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

1,106 篇 会议
48 篇 期刊文献
8 册 图书

馆藏范围

1,162 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

650 篇 工学
- 569 篇 计算机科学与技术...
- 421 篇 软件工程
- 133 篇 电气工程
- 61 篇 光学工程
- 50 篇 控制科学与工程
- 49 篇 信息与通信工程
- 39 篇 电子科学与技术（可...
- 34 篇 生物医学工程（可授...
- 27 篇 机械工程
- 16 篇 生物工程
- 12 篇 仪器科学与技术
- 7 篇 建筑学
- 7 篇 农业工程
- 7 篇 网络空间安全
- 6 篇 安全科学与工程
- 5 篇 材料科学与工程（可...
- 5 篇 土木工程
318 篇 医学
- 296 篇 临床医学
- 50 篇 特种医学
- 26 篇 基础医学(可授医学...
- 10 篇 药学(可授医学、理...
161 篇 理学
- 101 篇 数学
- 68 篇 物理学
- 16 篇 生物学
- 15 篇 统计学（可授理学、...
- 6 篇 系统科学
41 篇 管理学
- 24 篇 管理科学与工程(可...
- 22 篇 图书情报与档案管...
- 5 篇 工商管理
7 篇 农学
- 7 篇 作物学
5 篇 法学
3 篇 教育学
1 篇 经济学

主题

179 篇 image segmentati...
101 篇 feature extracti...
90 篇 image processing
79 篇 computer graphic...
75 篇 image color anal...
75 篇 shape
74 篇 computer vision
70 篇 training
69 篇 visualization
65 篇 image reconstruc...
52 篇 image analysis
49 篇 rendering (compu...
47 篇 graphics
45 篇 robustness
40 篇 layout
39 篇 image edge detec...
39 篇 computational mo...
39 篇 histograms
38 篇 cameras
37 篇 pixel

机构

11 篇 universidade de ...
10 篇 universidade fed...
7 篇 univ estadual ca...
7 篇 institute of com...
7 篇 univ sao paulo i...
6 篇 universidade est...
5 篇 univ fed minas g...
5 篇 impa rio de jane...
5 篇 school of comput...
5 篇 school of electr...
4 篇 univ sao paulo i...
4 篇 impa-instituto d...
4 篇 institute of com...
4 篇 géométrica proje...
4 篇 univ fed rio gra...
3 篇 computer science...
3 篇 universidade de ...
3 篇 departamento de ...
3 篇 departamento de ...
3 篇 pontificia univ ...

作者

11 篇 wu shin-ting
11 篇 falcao alexandre...
11 篇 velho luiz
10 篇 luiz velho
10 篇 velho l
9 篇 l. velho
9 篇 silvio jamil f. ...
9 篇 miranda paulo a....
8 篇 luis gustavo non...
7 篇 schwartz william...
7 篇 afonso paiva
7 篇 hirata nina s. t...
7 篇 r.a. lotufo
7 篇 waldemar celes
7 篇 guimaraes pedron...
6 篇 jefersson a. dos...
6 篇 guimaraes silvio...
6 篇 torres ricardo d...
6 篇 menotti david
6 篇 william robson s...

语言

1,159 篇 英文
3 篇 葡萄牙文

检索条件"任意字段=16th Brazilian Symposium on Computer Graphics and Image Processing"

共 1162 条记录，以下是281-290 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：

Fine-grained Cars Recognition using Deep Convolutional Neural Networks 35

Fine-grained Cars Recognition using Deep Convolutional Neura...

引用

35th SIBGRAPI Conference on graphics, Patterns and images (SIBGRAPI)

作者： Oliveira, Franklin Macena, Arianne Kamel, Otavio Souza, Wesley Freitas, Nicksson Vinuto, Tiago Univ Fed Pernambuco Comp Ctr Recife Brazil SiDi Recife Brazil

ISBN: (数字)9781665453851

ISBN: (纸本)9781665453851

Population growth and the high concentration of vehicles on urban roads have negatively impacted urban mobility and the global environment since the primary transportation modes occupy a lot of space on the streets and are one of the main polluting gas emitters. In this context of inefficient urban mobility and unsustainability, the Intelligent Transportation Systems (ITS) aims to solve or minimize urban traffic issues. ITS are also widely used in applications focused on traffic safety, such as vehicle recognition related to a traffic or law violation. For this task, the fine-grained vehicle classification technique is mainly used by computer vision and deep learning advances. However, identifying vehicles by the model can be problematic because the same vehicle can be easily misclassified when observed from different perspectives, with different colours, or by similar models. Knowing these inherent issues from vehicle recognition tasks, Deep Convolutional Neural Networks (DCNNs) are commonly used due to their ability to extract features from images. In that regard, the goal of this paper is to evaluate some state of art DCNNs architectures, conducting experiments with three different datasets to identify which architectures have the best performance metrics in the refined car classification task within ITS context.

关键词： Training computer vision Computational modeling Urban areas computer architecture Feature extraction Safety

来源：评论

学校读者我要写书评

暂无评论

An Investigation of 2D Keypoints Detection on Challenging Scenarios Using Depthwise Separable Convolutions: A Hand Pose Estimation Case Study 34

An Investigation of 2D Keypoints Detection on Challenging Sc...

引用

34th SIBGRAPI Conference on graphics, Patterns and images (SIBGRAPI)

作者： Costa, Willams Figueiredo, Lucas Teixeira, Joao Marcelo Lima, Joao Paulo Teichrieb, Veronica Univ Fed Pernambuco Ctr Informat Voxar Labs Recife PE Brazil Univ Fed Rural Pernambuco Dept Comp Recife PE Brazil

ISBN: (纸本)9781665423540

2D keypoints detection is a computer vision task applicable to several fields such as hand, face, and body tracking, which provides useful information for spatial analytics, gestural interactions, and augmented reality applications. this work investigates the usage of depthwise separable convolutions (an optimized convolution operation) to speed up the inference time on a largely used architecture for 2D keypoints estimation. We evaluate the impacts on the precision and performance of such optimization on a hand pose estimation task. We also extend the evaluation towards simulated challenging scenarios of defocused lens, motion blur, occlusions, and noisy images to understand how these stress situations affect both the original and the optimized architectures. We show that the execution time can be improved on average by 12.8% with an accuracy compromise of less than 1 pixel (mean EPE). the experiments on challenging scenarios revealed that the model powered by depthwise separable convolutions is most fit for the occlusion cases and noisy environments while suffering more on the motion blur simulated scenarios.

关键词： graphics computer vision Pose estimation computer architecture Noise measurement Task analysis Stress

来源：评论

学校读者我要写书评

暂无评论

An image processing system scheme in B mode ultrasonic ophthalmological scanner 16

An image processing system scheme in B mode ultrasonic ophth...

引用

16th IEEE symposium on computer-Based Medical Systems

作者： Tan, YY Zhang, N Nanjing Univ Dept Elect Sci & Engn Nanjing 210008 Peoples R China

ISBN: (纸本)0769519016

B mode ultrasonic ophthalmological scanners are used widely in clinic diagnosing of eye diseases. Digital Scan Converter (DSC) is a key component in their image processing systems, which Performs coordinate transformation and image interpolation between two adjacent scan lines. In this paper, we present a new image processing system scheme based on the FPGA technology. In this scheme, we mainly focus on the DSC component. In the DSC system, we applied the CORDIC algorithm to perform the transformation between Cartesian coordinates and polar coordinates, and use a modified R-theta algorithm to perform the image interpolations. At the same time, we mapped the. whole system into a Xilinx FPGA device (XCV50-BG256). Its performance in practical application indicates that the scheme is valid and can improve the image quality significantly and greatly reduce the dimensions of this instrument.

关键词： medical image processing eye biomedical ultrasonics algorithm theory digital simulation interpolation B mode ultrasonic ophthalmological scanners eye diseases image processing systems coordinate transformation image interpolation image processing system scheme digital scan converter component digital scan converter system CORDIC algorithm Cartesian coordinates polar coordinates modifed R-theta algorithm performance image quality

来源：评论

学校读者我要写书评

暂无评论

3D Modeling by Scanning Physical Modifications 28

3D Modeling by Scanning Physical Modifications

引用

28th SIBGRAPI Conference on graphics, Patterns and images SIBGRAPI

作者： Hattab, Ammar Taubin, Gabriel Brown Univ Sch Engn Providence RI 02912 USA

ISBN: (纸本)9781467379625

3D shape design tends to be a long and tedious process, with the design of a detailed 3D part usually requiring multiple revisions. Fabricating physical prototypes using low cost 3D fabrication technologies at intermediate stages of the design process is now a common practice, which helps the designer discover errors, and to incrementally refine the design. Most often, implementing the required changes directly in the computer model, within the 3D modeling software, is more difficult and time consuming than modifying the physical model directly using hand cutting, caving and sculpting tools, power tools, or machine tools. When one of the two models is modified, the changes need to be transferred to the other model, a process we refer to as synchronization. Changes made to the computer model can be transferred to the physical model by 3d printing a new physical model. In this paper, we address the problem of synchronizing the computer model to changes made in the physical model by 3D scanning the modified physical model, automatically detecting the changes, and updating the computer model. the proposed process comprises algorithms to: 1) register each 3D scan with a previous 3D scan and/or with the 3D representation used by the 3D modeling software;2) detect the changes (subtractive and/or additive);and 3) perform the changes on the 3D computer model.

关键词： 3D registration 3D reverse engineering 3D modeling tangible interface human-computer interaction

来源：评论

学校读者我要写书评

暂无评论

Multispectral image Segmentation With Dimensionality Reduction Using Autoencoders 36

Multispectral Image Segmentation With Dimensionality Reducti...

引用

36th SIBGRAPI Conference on graphics, Patterns and images (SIBGRAPI)

作者： Albuquerque, Eliton Jung, Claudio R. Univ Fed Rio Grande do Sul Inst Informat Porto Alegre Brazil

ISBN: (纸本)9798350338737;9798350338720

Autoencoder (AE) implementations through neural networks have achieved impressive results on dimensionality reduction tasks, such as multispectral (MS) imagery compression. Dimensionality reduction algorithms are necessary when dealing with large multispectral datasets, since the data captured by multiple levels of narrow spectral wavelengths causes high processing and storage costs, particularly when such highly dimensional MS data are used as input to deep learning networks. Traditional data compression techniques like Principal Component Analysis (PCA) are popular in remote sensing applications. However, its implementation on MS data may make the data unusable for computer vision (CV) tasks such as image segmentation, especially when applying severe compression. On the other hand, AEs provide great generalization capabilities over complex data, especially when combined with other CV pipelines. For the relevant problem of semantic segmentation, the results are considerably degraded when using dimensionality-reduced images with PCA. When using vanilla autoencoders trained with the traditional MSE loss, the segmentation results improve over PCA but are still considerably behind the one obtained with uncompressed data, which indicates a potential domain shift. In this work, we show that training an AE using a combination of the MSE loss and an additional proxy loss based on a pre-trained segmentation module can significantly improve the AE restoration process, alleviating the accuracy drop of semantic segmentation even for strong compression rates. Our code is available at https://***/elitonfilho/pca.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

brazilian Road's Animals (BRA): An image Dataset of Most Commonly Run Over Animals 35

Brazilian Road's Animals (BRA): An Image Dataset of Most Com...

引用

35th SIBGRAPI Conference on graphics, Patterns and images (SIBGRAPI)

作者： Ferrante, Gabriel S. Nakamura, Luis H. V. Andrade, Fernando R. H. Rocha Filho, Geraldo P. De Grande, Robson E. Meneguette, Rodolfo I. Univ Sao Paulo Inst Sci Math & Comp Sci Sao Carlos Brazil Fed Inst Sao Paulo Dept Informat Catanduva Brazil Univ Brasilia Dept Comp Sci Brasilia Brazil Brock Univ Dept Comp Sci St Catharines ON Canada

ISBN: (数字)9781665453851

ISBN: (纸本)9781665453851

In Brazil, about 475 million animals, including small and large species, are killed on the roads every year. Although this problem with wildlife can be considered recurrent, it involves significant investments and resources whose governments cannot afford to allocate to develop new mechanisms and technologies to identify, monitor, and guarantee the safety of animals in high-risk areas. In the field of computer vision, there are already datasets about animals in the literature, but not focusing on animals that suffer most accidents on highways. this work thus aims to present a new dataset of labelled images to address this gap, the BRA-Dataset. the labeling concerns five medium and large mammals that die the most on brazilian roads, which can serve as a training dataset for future animal detection models on highways. the images were obtained using the proposed acquisition approach with a manual cleaning process;the dataset contain 1823 images in total and labelled in the YOLO Darknet and PASCAL VOC format. Also was effectuated experimentation on BRA-Dataset for validation of its performance on YOLO models training and tests. the results showed a high average precision achieved over the dataset in its first version without data augmentation or application process of improvement.

关键词： Training computer vision Animals Biological system modeling Roads Data models Safety

来源：评论

学校读者我要写书评

暂无评论

SynLibras: A Disentangled Deep Generative Model for brazilian Sign Language Synthesis 35

SynLibras: A Disentangled Deep Generative Model for Brazilia...

引用

35th SIBGRAPI Conference on graphics, Patterns and images (SIBGRAPI)

作者： Silveira, Wellington Alaniz, Andrew Hurtado, Marina da Silva, Bernardo Castello de Bem, Rodrigo Fed Univ Rio Grande FURG Ctr Computat Sci C3 Rio Grande Brazil

ISBN: (数字)9781665453851

ISBN: (纸本)9781665453851

Recent advances regarding deep generative models have strengthened a realm of approaches in which discriminative and generative tasks are tackled jointly in an analysis-by-synthesis manner. In this category, variational autoencoders (VAEs) and generative adversarial networks (GANs) aim for learning latent data representations from which sampling of synthetic images may be performed. However, sampling in such models normally does not allow for independent control of diverse factors of variation. Despite general efforts to overcome this issue, deep generative models tailored for sign language with disentangled factors of variation are yet not vastly explored in the literature. In this work, we introduce the SynLibras, a novel model that allows for disentangling appearance and gestural communication (i.e. body, hands and face poses) on image synthesis. Our model is capable of performing cross-language pose-transfer while maintaining the appearance of the source signer. We perform experiments on the RWth-PHOENIX-Weather dataset and evaluation using the PSNR and the SSIM metrics. To our knowledge, the SynLibras is the first method for brazilian sign language (Libras) synthesis in images. We compare our model with the EDN, a well-known general pose-transfer method, achieving better results on Libras synthesis. Finally, we also introduce the SynLibras-Pose, a dataset with annotated poses of Libras signers performing single words.

关键词： Measurement graphics Analytical models image synthesis Gesture recognition Assistive technologies Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Assessing Facial image Accordance to ISO/ICAO Requirements 29

Assessing Facial Image Accordance to ISO/ICAO Requirements

引用

29th SIBGRAPI Conference on graphics, Patterns and images (SIBGRAPI)

作者： Parente, R. L. Batista, L. V. Andrezza, Igor L. P. Borges, Erick V. C. L. Mota, Rajiv A. T. Fed Univ Paraiba UFPB Informat Ctr CI Joao Pessoa Paraiba Brazil VSoft Tecnol Joao Pessoa PB Brazil

ISBN: (纸本)9781509035687

Face has been adopted as default biometric validation method and the International Standard Organization (ISO) proposed a standard which states constraints for facial image. this paper presents methods for evaluating face image conformance to the following ISO/ICAO requirements: pixelation, hair across eyes, veil over face and mouth opened. Each requirement is individually evaluated. the algorithm for analyzing pixelation achieved an equal error rate (EER) equals to 1.7%, result very close to state-of-the-art (0.0% EER). the "Hair Across Eyes" analysis method achieved an EER equals to 11.9% which surpass the best state-of-art result (12.4%). the algorithm for evaluating "Veil Over Face" requirement achieved EER equals to 1.2% which also surpass the best state-of-art result (2.5%). the "Mouth Opened" requirement achieved an EER equals to 4.20%, a result compatible with state-of-art rates for this requirement (3.3%).

关键词： Face image quality ICAO ISO/IEC 19794-5 Pixelation Hair across eyes Veil Over Face Mouth Opened

来源：评论

学校读者我要写书评

暂无评论

Learning to Segment Medical images from Few-Shot Sparse Labels 34

Learning to Segment Medical Images from Few-Shot Sparse Labe...

引用

34th SIBGRAPI Conference on graphics, Patterns and images (SIBGRAPI)

作者： Gama, Pedro H. T. Oliveira, Hugo dos Santos, Jefersson A. Univ Fed Minas Gerais Dept Comp Sci Belo Horizonte MG Brazil Univ Sao Paulo Inst Math & Stat Sao Paulo Brazil

ISBN: (纸本)9781665423540

In this paper, we propose a novel approach for few-shot semantic segmentation with sparse labeled images. We investigate the effectiveness of our method, which is based on the Model-Agnostic Meta-Learning (MAML) algorithm, in the medical scenario, where the use of sparse labeling and few-shot can alleviate the cost of producing new annotated datasets. Our method uses sparse labels in the meta-training and dense labels in the meta-test, thus making the model learn to predict dense labels from sparse ones. We conducted experiments with four Chest X-Ray datasets to evaluate two types of annotations (grid and points). the results show that our method is the most suitable when the target domain highly differs from source domains, achieving Jaccard scores comparable to dense labels, using less than 2% of the pixels of an image with labels in few-shot scenarios.

关键词： graphics image segmentation Costs Annotations Semantics Predictive models Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

Deterministic texture analysis and synthesis using tree structure vector quantization 12

Deterministic texture analysis and synthesis using tree stru...

引用

12th brazilian symposium on computer graphics and lmage processing, SIBGRAPI 1999

作者： Wei, Li-Yi Gates Computer Science Building StanfordCA94309 United States

ISBN: (纸本)0769504817

Texture analysis and synthesis is very important for computer graphics, vision, and image processing. this paper describes an algorithm which can produce new textures with a matching visual appearance from a given example image. Our algorithm is based on a model that characterizes textures using a nonlinear deterministic function. During analysis, an example texture is summarized into this function using tree structure vector quantization. An output texture, initially random noise, is then synthesized from this estimated function. Compared to existing approaches, our algorithm can efficiently generate a wide variety of textures. the effectiveness of our approach is demonstrated using standard test images from the Brodatz texture album. © 1999 IEEE.

关键词： Textures

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117页 << < 25 26 27 28 29 30 31 32 33 34 > >>

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：