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

33 篇 会议
2 篇 期刊文献
1 册 图书

馆藏范围

36 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

16 篇 工学
- 9 篇 计算机科学与技术...
- 6 篇 软件工程
- 5 篇 电气工程
- 2 篇 仪器科学与技术
- 2 篇 生物工程
- 1 篇 机械工程
- 1 篇 光学工程
- 1 篇 电子科学与技术（可...
- 1 篇 信息与通信工程
- 1 篇 控制科学与工程
- 1 篇 船舶与海洋工程
- 1 篇 生物医学工程（可授...
9 篇 理学
- 5 篇 物理学
- 3 篇 数学
- 2 篇 生物学
3 篇 医学
- 3 篇 临床医学
- 1 篇 基础医学(可授医学...
- 1 篇 药学(可授医学、理...
2 篇 管理学
- 2 篇 图书情报与档案管...
2 篇 艺术学
- 1 篇 美术学
- 1 篇 设计学（可授艺术学...
1 篇 法学
- 1 篇 社会学

主题

12 篇 data visualizati...
5 篇 computer science
4 篇 application soft...
3 篇 neural networks
3 篇 data mining
3 篇 geographic infor...
3 篇 shape
3 篇 data analysis
3 篇 weaving
2 篇 support vector m...
2 篇 roads
2 篇 size control
2 篇 computer archite...
2 篇 image segmentati...
2 篇 spatial database...
2 篇 educational inst...
2 篇 laboratories
2 篇 frequency
2 篇 visualization
2 篇 feature extracti...

机构

4 篇 visualization an...
3 篇 institute for vi...
2 篇 department of co...
2 篇 institute for vi...
2 篇 institute for vi...
2 篇 center for polym...
2 篇 institute for vi...
1 篇 visualization an...
1 篇 institute for vi...
1 篇 institute for vi...
1 篇 nasa ames resear...
1 篇 institute for vi...
1 篇 general surgery ...
1 篇 system engineeri...
1 篇 center for compu...
1 篇 university of sa...
1 篇 scientific visua...
1 篇 department head ...
1 篇 institute for vi...
1 篇 computer graphic...

作者

6 篇 georges grinstei...
6 篇 sukhendu das
4 篇 g. grinstein
3 篇 grinstein george...
3 篇 levkowitz h
2 篇 das sukhendu
2 篇 saurabh kumar ja...
2 篇 shweta purushe
2 篇 lee john peter
2 篇 grinstein george...
2 篇 h. levkowitz
2 篇 smith stuart
1 篇 e.f. flores
1 篇 a. kobsa
1 篇 c. plaisant
1 篇 ekaterina i. gal...
1 篇 t.t. mirnalinee
1 篇 t.t mirnalinee
1 篇 r. minghim
1 篇 pickett rm

语言

36 篇 英文

检索条件"机构=Institute for Visualization and Perception ResearchDepartment of Computer Science"

共 36 条记录，以下是1-10 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：

MARRS: Modern Backbones Assisted Co-training for Rapid and Robust Semi-Supervised Domain Adaptation

MARRS: Modern Backbones Assisted Co-training for Rapid and R...

引用

2023 IEEE/CVF Conference on computer Vision and Pattern Recognition Workshops, CVPRW 2023

作者： Jain, Saurabh Kumar Das, Sukhendu Indian Institute of Technology Visualization and Perception Lab Department of Computer Science Engineering Madras India

ISBN: (纸本)9798350302493

Semi-Supervised Domain Adaptation (SSDA) aims to develop domain invariant models from scarcely labeled target domain in addition to the fully labeled source domain. Current SSDA works are often applied in conjunction with ResNet34 backbone, which makes them overlook the advantages of utilizing other backbones. Hence, in this paper, we investigate the impact of employing different modern backbones in SSDA and propose a novel solution named Modern Backbones Assisted Co-training for Rapid and Robust Semi-Supervised Domain Adaptation (MARRS), that uses discriminative features of two modern backbones for training linear classifiers using the well established co-training framework. To induce diversity among classifiers for effective co-training, we propose a novel module that produces diversity at three levels, namely image, backbone, and feature distribution levels. Experiments reveal that MARRS not only achieves state-of-the-art performance across all popular SSDA datasets, but also drastically cuts the computation time compared to other SSDA approaches, making MARRS a rapid and robust solution for SSDA. We also provide extensive ablation experiments to verify our framework's vitality and primary design choices. © 2023 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Stochastic Binary Network for Universal Domain Adaptation

Stochastic Binary Network for Universal Domain Adaptation

引用

IEEE Workshop on Applications of computer Vision (WACV)

作者： Saurabh Kumar Jain Sukhendu Das Department of Computer Science Engineering Visualization and Perception Lab Indian Institute of Technology Madras India

Universal domain adaptation (UniDA) is the unsupervised domain adaptation with label shift. UniDA aims to classify unlabeled target samples into one of the "known" categories or into a single "unknown" category. Its main challenge lies in detecting private classes from both domains and performing alignment between the common classes. Current methods employ various techniques and loss functions to address these challenges. However, these methods commonly represent classifiers as point weight vectors, which are prone to overfitting by the source domain samples due to the lack of supervision from the target domain. Consequently, these classifiers struggle to separate target samples into known and unknown categories effectively. To address this, we introduce a novel framework called Stochastic Binary Network for Universal Domain Adaptation (STUN). STUN uses a Stochastic binary classifier for each class, whose weight is modeled as Gaus-sian distribution, enabling to sample an arbitrary number of classifiers while keeping the model size same as of two classifiers. Consistency between these sampled classifiers is used to derive the confidence scores for both source and target samples, which facilitates the alignment of common classes using weighted adversarial learning. Finally, we use deep discriminative clustering to formulate a loss function for solving the problem of fragmented feature distributions in the target domain. Extensive ablation studies and state-of-the-art results across three standard benchmark datasets show the efficacy of our framework.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MARRS: Modern Backbones Assisted Co-training for Rapid and Robust Semi-Supervised Domain Adaptation

MARRS: Modern Backbones Assisted Co-training for Rapid and R...

引用

IEEE computer Society Conference on computer Vision and Pattern Recognition Workshops (CVPRW)

作者： Saurabh Kumar Jain Sukhendu Das Department of Computer Science Engineering Visualization and Perception Lab Indian Institute of Technology Madras India

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exploring memory and time efficient neural networks for image captioning 6th

Exploring memory and time efficient neural networks for imag...

引用

6th National Conference on computer Vision, Pattern Recognition, Image Processing and Graphics, NCVPRIPG 2017

作者： Parameswaran, Sandeep Narayan Visualization and Perception Lab Department of Computer Science and Engineering Indian Institute of Technology Madras Chennai600036 India

ISBN: (纸本)9789811300196

Automatically describing the contents of an image is one of the fundamental problems in artificial intelligence. Recent research has primarily focussed on improving the quality of the generated descriptions. It is possible to construct multiple architectures that achieve equivalent performance for the same task. Among these, the smaller architecture is desirable as they require less communication across servers during distributed training and less bandwidth to export a new model from one place to another through a network. Generally, a deep learning architecture for image captioning consists of a Convolutional Neural Network (CNN) and a Recurrent Neural Network (RNN) clubbed together within an encoder-decoder framework. We propose to combine a significantly smaller CNN architecture termed SqueezeNet and a memory and computation efficient LightRNN within a visual attention framework. Experimental evaluation of the proposed architecture on Flickr8k, Flickr30k and MS-COCO datasets reveal superior result when compared to the state of the art. © Springer Nature Singapore Pte Ltd. 2018.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Temporal coherency based criteria for predicting video frames using deep multi-stage generative adversarial networks 17

Temporal coherency based criteria for predicting video frame...

引用

Proceedings of the 31st International Conference on Neural Information Processing Systems

作者： Prateep Bhattacharjee Sukhendu Das Visualization and Perception Laboratory Department of Computer Science and Engineering Indian Institute of Technology Madras Chennai India

ISBN: (纸本)9781510860964

Predicting the future from a sequence of video frames has been recently a sought after yet challenging task in the field of computer vision and machine learning. Although there have been efforts for tracking using motion trajectories and flow features, the complex problem of generating unseen frames has not been studied extensively. In this paper, we deal with this problem using convolutional models within a multi-stage Generative Adversarial Networks (GAN) framework. The proposed method uses two stages of GANs to generate crisp and clear set of future frames. Although GANs have been used in the past for predicting the future, none of the works consider the relation between subsequent frames in the temporal dimension. Our main contribution lies in formulating two objective functions based on the Normalized Cross Correlation (NCC) and the Pairwise Contrastive Divergence (PCD) for solving this problem. This method, coupled with the traditional L1 loss, has been experimented with three real-world video datasets viz. Sports-1M, UCF-101 and the KITTI. Performance analysis reveals superior results over the recent state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Challenges of exploratory visualization of gene-environment interaction in Alzheimer's disease

Challenges of exploratory visualization of gene-environment ...

引用

2012 16th International Conference on Information Visualisation, IV 2012

作者： Galkina, Ekaterina I. Grinstein, Georges G. Institute for Visualization and Perception Research Department of Computer Science University of Massachusetts Lowell United States

ISBN: (纸本)9780769547718

Alzheimer's Disease (AD) is the 6th leading cause of death in the United States. Although several genetic and environmental factors have been implicated in AD risks, no single factor is found solely responsible for disease manifestation in all Alzheimer's cases. In cases when no single gene can explain causality, the scenario of a combination of factors with modest effect sizes has been suggested. Through means of visual analysis in Weave we uncovered and further strengthened growing evidence for the link between genetics, air pollution and an earlier onset of Alzheimer's disease as exemplified in US cities with the highest reported levels of toxicity. Major sources of bias impacting our dataset are examined to caution the reader about the value of correlation findings in this less than ideal study sample. © 2012 IEEE.

关键词： Genes

来源：评论

学校读者我要写书评

暂无评论

Challenges of Exploratory visualization of Gene-environment Interaction in Alzheimer's Disease

Challenges of Exploratory Visualization of Gene-environment ...

引用

International Conference on Information Visualisation (IV)

作者： Ekaterina I. Galkina Georges G. Grinstein Institute for Visualization and Perception Research Department of Computer Science University of Massachusetts Lowell USA

关键词： Cities and towns Alzheimer's disease Histograms Air pollution Genetics

来源：评论

学校读者我要写书评

暂无评论

Interactive Animated visualizations of Breast, Ovarian Cancer and Other Health Indicator Data Using Weave, an Interactive Web -- based Analysis and visualization Environment

Interactive Animated Visualizations of Breast, Ovarian Cance...

引用

International Conference on Information Visualisation (IV)

作者： Shweta Purushe Georges Grinstein Mary Beth Smrtic Helen Lyons Institute for Visualization and Perception Research Department of Computer Science University of Massachusetts Lowell USA

Recent research in genomics and biomedical studies has shown a relationship between heredity, mutations in certain genes and the corresponding probabilities of developing certain cancers. In this study we looked at breast and ovarian cancer distributions across all states and counties in the United States over time. We describe briefly Weave, our Web-based Analysis and visualization Environment and use it to explore these cancers and present interactive animated visualizations of family hereditary patterns and genetic distributions, not only for these cancers, but also for other life-threatening cancers and related health indicators. We also show how Weave can be used to integrate other diverse epidemiological data, in particular obesity, and explore its relationship with cancer data.

关键词： Data visualization Weaving Breast cancer Obesity Correlation

来源：评论

学校读者我要写书评

暂无评论

Development of an Interactive Ramachandran Plot in Weave

Development of an Interactive Ramachandran Plot in Weave

引用

International Conference on Information Visualisation (IV)

作者： Shweta Purushe Sanjay Krishna Anbalagan Georges Grinstein Institute for Visualization and Perception Research Department of Computer Science University of Massachusetts Lowell USA

Current software systems having Ramachandran Plots do not support interactivity with the visualization. Current web-based Ramachandran Plot tools provide only primitive analysis and simple report generation features. In Weave (Web-based Analysis and visualization Environment), we have developed an improved Ramachandran Plot with interactivity that facilitates better analysis, sequence searching features and supplementary visualizations. Weave provides essential features facilitating broader amino acid analysis, statistical computations and the advantages of a more general web-based application.

关键词： Weaving Amino acids Data visualization Protein sequence Histograms Three dimensional displays

来源：评论

学校读者我要写书评

暂无评论

Enhancing STEM classes using weave: A collaborative web-based visualization environment

Enhancing STEM classes using weave: A collaborative web-base...

引用

IEEE Integrated STEM Education Conference (ISEC)

作者： Alexander Baumann Safi Shams Matthew Ross William Mass Georges Grinstein Department of Computer Science Institute for Visualization and Perception Research (IVPR) University of Massachusetts Lowell USA Economic and Social Development of Regions University of Massachusetts Lowell USA Department of Computer Science University of Massachusetts Lowell USA

Learning within a STEM classroom environment can be greatly enhanced by engaging the students in real-world datasets. This provides the opportunity to go beyond textbook examples that are often only marginally close to those students will see in their future careers. The Weave (WEb-based Analysis and visualization Environment) developed at the University of Massachusetts at Lowell allows collaborative data visualization in a web browser that is highly applicable to STEM classrooms. Larger and more field appropriate datasets can be loaded into the system, hypotheses can be made and confirmed, and students can collaboratively work together. This paper discusses the ways in which Weave could be used in the STEM classroom to foster learning.

关键词： Weaving Data visualization Collaboration computers computer science Educational institutions Economics

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4页 << < 1 2 3 4 > >>

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：