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

489 篇 会议
60 册 图书
8 篇 期刊文献

馆藏范围

557 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

323 篇 工学
- 269 篇 计算机科学与技术...
- 204 篇 软件工程
- 53 篇 电气工程
- 50 篇 信息与通信工程
- 38 篇 光学工程
- 26 篇 生物工程
- 23 篇 电子科学与技术（可...
- 20 篇 控制科学与工程
- 19 篇 生物医学工程（可授...
- 14 篇 机械工程
- 14 篇 仪器科学与技术
- 14 篇 建筑学
- 12 篇 交通运输工程
- 12 篇 安全科学与工程
- 11 篇 化学工程与技术
- 9 篇 动力工程及工程热...
- 8 篇 环境科学与工程（可...
- 7 篇 城乡规划学
116 篇 理学
- 51 篇 物理学
- 49 篇 数学
- 27 篇 生物学
- 14 篇 系统科学
- 11 篇 统计学（可授理学、...
- 10 篇 化学
- 7 篇 地理学
58 篇 医学
- 57 篇 临床医学
- 10 篇 基础医学(可授医学...
32 篇 管理学
- 19 篇 管理科学与工程(可...
- 14 篇 图书情报与档案管...
8 篇 法学
- 8 篇 社会学
4 篇 农学
3 篇 教育学
2 篇 经济学
1 篇 军事学

主题

76 篇 computer vision
47 篇 image processing
44 篇 artificial intel...
37 篇 image processing...
32 篇 image segmentati...
27 篇 pattern recognit...
25 篇 computer graphic...
20 篇 deep learning
18 篇 information syst...
17 篇 computer imaging...
17 篇 layout
16 篇 computer science
16 篇 computer archite...
15 篇 graphics process...
15 篇 shape
12 篇 application soft...
12 篇 image analysis
11 篇 object detection
11 篇 image reconstruc...
10 篇 machine vision

机构

6 篇 indian statistic...
6 篇 indian institute...
6 篇 indian inst tech...
6 篇 indian inst tech...
5 篇 indian inst tech...
5 篇 indian institute...
4 篇 institute of aut...
4 篇 school of intera...
4 篇 indian inst tech...
4 篇 microsoft resear...
4 篇 wrocław universi...
3 篇 indian stat inst...
3 篇 indian institute...
3 篇 indian institute...
3 篇 indian institute...
3 篇 tongji universit...
3 篇 indian institute...
3 篇 national key lab...
3 篇 indian inst tech...
3 篇 university of so...

作者

9 篇 mukherjee jayant...
8 篇 chaudhuri subhas...
7 篇 subhasis chaudhu...
7 篇 balasubramanian ...
6 篇 harit gaurav
5 篇 das sukhendu
5 篇 sural shamik
4 篇 yasuyuki matsush...
4 篇 banerjee biplab
4 篇 james m. rehg
4 篇 ngoc thanh nguye...
4 篇 kyoung mu lee
4 篇 bogdan trawiński
4 篇 sukhendu das
4 篇 zhanyi hu
4 篇 jayadeva jayadev...
3 篇 wilfried philips
3 篇 ryszard tadeusie...
3 篇 ravindra hegadi
3 篇 j. kittler

语言

550 篇 英文
4 篇 中文
3 篇 其他

检索条件"任意字段=Proceedings of the 11th Indian Conference on Computer Vision, Graphics and Image Processing"

共 557 条记录，以下是201-210 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 empathizing with persona helps in design thinking: An experimental study with novice designers 12

How empathizing with persona helps in design thinking: An ex...

引用

12th International conference on Interfaces and Human computer Interaction 2018, 11th International conference on Game and Entertainment Technologies 2018 and 12th International conference on computer graphics, Visualization, computer vision and image processing 2018, part of the Multi conference on computer Science and Information Systems 2018, MCCSIS 2018

作者： Dahiya, Abhishek Kumar, Jyoti Indian Institute of Technology Delhi New Delhi India

ISBN: (纸本)9789898533791

Personas are widely used by HCI designers in design process. From defining target users to explicating user understanding, persona assists designers at various stages of design process of HCI systems. Design literature advocates the use of persona not only as a source of information about users but also as a tool to empathize. this paper reports observations from an experimental study done on novice designers on how empathizing with persona affected their design solutions. A total of 30 novice designers participated in this study. Participants were asked to design a graphical composition for persona. the data collected was analyzed through expert’s rating on design solutions on the basis of directness of illustration of persona information and verbal protocols. On the basis of direct illustration of persona information on design solutions it was observed that empathizing with persona helped designers to iterate more on design thinking. © 2018.

关键词： User centered design

来源：评论

学校读者我要写书评

暂无评论

An experimental study to evaluate influence of usability on learning behaviour 12

An experimental study to evaluate influence of usability on ...

引用

作者： Kumar, Jyotish Khare, Aarati Prakash Kumar, Jyoti Indian Institute of technology Delhi New Delhi India

ISBN: (纸本)9789898533791

Usability has been one of the well-established quality measures of HCI systems. Designing an efficient e-learning system is a complex process and requires usability testing at various stages. Unlike conventional HCI systems, e-learning system is not only designed to interact with users but also to facilitate learning to user. In order to develop learner centric system design, there is a need to find the ways in which learning and usability interact. In this study, six learning behaviour markers were identified which can be integrated with conventional usability testing. this paper investigates a relationship between usability attributes and learning behaviour through usability testing of two different e-learning websites with similar in content but different in usability. Other than usability attributes and learning behaviour markers, Galvanic skin response (GSR) of users was also recorded and compared to support the usability testing results. Significant difference (p © 2018.

关键词： Websites

来源：评论

学校读者我要写书评

暂无评论

VidSeg-GAN: Generative Adversarial Network for Video Object Segmentation Tasks 11

VidSeg-GAN: Generative Adversarial Network for Video Object ...

引用

11th indian conference on computer vision, graphics and image processing (ICVGIP)

作者： Adak, Saptakatha Das, Sukhendu Indian Inst Technol Madras Chennai Tamil Nadu India

ISBN: (纸本)9781450366151

Video object segmentation aims to segment objects in a video sequence, given some user annotation which indicates the object of interest. Although Convolutional Neural Networks (CNNs) have been used in the recent past for the purpose of foreground segmentation in videos, adversarial training methods have not been used effectively to solve this problem, in spite of its extensive use for solving many other problems in computer vision. Earlier, flow features and motion trajectories have been extensively used to capture the temporal consistency between subsequent frames to segment moving objects in videos. However, we show that our proposed framework of processing the video frames independently using a deep generative adversarial network (GAN), is able to maintain the temporal coherency across frames without the use of any explicit trajectory based information, to provide superior results. Our main contribution lies in introducing a GAN based framework along with the incorporation of an Intersection-over-Union score based novel cost function for training the model, to solve the problem of foreground object segmentation in videos. the proposed method, when evaluated on popular real-world video segmentation datasets viz. DAVIS, SegTrack-v2 and YouTube-Objects, exhibits substantial performance gain over the recent state-of-the-art methods.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Temporal Modeling of EEG Signals using Block Sparse Variational Bayes Framework 11

Temporal Modeling of EEG Signals using Block Sparse Variatio...

引用

11th indian conference on computer vision, graphics and image processing (ICVGIP)

作者： Sharma, Shruti Chaudhury, Santanu Jayadeva, Jayadeva Indian Inst Technol Delhi New Delhi India

ISBN: (纸本)9781450366151

Compressed Sensing (CS) has emerged as an alternate method to acquire high dimensional signals effectively by exploiting the sparsity assumption. However, owing to non-sparse and non-stationary nature, it is extremely difficult to process Electroencephalograph (EEG) signals using CS paradigm. the success of Bayesian algorithms in recovering non-sparse signals has triggered the research in CS based models for neurophysiological signal processing. In this paper, we address the problem of Temporal Modeling of EEG Signals using Block Sparse Variational Bayes (SVB) Framework. Temporal correlation of EEG signals is modeled blockwise using normal variance scale mixtures parameterized via some random and deterministic parameters. Variational inference is exploited to infer the random parameters and Expectation Maximization (EM) is used to obtain the estimate of deterministic parameters. To validate the framework, we present experimental results for benchmark State Visual Evoked Potential (SSVEP) dataset with 40-target Brain-computer Interface (BCI) speller using two frequency recognition algorithms viz. Canonical Correlation Analysis (CCA) and L1-regularized Multiway CCA. Results show that the proposed temporal model is highly useful in processing SSVEP-EEG signals irrespective of the recognition algorithms used.

关键词： Brain computer interface

来源：评论

学校读者我要写书评

暂无评论

Texture remapping and morphing integrated with spherical mesh parameterization 12

Texture remapping and morphing integrated with spherical mes...

引用

作者： Timalsena, Sabin Peng, Chao Department of Computer Science University of Alabama in Huntsville 301 Sparkman Drive HuntsvilleAL35899 United States

ISBN: (纸本)9789898533791

the animation of character morphing is commonly used as a special effect in video games and movies. While existing mesh parameterization methods create smooth morphing effects for meshes, there is a lack of techniques to preserve the textures of meshes during mesh morphing. In this work, we present a novel method which morphs textures and is seamlessly integrated with the methods of spherical mesh parameterization, remeshing and mesh morphing. © 2018.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Perfectly Secure Shamir's Secret Sharing Scheme for Privacy Preserving image processing Over Cloud 11

Perfectly Secure Shamir's Secret Sharing Scheme for Privacy ...

引用

11th indian conference on computer vision, graphics and image processing (ICVGIP)

作者： Sadhya, Debanjan Agarwal, Akshay Raman, Balasubramanian Indian Inst Technol Roorkee Roorkee Uttar Pradesh India Manipal Inst Technol Manipal India

ISBN: (纸本)9781450366151

Cloud computing is a highly prospective paradigm in which computational resources from third parties are used for processing outsourced data. Nonetheless, the distributed architecture of this concept poses many security and privacy threats for the data owners. Shamir's secret sharing is an effective technique for distributing and processing secret images over the encrypted domain. However, it has got some critical limitations primarily due to the presence of correlated information between the image pixels. Our study addresses this problem by proposing a perfectly secure Shamir's secret sharing scheme for images. Our work builds upon the formal notion of perfect secrecy for encoding the Shamir's shares in a particular manner such that they (i.e. encoded shares) do not reveal any additional information about the original image. Importantly, we have provided both theoretical and empirical validation of our proposed approach. We have also performed several image filtering operations on the stored shares and found the resulting PSNR and NCC values to be similar in the plain and encrypted domains. Hence our work provides a privacy-preserving and secure framework for working with images over a cloud-based architecture.

关键词： Cloud Computing Shamir's Secret Sharing Perfect Secrecy Encrypted Domain

来源：评论

学校读者我要写书评

暂无评论

Towards Automated Floorplan Generation 11

Towards Automated Floorplan Generation

引用

11th indian conference on computer vision, graphics and image processing (ICVGIP)

作者： Chelani, Kunal Sidhartha, Chitturi Govindu, Venu Madhav Indian Inst Sci Bengaluru India

ISBN: (纸本)9781450366151

In this paper, we propose a pipeline for generating a 2D floorplan using depth cameras. In our pipeline we use an existing approach to recovering the camera motion trajectories from the depth and RGB sequences. Given these motion estimates we construct a full 3D representation of the scanned indoor spaces. For generating a floorplan we need to abstract the large volumes of registered 3D data into a simplified rectilinear representation. We evaluate two approaches to solve this problem, viz slicing the reconstructed volume at a given height and direct segmentation of the 3D point cloud representation into individual planar segments. We also note that the fidelity of our estimated floorplan crucially depends on the accuracy of the estimation of the ground plane orientation. We examine the comparative accuracies of two ground plane estimation methods for each of the above mentioned approaches to rectilinear abstraction. Given the line drawing abstractions of the individual rooms, we merge them into a consistent floorplan. We present results on a real-world floorplan estimation problem and demonstrate its accuracy. Additionally, the implications of errors in the individual components of our pipeline are also studied.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning-based Model for Phase Unwrapping 11

A Deep Learning-based Model for Phase Unwrapping

引用

11th indian conference on computer vision, graphics and image processing (ICVGIP)

作者： Spoorthi, G. E. Gorthi, Subrahmanyam Gorthi, Rama Krishna Sai Indian Inst Technol Tirupati Andhra Pradesh India

ISBN: (纸本)9781450366151

Phase unwrapping is an important problem in several applications that attempts to restore original phase from wrapped phase. In this paper, we propose a novel phase unwrapping model based on the deep convolutional neural network by formulating the phase unwrapping as a semantic segmentation problem. the proposed architecture consists of a convolutional encoder network and corresponding decoder network followed by a pixel-wise classification layer. One of the critical challenges in DCNN is availability of large set of labeled training data. this issue is effectively circumvented for the proposed framework through a generic simulation procedure that automatically generates large labeled data. Results from the proposed method are compared with widely used quality-guided phase unwrapping algorithm for various SNR values. It is found that the proposed method is performing well both in terms of accuracy and computational time, even in the presence strong noise. To the best of our knowledge, this is the first work that uses convolutional neural network for phase unwrapping, and this will hopefully pave the way to a new class of techniques for unwrapping the phase.

关键词： Phase Unwrapping Deep Convolutional Neural Network (DCNN) Encoder Decoder Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

A Neural Network Based Approach for Geo-Localizing Events in Crowd Sourced Videos 11

A Neural Network Based Approach for Geo-Localizing Events in...

引用

11th indian conference on computer vision, graphics and image processing (ICVGIP)

作者： More, Amit Chaudhuri, Subhasis Indian Inst Technol Mumbai Maharashtra India

ISBN: (纸本)9781450366151

Popular events are often video recorded simultaneously by a general crowd using smartphones. In the present work, we propose a robust recurrent neural network (RNN) based approach for geo-localizing these events using sensor data collected by user smartphones while recording such events. For this task we use GPS and compass sensors, which are commonly available on the smartphones. the circular nature (modulo 2p) of the orientation data from compass limits the ability of the classical neural networks (NN) to geo-localize these events. We mitigate this issue by incorporating circular nodes in our network and show the performance improvements. We train the proposed NN model using simulated data and apply it directly on real data. We train several RNN models using this strategy and show our analyses. the proposed work outperforms all previous approaches in terms of event geo-localization accuracy.

关键词： Event Geo-localization Neural Network Circular Nodes GPS data Compass Data Smartphone

来源：评论

学校读者我要写书评

暂无评论

image Co-segmentation using Graph Convolution Neural Network 11

Image Co-segmentation using Graph Convolution Neural Network

引用

11th indian conference on computer vision, graphics and image processing (ICVGIP)

作者： Banerjee, Sayan Hati, Avik Chaudhuri, Subhasis Velmurugan, Rajbabu Indian Inst Technol Mumbai Maharashtra India

ISBN: (纸本)9781450366151

image co-segmentation is jointly segmenting two or more images sharing common foreground objects. In this paper, we propose a novel graph convolution neural network (graph CNN) based end-to-end model for performing co-segmentation. At the beginning, each input image is over-segmented into a set of superpixels. Next, a weighted graph is formed using the over-segmented images exploiting spatial adjacency and both intra-image and inter-image feature similarities among the image superpixels (nodes). Subsequently, the proposed network, consisting of graph convolution layers followed by node classification layers, classifies each superpixel either into the common foreground or its complement. During training, along with the co-segmentation network, an additional network is introduced to exploit the corresponding semantic labels, and the two networks share the same weights in graph convolution layers. the whole model is learned in an end-to-end fashion using a novel cost function comprised of a superpixel wise binary cross entropy and a multi-label cross entropy. We also use empirical class probabilities in the loss function to deal with class imbalance. Experimental results reflect that the proposed technique is very competitive with the state-of-the-art methods on two challenging datasets, Internet and Pascal-VOC.

关键词： Co-segmentation graph superpixel graph CNN convolution filter

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56页 << < 17 18 19 20 21 22 23 24 25 26 > >>

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：