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

195 篇 会议
17 篇 期刊文献
2 册 图书

馆藏范围

214 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

140 篇 工学
- 124 篇 计算机科学与技术...
- 68 篇 软件工程
- 20 篇 电气工程
- 9 篇 信息与通信工程
- 7 篇 生物医学工程（可授...
- 6 篇 光学工程
- 5 篇 机械工程
- 5 篇 控制科学与工程
- 4 篇 生物工程
- 3 篇 电子科学与技术（可...
- 2 篇 交通运输工程
- 1 篇 仪器科学与技术
- 1 篇 材料科学与工程（可...
- 1 篇 化学工程与技术
62 篇 医学
- 58 篇 临床医学
- 5 篇 特种医学
20 篇 理学
- 8 篇 数学
- 6 篇 物理学
- 6 篇 生物学
- 2 篇 化学
- 2 篇 统计学（可授理学、...
- 1 篇 天文学
- 1 篇 大气科学
- 1 篇 地球物理学
- 1 篇 系统科学
11 篇 管理学
- 10 篇 管理科学与工程(可...
- 5 篇 工商管理
- 4 篇 图书情报与档案管...
2 篇 法学
- 2 篇 社会学
1 篇 教育学
- 1 篇 教育学

主题

31 篇 feature extracti...
25 篇 image color anal...
23 篇 training
21 篇 image segmentati...
16 篇 image processing
15 篇 task analysis
15 篇 visualization
13 篇 computer archite...
13 篇 cameras
11 篇 computer graphic...
9 篇 rendering (compu...
9 篇 databases
9 篇 computer vision
8 篇 digital image pr...
7 篇 deep learning
7 篇 real-time system...
7 篇 image recognitio...
7 篇 image reconstruc...
6 篇 support vector m...
6 篇 lighting

机构

4 篇 department of co...
2 篇 univ tecnol fed ...
2 篇 univ fed minas g...
2 篇 univ sao paulo i...
2 篇 faculty of elect...
2 篇 univ sao paulo i...
2 篇 college of compu...
2 篇 univ estadual ca...
2 篇 college of mathe...
2 篇 inst matematica ...
2 篇 univ fed minas g...
2 篇 instituto de mat...
2 篇 universidade fed...
2 篇 universidade de ...
2 篇 univ sao paulo i...
2 篇 college of compu...
1 篇 computaçáo brasi...
1 篇 laboratory of vi...
1 篇 hunan university...
1 篇 at&t research

作者

5 篇 wu st
3 篇 eler danilo m.
3 篇 alexandre xavier...
3 篇 nakazaki marcel ...
3 篇 menotti david
3 篇 laroca rayson
3 篇 santos davi p.
3 篇 ponti moacir a.
3 篇 david menotti
3 篇 william robson s...
3 篇 paulovich fernan...
3 篇 minghim rosane
3 篇 rayson laroca
2 篇 britto alceu s. ...
2 篇 flores franklin ...
2 篇 moacir antonelli...
2 篇 paulo ivson
2 篇 guillermo camara...
2 篇 meyer fernand
2 篇 schwartz william...

语言

212 篇 英文
1 篇 葡萄牙文
1 篇 中文

检索条件"任意字段=21st Brazilian Symposium on Computer Graphics and Image Processing"

共 214 条记录，以下是171-180 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：

Visualization and Analysis of Parallel Dataflow Execution with Smart Traces

Visualization and Analysis of Parallel Dataflow Execution wi...

引用

brazilian symposium on computer graphics and image processing (SIBGRAPI)

作者： Daniel K. Osmari Huy T. Vo Cláudio T. Silva João L. D. Comba Lauro Lins Polytechnic School of Engineering New York University UFRGS Instituto de Informática AT&T Research

ISBN: (纸本)9781479942572

Most performance analysis tools focus on presenting an overload of details, with little application-dependent structure, and predefined statistical summaries. This makes the complex relations present in a parallel program not directly recognisable to the user, making the task of identifying performance issues more costly in both time and effort. In this work we investigate the requirements to create visualisations of execution traces of parallel programs modelled as dataflows. We propose the Smart Trace (st) concept, to encode the structure of the data, and guide the construction of specialised visualizations. A visualization tool can then leverage the relationships in the data to automate a given analysis task. We show with examples the power and flexibility of visualisations we can create to address specific questions formulated about the analysis of the data, with emphasis in parallel dataflow traces.

关键词： Data visualization Pipelines Instruments graphics processing units Ports (computers) image color analysis Data models

来源：评论

学校读者我要写书评

暂无评论

image-Based Visualization of Classifier Decision Boundaries

Image-Based Visualization of Classifier Decision Boundaries

引用

brazilian symposium on computer graphics and image processing (SIBGRAPI)

作者： Francisco Caio M. Rodrigues Roberto Hirata Alexandru Cristian Telea Institue of Mathematics and Statistics University of São Paulo Johann Bernoulli Institute University of Groningen

Understanding how a classifier partitions a high-dimensional input space and assigns labels to the parts is an important task in machine learning. Current methods for this task mainly use color-coded sample scatterplots, which do not explicitly show the actual decision boundaries or confusion zones. We propose an image-based technique to improve such visualizations. The method samples the 2D space of a dimensionality-reduction projection and color-code relevant classifier outputs, such as the majority class label, the confusion, and the sample density, to render a dense depiction of the high-dimensional decision boundaries. Our technique is simple to implement, handles any classifier, and has only two simple-to-control free parameters. We demonstrate our proposal on several real-world high-dimensional datasets, classifiers, and two different dimensionality reduction methods.

关键词： Two dimensional displays Visualization Training Dimensionality reduction Color Brightness Task analysis

来源：评论

学校读者我要写书评

暂无评论

RISF: Recursive Iterative Spanning Forest for Superpixel Segmentation

RISF: Recursive Iterative Spanning Forest for Superpixel Seg...

引用

brazilian symposium on computer graphics and image processing (SIBGRAPI)

作者： Felipe Lemes Galvão Alexandre Xavier Falcão Ananda Shankar Chowdhury Institute of Computing University of Campinas Campinas SP Brazil Dept. of Electronics and Telecommunication Engineering Jadavpur University Kolkata India

Methods for superpixel segmentation have become very popular in computer vision. Recently, a graph-based framework named ISF (Iterative Spanning Forest) was proposed to obtain connected superpixels (supervoxels in 3D) based on multiple executions of the image Foresting Transform (IFT) algorithm from a given choice of four components: a seed sampling strategy, an adjacency relation, a connectivity function, and a seed recomputation procedure. In this paper, we extend ISF to introduce a unique characteristic among superpixel segmentation methods. Using the new framework, termed as Recursive Iterative Spanning Forest (RISF), one can recursively generate multiple segmentation scales on region adjacency graphs (i.e., a hierarchy of superpixels) without sacrificing the efficiency and effectiveness of ISF. In addition to a hierarchical segmentation, RISF allows a more effective geodesic seed sampling strategy, with no negative impact in the efficiency of the method. For a fixed number of scales using 2D and 3D image datasets, we show that RISF can consistently outperform the most competitive ISF-based methods.

关键词： Forestry image segmentation Vegetation image color analysis Three-dimensional displays Transforms Two dimensional displays

来源：评论

学校读者我要写书评

暂无评论

image-Based state Recognition for Disconnect Switches in Electric Power Distribution Substations

Image-Based State Recognition for Disconnect Switches in Ele...

引用

brazilian symposium on computer graphics and image processing (SIBGRAPI)

作者： Bogdan Tomoyuki Nassu Lourival Lippmann Bruno Marchesi Amanda Canestraro Rafael Wagner Vanderlei Zarnicinski Federal University of Technology Parana Brazil Amanda Canestraro and Rafael Wagner Institutos Lactec Brazil Inst. Lactec Curitiba Brazil Companhia Paranaense de Energia Brazil

Knowing the state of the disconnect switches in a power distribution substation is important to avoid accidents, damaged equipment, and service interruptions. This information is usually provided by human operators, who can commit errors because of the cluttered environment, bad weather or lighting conditions, or lack of attention. In this paper, we introduce an approach for determining the state of each switch in a substation, based on images captured by regular pan-tilt-zoom surveillance cameras. The proposed approach includes noise reduction, image registration using phase correlation, and classification using a convolutional neural network and a support vector machine fed with gradient-based descriptors. By combining information given in an initial labeling stage with image processing techniques to reduce variations in viewpoint, our approach achieved 100% accuracy on experiments performed at a real substation over multiple days. We also show how modifications to the standard phase correlation image registration algorithm can make it more robust to lighting variations, and how SIFT (Scale-Invariant Feature Transform) descriptors can be made more robust in scenarios where the relevant objects may be brighter or darker than the background.

关键词： Substations Cameras image registration Lighting Monitoring Labeling Correlation

来源：评论

学校读者我要写书评

暂无评论

A Divide-and-Conquer Clustering Approach Based on Optimum-Path Forest

A Divide-and-Conquer Clustering Approach Based on Optimum-Pa...

引用

brazilian symposium on computer graphics and image processing (SIBGRAPI)

作者： Adán Echemendía Montero Alexandre Xavier Falcão Laboratory of Image Data Science University of Campinas

Data clustering is one of the main challenges when solving Data Science problems. Despite its progress over almost one century of research, clustering algorithms still fail in identifying groups naturally related to the semantics of the problem. Moreover, the technological advances add crucial challenges with a considerable data increase, which are not handled by most techniques. We address these issues by proposing a divide-and-conquer approach to a clustering technique, which is unique in finding one group per dome of the probability density function of the data - the Optimum-Path Forest (OPF) clustering algorithm. Our approach can use all samples, or at least many samples, in the unsupervised learning process without affecting the grouping performance and, therefore, being less likely to lose relevant grouping information. We show that it can obtain satisfactory results when segmenting natural images into superpixels.

关键词： Clustering algorithms Training Forestry Partitioning algorithms Probability density function Vegetation Prototypes

来源：评论

学校读者我要写书评

暂无评论

Multimodal Human Action Recognition Based on a Fusion of Dynamic images Using CNN Descriptors

Multimodal Human Action Recognition Based on a Fusion of Dyn...

引用

brazilian symposium on computer graphics and image processing (SIBGRAPI)

作者： Edwin Escobedo Cardenas Guillermo Camara Chavez Universidade Federal de Ouro Preto Ouro Preto MG BR

In this paper, we propose the use of dynamic-images-based approach for action recognition. Specifically, we exploit the multimodal information recorded by a Kinect sensor (RGB-D and skeleton joint data). We combine several ideas from rank pooling and skeleton optical spectra to generate dynamic images to summarize an action sequence into single flow images. We group our dynamic images into five groups: a dynamic color group (DC); a dynamic depth group (DD) and three dynamic skeleton groups (DXY, DYZ, DXZ). As action is composed of different postures along time, we generated N different dynamic images with the main postures for each dynamic group. Next, we applied a pre-trained flow-CNN to extract spatiotemporal features with a max-mean aggregation. The proposed method was evaluated on a public benchmark dataset, the UTD-MHAD, and achieved the state-of-the-art result.

关键词： Skeleton Feature extraction Dynamics Spatiotemporal phenomena image color analysis Video sequences Robot sensing systems

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning Approach for Graph-Based Page Segmentation

A Machine Learning Approach for Graph-Based Page Segmentatio...

引用

brazilian symposium on computer graphics and image processing (SIBGRAPI)

作者： Ana L.L.M. Maia Frank D. Julca-Aguilar Nina S.T. Hirata Universidade de Sao Paulo Sao Paulo SÃ£o Paulo BR

We propose a new approach for segmenting a document image into its page components (e.g. text, graphics and tables). Our approach consists of two main steps. In the first step, a set of scores corresponding to the output of a convolutional neural network, one for each of the possible page component categories, is assigned to each connected component in the document. The labeled connected components define a fuzzy over-segmentation of the page. In the second step, spatially close connected components that are likely to belong to a same page component are grouped together. This is done by building an attributed region adjacency graph of the connected components and modeling the problem as an edge removal problem. Edges are then kept or removed based on a pre-trained classifier. The resulting groups, defined by the connected subgraphs, correspond to the detected page components. We evaluate our method on the ICDAR2009 dataset. Results show that our method effectively segments pages, being able to detect the nine types of page components. Furthermore, as our approach is based on simple machine learning models and graph-based techniques, it should be easily adapted to the segmentation of a variety of document types.

关键词： image segmentation Layout image edge detection Machine learning Training

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Dialogue Act Classification with Optimum-Path Forest

Unsupervised Dialogue Act Classification with Optimum-Path F...

引用

brazilian symposium on computer graphics and image processing (SIBGRAPI)

作者： Luiz Carlos Felix Ribeiro João Paulo Papa Dept. of Comput. Sao Paulo State Univ. Bauru Brazil Department of Computing São Paulo State University UNESP Bauru SP Brazil

Dialogue Act classification is a relevant problem for the Natural Language processing field either as a standalone task or when used as input for downstream applications. Despite its importance, most of the existing approaches rely on supervised techniques, which depend on annotated samples, making it difficult to take advantage of the increasing amount of data available in different domains. In this paper, we briefly review the most commonly used datasets to evaluate Dialogue Act classification approaches and introduce the Optimum-Path Forest (OPF) classifier to this task. Instead of using its original strategy to determine the corresponding class for each cluster, we use a modified version based on majority voting, named M-OPF, which yields good results when compared to k-means and Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN), according to accuracy and V-measure. We also show that M-OPF, and consequently OPF, are less sensitive to hyper-parameter tuning when compared to HDBSCAN.

关键词： Task analysis Prototypes Forestry Vegetation Switches Hidden Markov models Natural language processing

来源：评论

学校读者我要写书评

暂无评论

An Architecture for Collision Risk Prediction for Visually Impaired People

An Architecture for Collision Risk Prediction for Visually I...

引用

brazilian symposium on computer graphics and image processing (SIBGRAPI)

作者： Natal Henrique Cordeiro Emerson Carlos Pedrino Department of Computing Federal Institute of São Paulo Votuporanga SP Brazil Department of Computer Sciences Federal University of São Carlos São Carlos SP Brazil

The production of sensory substitution equipment for the visually impaired (VIP) is growing. The aim of this project is to understand the VIP context and predict the risks of collision for the VIP, following an analysis of the position, distance, size and motion of the objects present in their environment. This understanding is refined by data fusion steps applied to the Situation Awareness model to predict possible impacts in the near future. With this goal, a new architecture was designed, composed of systems that detect free passages, static objects, dynamic objects and the paths of these dynamic objects. The detected data was mapped into a 3D plane verifying positions and sizes. For the fusion, a method was developed that compared four more general classifiers in order to verify which presented greater reliability in the given context. These classifiers allowed inferences to be made when analyzing the risks of collision in different directions. The architecture designed for risk prediction is the main contribution of this project.

关键词： computer architecture Cameras Indoor environment Data integration Surface acoustic waves Radiofrequency identification

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

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

引用

brazilian symposium on computer graphics and image processing (SIBGRAPI)

作者： Lucas Teixeira Gonçalves Joel Felipe de Oliveira Gaya Paulo Jorge Lilles Drews Junior Silvia Silva da Costa Botelho Intelligent Robotics and Automation Group - NAUTEC Universidade Federal do Rio Grande - FURG Rio Grande Brazil Universidade Federal do Rio Grande Rio Grande RS BR

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22页 << < 13 14 15 16 17 18 19 20 21 22 > >>

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：