain. The goal of this paper is to present a review of the state-of-the-art in medical image registration starting from the preprocessing steps, covering the most popular methodologies of the literature and finish with the more recent advances and perspectives from the application of Deep Learning architectures.

关键词： image Registration Medical Imaging Deep Learning

来源：评论

学校读者我要写书评

暂无评论

Vehicle Detection and Classification in Traffic images Using ConvNets With Constrained Resources 26

Vehicle Detection and Classification in Traffic Images Using...

引用

26th International Conference on Systems, Signals and image processing (IWSSIP)

作者： Roecker, Max N. Costa, Yandre M. G. Britto, Alceu S., Jr. Oliveira, Luiz E. S. Bertolini, Diego Univ Estadual Maringa Maringa Parana Brazil Pontificia Univ Catolica Parana Curitiba Parana Brazil Univ Fed Parana Curitiba Parana Brazil Fed Technol Univ Parana Curitiba Parana Brazil

ISBN: (纸本)9781728132273

This paper proposes a convolutional neural network model for detection and classification of vehicles present in digital images into six categories, namely Bus, Microbus, Minivan, Sedan, SUV, and Truck. Experimental results with the BIT-Vehicle Dataset report a mean average precision (mAP) of 92.40% and the average intersection over a union (IoU) of 81.26% with the average inference latency under 70 milliseconds in an environment equipped with a graphics processing unit. We conclude that the model is discriminative and capable of generalizing the patterns of the vehicle type classification task while not requiring expensive computational resources. These features suggest that the model can be useful in the development of embedded intelligent traffic systems improving accuracy and decision latency.

关键词： computer vision convolutional neural networks machine learning vehicle classification vehicle detection

来源：评论

学校读者我要写书评

暂无评论

Restoration of images Affected by Welding Fume 31

Restoration of Images Affected by Welding Fume

引用

31st Conference on graphics, Patterns and images (SIBGRAPI)

作者： Vaz-, Edwilson, Jr. Drews-, Paulo, Jr. Steffens, Cristiano Fed Univ Rio Grande Ctr Computat Sci C3 Rio Grande Brazil

ISBN: (纸本)9781538692646

Machine vision performs an important role in many applications, including robotics. Combined with classical instrumentation, welding robots can use a camera to perceive the scene and take a decision. A camera attached to the robot body and machine vision system work as the eyes of the robot during the welding process. However, image-based systems are susceptible to the interference of fumes, sparks, dust, and artifacts generated as a side effect of the welding process. Fume can adhere to the lenses and degrades the image, introducing a negative impact on the processing pipeline. This paper proposes a novel image fusion based algorithm that minimizes the effects caused by the fume adhered to the camera lens. Results show the proposed method is able to enhance the overall image quality, outperforming classical alternatives for similar problems.

关键词： Welding Cameras Lenses Robot vision systems Glass image fusion

来源：评论

学校读者我要写书评

暂无评论

Real-time image Aesthetic Score Prediction for Portable Devices

Real-time Image Aesthetic Score Prediction for Portable Devi...

引用

Midwest symposium on Circuits and Systems (MWSCAS)

作者： Prashanth Venkataswamy M. Omair Ahmad M.N.S Swamy Department of Electrical and Computer Engineering Concordia University Montreal Canada

ISBN: (数字)9781728180588

ISBN: (纸本)9781728180595

With rapid advancements in technology, in recent times we have witnessed tremendous strides taken in camera and imaging sciences. Digital processing has also added to exceptional details in photography. The advancements in imaging have created a gap between capturing a moment centered around aesthetics and random captures without meaning. In this work, we aim to provide to users an insightful feedback on the aesthetics of the images captured. The feedback concentrates on the rule of thirds, high dynamic range, color, content and various quality aspects for each image captured. To achieve this, we propose a hierarchical real time image aesthetic score prediction technique. We use a modified YOLO-CNN and Mobilenet for object detection and style prediction, followed by a multi-threaded aesthetic predictor to analyze and score the images on portable devices.

关键词： Real-time systems Visualization graphics processing units Feature extraction image color analysis Object detection Hardware

来源：评论

学校读者我要写书评

暂无评论

InteractionGAN: image-Level Interaction using Generative Adversarial Networks 18

InteractionGAN: Image-Level Interaction using Generative Adv...

引用

International Normal Labour and Birth Research Conference

作者： Son, Minjung Chang, Hyun Sung Samsung Adv Inst Technol Suwon South Korea

ISBN: (纸本)9781728147659

We present a novel strategy for image-level interaction that is applicable to a single image without any prior structural knowledge, such as object status or reconstructed 3D models. By training sets of input image and interaction pairs using a target image, our model can generate result images by applying the desired interaction to new unseen images. The proposed method is differentiated from previous approaches for changing poses, which requires absolute statuses for training images or estimated 3D model with reconstruction errors. Based on the conceptual analysis of encoder-decoder networks, we propose a novel generator network architecture containing a feature converter network, which is suitable for applying interactions to images. We also implement a discriminator network for training, which is a well-known technique for generative adversarial networks. Experimental results demonstrate that the proposed method successfully generates result images with applied interactions without any prior knowledge. We expect that our method will provide insights into novel interaction schemes for augmented reality by reflecting interactions onto real scenes and providing more realistic user experiences.

关键词： Human-centered computing Interaction paradigms Mixed / augmented reality Computing methodologies computer vision computer vision representations image representations Computing methodologies computer graphics image manipulation image processing

来源：评论

学校读者我要写书评

暂无评论

GuidedNet: Single image Dehazing Using an End-to-end Convolutional Neural Network 31

GuidedNet: Single Image Dehazing Using an End-to-end Convolu...

引用

31st Conference on graphics, Patterns and images (SIBGRAPI)

作者： Goncalves, Lucas T. Gaya, Joel O. Drews-, Paulo, Jr. Botelho, Silvia S. C. Univ Fed Rio Grande FURG Ctr Computat Sci C3 Intelligent Robot & Automat Grp NAUTEC Rio Grande Brazil

ISBN: (纸本)9781538692646

Poor visibility is a common problem when capturing images in participating mediums such as mist or water. The problem of generating a haze-free image based on a hazy one can be described as image dehazing. Previous approaches dealt with this problem using physical models based on priors and simplifications. In this paper, we demonstrate that an end-to-end convolutional neural network is able to learn the dehazing process with no parameters or priors required, resulting in a more generic method. Even though our model is trained entirely with hazy indoor images, we are able to fully restore outdoor images with real haze. Also, we propose an architecture containing the novel Guided Layers, introduced in order to reduce the loss of spatial information while restoring the images. Our method outperforms other machine learning based models, yielding superior results both qualitatively and quantitatively.

关键词： Atmospheric modeling Neural networks image restoration Training Scattering Degradation Network architecture

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305页 << < 29 30 31 32 33 34 35 36 37 38 > >>

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：