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
135 篇 期刊文献
75 册 图书

馆藏范围

3,050 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,382 篇 工学
- 1,103 篇 计算机科学与技术...
- 831 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

431 篇 computer graphic...
372 篇 image segmentati...
368 篇 image processing
367 篇 rendering (compu...
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...
165 篇 computer vision
164 篇 computer archite...
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

3,016 篇 英文
16 篇 其他
13 篇 葡萄牙文
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 3050 条记录，以下是391-400 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 Effective Is Super-Resolution to Improve Dense Labelling of Coarse Resolution imagery?

How Effective Is Super-Resolution to Improve Dense Labelling...

引用

brazilian symposium on computer graphics and image processing (SIBGRAPI)

作者： Matheus B. Pereira Jefersson A. dos Santos Department of Computer Science Universidade Federal de Minas Gerais Brazil Belo Horizonte Minas Gerais

Coarse resolution remote sensing images, such as LANDSAT and MODIS are easily found in public open repositories and, therefore, are widely used in many studies. But their use for automatic creation of thematic maps is very restrict since most of the deep-based semantic segmentation (a.k.a dense labelling) approaches are only suitable for subdecimeter data. In this paper, we design a straightforward framework in order to evaluate the effectiveness of deep-based super-resolution in the semantic segmentation of low-resolution remote sensing images. We carried out an extensive set of experiments on three remote sensing datasets with distinct nature/properties. The results show that super-resolution is effective to improve semantic segmentation performance on low-resolution aerial imagery. It not only outperforms unsupervised interpolation but also achieves semantic segmentation results comparable to high-resolution data.

关键词： image segmentation Semantics Remote sensing Task analysis Satellites Spatial resolution

来源：评论

学校读者我要写书评

暂无评论

Screen partitioning load balancing for parallel rendering on a multi-GPU multi-displayworkstation

Screen partitioning load balancing for parallel rendering on...

引用

19th Eurographics symposium on Parallel graphics and Visualization, EGPGV 2019

作者： Dong, Yangzi Peng, Chao Computer Science Department The University of Alabama Huntsville United States

ISBN: (纸本)9783038680796

Commodity workstations with multiple GPUs have been built by engineers and scientists for real-time rendering applications. As a result, a high display resolution can be achieved by connecting each GPU to a display monitor (resulting in a tiled large display). Using a multi-GPU workstation may not always produce a highly interactive rendering rate due to imbalanced rendering workloads among GPUs. In this work, we propose a parallel load balancing algorithm based on a screen partitioning strategy to dynamically balance the amount of vertices and triangles rendered by each GPU. Each GPU renders a screen region whose size may be different from the screen regions of other GPUs, but the amounts of vertices and triangles in those screen regions are balanced. It is possible that a screen region rendered by a GPU has to be displayed by another GPU. We propose a frame exchanging algorithm that allows GPUs to exchange screen regions efficiently. The inter-GPU communication overhead is very small since the data transferred between GPUs are a small amount of image pixels. © 2019 Eurographics Association. All rights reserved.

关键词： graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

CV-C3D: Action Recognition on Compressed Videos with Convolutional 3D Networks

CV-C3D: Action Recognition on Compressed Videos with Convolu...

引用

brazilian symposium on computer graphics and image processing (SIBGRAPI)

作者： Samuel Felipe dos Santos Nicu Sebe Jurandy Almeida Instituto de Ciência e Tecnologia Universidade Federal de São Paulo - UNIFESP São José dos Campos SP Brazil Dept. of Information Engineering and Computer Science University of Trento - UniTn Trento TN Italy

Action recognition in videos has gained substantial attention from the computer vision community due to the wide range of possible applications. Recent works have addressed this problem with deep learning methods. The main limitation of existing approaches is their difficulty to learn temporal dynamics due to the high computational load demanded for processing huge amounts of data required to train a model. To overcome this problem, we propose a Compressed Video Convolutional 3D network (CV-C3D). It exploits information from the compressed representation of a video in order to avoid the high computational cost for fully decoding the video stream. The speed up of the computation enables our network to use 3D convolutions for capturing the temporal context efficiently. Our network has the lowest computational complexity among all the compared approaches. Results of our approach in the task of action recognition on two public benchmarks, UCF-101 and HMDB-51, were comparable to the baselines, with the advantage of running at faster inference speed.

关键词： Videos Three-dimensional displays Machine learning Computational modeling image coding Decoding Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Low-Dose CT Dental image Denoising by Morphological Operators and 3D Filtering

Low-Dose CT Dental Image Denoising by Morphological Operator...

引用

brazilian symposium on computer graphics and image processing (SIBGRAPI)

作者： Romulo Marconato Stringhini Daniel Welfer Marcos Cordeiro d'Ornellas Daniel Fernando Tello Gamarra Federal University of Santa Maria Santa Maria Brazil Department of Applied Computing Federal University of Santa Maria Santa Maria Brazil

The impact in reducing the radiation dose in computed tomography (CT) exams is directly related to the quality of the images obtained in these exams. Such images are degraded by undesirable artifacts, known as noise. In order to improve the quality of these images and provide an accurate medical diagnosis, it is necessary to apply noise reduction techniques. In this study, a method based on structural segmentation and filtering through morphological operators along with a BM3D filtering is proposed to reduce noise and preserve details in low-dose CT dental images. Experimental results of the proposed method were compared with several existing methods and validated using the PSNR, SSIM, MSE and EPI metrics. Our method demonstrated superior performance among the evaluated filters. In comparison to the filter that obtained the best results, our method had a gain of 12.46% on PSNR, 11.11% on SSIM, 14.5% on MSE and 9.63% on EPI metrics.

关键词： Noise measurement Three-dimensional displays Computed tomography Noise reduction image segmentation image edge detection image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Skeleton image Representation for 3D Action Recognition Based on Tree Structure and Reference Joints

Skeleton Image Representation for 3D Action Recognition Base...

引用

brazilian symposium on computer graphics and image processing (SIBGRAPI)

作者： Carlos Caetano François Brémond William Robson Schwartz Department of Computer Science Universidade Federal de Minas Gerais Belo Horizonte Brazil INRIA Valbonne France

In the last years, the computer vision research community has studied on how to model temporal dynamics in videos to employ 3D human action recognition. To that end, two main baseline approaches have been researched: (i) Recurrent Neural Networks (RNNs) with Long-Short Term Memory (LSTM); and (ii) skeleton image representations used as input to a Convolutional Neural Network (CNN). Although RNN approaches present excellent results, such methods lack the ability to efficiently learn the spatial relations between the skeleton joints. On the other hand, the representations used to feed CNN approaches present the advantage of having the natural ability of learning structural information from 2D arrays (i.e., they learn spatial relations from the skeleton joints). To further improve such representations, we introduce the Tree Structure Reference Joints image (TSRJI), a novel skeleton image representation to be used as input to CNNs. The proposed representation has the advantage of combining the use of reference joints and a tree structure skeleton. While the former incorporates different spatial relationships between the joints, the latter preserves important spatial relations by traversing a skeleton tree with a depth-first order algorithm. Experimental results demonstrate the effectiveness of the proposed representation for 3D action recognition on two datasets achieving state-of-the-art results on the recent NTU RGB+D 120 dataset.

关键词： Skeleton image representation Three-dimensional displays Hidden Markov models image recognition Videos Neural networks

来源：评论

学校读者我要写书评

暂无评论

Optimizing Super Resolution for Face Recognition

Optimizing Super Resolution for Face Recognition

引用

brazilian symposium on computer graphics and image processing (SIBGRAPI)

作者： Antonio Augusto Abello R. Hirata Instituto de Matemática e Estatística Universidade de São Paulo São Paulo Brazil

Face Super-Resolution is a subset of Super Resolution (SR) that aims to retrieve a high-resolution (HR) image of a face from a lower resolution input. Recently, Deep Learning (DL) methods have improved drastically the quality of SR generated images. However, these qualitative improvements are not always followed by quantitative improvements in the traditional metrics of the area, namely PSNR (Peak Signal-to-Noise Ratio) and SSIM (Structural Similarity Index). In some cases, models that perform better in opinion scores and qualitative evaluation have worse performance in these metrics, indicating they are not sufficiently informative. To address this issue we propose a task-based evaluation procedure based on the comparative performance of face recognition algorithms on HR and SR images to evaluate how well the models retrieve high-frequency and identity defining information. Furthermore, as our face recognition model is differentiable, this leads to a novel loss function that can be optimized to improve performance in these tasks. We successfully apply our evaluation method to validate this training method, yielding promising results.

关键词： image resolution Face Task analysis Face recognition Training Measurement Signal resolution

来源：评论

学校读者我要写书评

暂无评论

The Effects of Augmented Training Dataset on Performance of Convolutional Neural Networks in Face Recognition System

The Effects of Augmented Training Dataset on Performance of ...

引用

Federated Conference on computer Science and Information Systems (FedCSIS)

作者： Kutlugun, Mehmet Ali Sirin, Yahya Karakaya, Mehmet Ali Istanbul Sabahattin Zaim Univ Comp Sci & Engn Istanbul Turkey Anadolu Univ Management Informat Syst Eskisehir Turkey

ISBN: (纸本)9788395235788

Now adays, deep learning methods have been used in many areas such as big data analysis, speech and image processing with the increasing processing power and the development of graphics processors. In particular, face recognition systems have become one of the most important research topics in biometry. Light direction, reflection, emotional and physical changes in facial expression arc the main factors in face recognition systems that make recognition difficult. Training of the system with the available data in small data sets is an important factor that negatively affects the performance. The Convolutional Neural Network (CNN) model is a deep learning architecture used for large amounts of training data. In this study, a small number of employee images set of a small-scale company has been increased by applying different filters. In addition, it has been tried to determine which data augmentation options have more effect on face recognition. Thus, non-real-time face recognition has been performed by training with new augmented dataset of each picture with many features.

关键词： deep learning convolutional neural networks image processing face recognition data augmentation

来源：评论

学校读者我要写书评

暂无评论

The Importance of Object-Based Seed Sampling for Superpixel Segmentation

The Importance of Object-Based Seed Sampling for Superpixel ...

引用

brazilian symposium on computer graphics and image processing (SIBGRAPI)

作者： Felipe Belém Leonardo Melo Silvio Guimarães Alexandre Falcão University of Campinas Campinas Brazil University of Campinas Campinas SP Brazil Pontifical Catholic University of Minas Gerais Belo Horizonte Brazil

Superpixel segmentation can be defined as an image partition into connected regions, such that image objects may be represented by the union of their superpixels. In this context, multiple iterations of superpixel segmentation from improved seed sets is a strategy exploited by several algorithms. The Iterative Spanning Forest (ISF) framework divides this strategy into three independent components: a seed sampling method, a superpixel delineation algorithm based on strength of connectedness between seeds and pixels, and a seed recomputation procedure. A recent work shows that object information can be added to each component of ISF such that the user can control the number of seeds inside the objects and so improve superpixel segmentation. However, it is uncertain how the added information impacts each component of the pipeline. Therefore, in this work, a study is conducted to evaluate such inclusion in the seed sampling procedure, partially elucidating its benefits. Additionally, we introduce a novel object-based sampling approach, named Object Saliency Map sampling by Ordered Extraction (OSMOX), and demonstrate the results for supervised and unsupervised object information. The experiments show considerable improvements in under-segmentation error, specially with a low number of superpixels.

关键词： image segmentation Forestry Pipelines Estimation Vegetation Partitioning algorithms Nickel

来源：评论

学校读者我要写书评

暂无评论

Acquisition of Digital images and Identification of Aedes Aegypti Mosquito Eggs using Classification and Deep Learning

Acquisition of Digital Images and Identification of Aedes Ae...

引用

brazilian symposium on computer graphics and image processing (SIBGRAPI)

作者： Pedro Saint Clair Garcia Rafael Martins George Luiz Lins Machado Coelho Guillermo Cámara-Chávez Computer Science Department Campus Universitário Morro do Cruzeiro Ouro Preto MG Brazil Biology Department Federal Campus Universitário Morro do Cruzeiro Ouro Preto MG Brazil Federal University of Ouro Preto Ouro Preto Brazil

The mosquito Aedes aegypti can transmit some diseases, which makes the study of the proliferation of this vector a necessary task. With the use of traps made in the laboratory, called ovitraps, it is possible to map egg deposition in a community. Through a camera, coupled with a magnifying glass, are acquired images containing the elements (eggs) to be counted. First, the goal is to find pixels with a similar color to mosquito eggs; for that, we take advantage of the slice color method. From these already worked images, a process of transfer learning with a convolutional neural network (CNN) is carried out. The intention is to separate which elements are eggs from the others. In 10% of the test images, the count performed by the model, and the ground truth of the number of eggs was considered weakly correlated. This problem occurs in images that have a high density of eggs or appear black elements that resemble mosquito eggs, but they are not. For the remaining 90% of the test images, the counting was considered to be perfectly correlated.

关键词： image color analysis Diseases Cameras image segmentation Databases Glass Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Sparse Tensor Core: Algorithm and Hardware Co-Design for Vector-wise Sparse Neural Networks on Modern GPUs 52

Sparse Tensor Core: Algorithm and Hardware Co-Design for Vec...

引用

52nd Annual IEEE/ACM International symposium on Microarchitecture (MICRO)

作者： Zhu, Maohua Zhang, Tao Gu, Zhenyu Xie, Yuan Univ Calif Santa Barbara Santa Barbara CA 93106 USA Alibaba DAMO Acad Beijing Peoples R China

ISBN: (纸本)9781450369381

Deep neural networks have become the compelling solution for the applications such as image classification, object detection, speech recognition, and machine translation. However, the great success comes at the cost of excessive computation due to the over-provisioned parameter space. To improve the computation efficiency of neural networks, many pruning techniques have been proposed to reduce the amount of multiply-accumulate (MAC) operations, which results in high sparsity in the networks. Unfortunately, the sparse neural networks often run slower than their dense counterparts on modern GPUs due to their poor device utilization rate. In particular, as the sophisticated hardware primitives (e.g., Tensor Core) have been deployed to boost the performance of dense matrix multiplication by an order of magnitude, the performance of sparse neural networks lags behind significantly. In this work, we propose an algorithm and hardware co-design methodology to accelerate the sparse neural networks. A novel pruning algorithm is devised to improve the workload balance and reduce the decoding overhead of the sparse neural networks. Meanwhile, new instructions and micro-architecture optimization are proposed in Tensor Core to adapt to the structurally sparse neural networks. Our experimental results show that the pruning algorithm can achieve 63% performance gain with model accuracy sustained. Furthermore, the hardware optimization gives an additional 58% performance gain with negligible area overhead.

关键词： neural networks graphics processing units pruning

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 << < 36 37 38 39 40 41 42 43 44 45 > >>

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：