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

3 篇 会议

馆藏范围

3 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

2 篇 工学
- 1 篇 机械工程
- 1 篇 计算机科学与技术...

主题

1 篇 mouth
1 篇 hidden markov mo...
1 篇 neural networks
1 篇 frame level
1 篇 gesture recognit...
1 篇 expectation-maxi...
1 篇 assistive techno...
1 篇 classification (...
1 篇 shape
1 篇 classifiers
1 篇 sign language re...
1 篇 training
1 篇 hand
1 篇 images

机构

2 篇 human language t...
1 篇 centre for visio...
1 篇 centre for visio...
1 篇 human language t...
1 篇 centre for visio...

作者

2 篇 hermann ney
2 篇 oscar koller
2 篇 richard bowden
1 篇 koller oscar
1 篇 ney hermann
1 篇 bowden richard

语言

3 篇 英文

检索条件"机构=Human Language Technology and Pattern Recog."

共 3 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：

Deep hand: How to train a CNN on 1 million hand images when your data is continuous and weakly labelled

Deep hand: How to train a CNN on 1 million hand images when ...

引用

2016 IEEE Conference on Computer Vision and pattern recog.ition, CVPR 2016

作者： Koller, Oscar Ney, Hermann Bowden, Richard Human Language Technology and Pattern Recog. RWTH Aachen University Germany Centre for Vision Speech and Signal Processing University of Surrey United Kingdom

ISBN: (纸本)9781467388511

This work presents a new approach to learning a framebased classifier on weakly labelled sequence data by embedding a CNN within an iterative EM algorithm. This allows the CNN to be trained on a vast number of example images when only loose sequence level information is available for the source videos. Although we demonstrate this in the context of hand shape recog.ition, the approach has wider application to any video recog.ition task where frame level labelling is not available. The iterative EM algorithm leverages the discriminative ability of the CNN to iteratively refine the frame level annotation and subsequent training of the CNN. By embedding the classifier within an EM framework the CNN can easily be trained on 1 million hand images. We demonstrate that the final classifier generalises over both individuals and data sets. The algorithm is evaluated on over 3000 manually labelled hand shape images of 60 different classes which will be released to the community. Furthermore, we demonstrate its use in continuous sign language recog.ition on two publicly available large sign language data sets, where it outperforms the current state-of-the-art by a large margin. To our knowledge no previous work has explored expectation maximization without Gaussian mixture models to exploit weak sequence labels for sign language recog.ition.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Deep Hand: How to Train a CNN on 1 Million Hand Images When Your Data Is Continuous and Weakly Labelled

Deep Hand: How to Train a CNN on 1 Million Hand Images When ...

引用

IEEE Conference on Computer Vision and pattern recog.ition

作者： Oscar Koller Hermann Ney Richard Bowden Human Language Technology & Pattern Recog. RWTH Aachen University Centre for Vision Speech & Signal Processing University of Surrey

ISBN: (纸本)9781467388528

This work presents a new approach to learning a frame-based classifier on weakly labelled sequence data by embedding a CNN within an iterative EM algorithm. This allows the CNN to be trained on a vast number of example images when only loose sequence level information is available for the source videos. Although we demonstrate this in the context of hand shape recog.ition, the approach has wider application to any video recog.ition task where frame level labelling is not available. The iterative EM algorithm leverages the discriminative ability of the CNN to iteratively refine the frame level annotation and subsequent training of the CNN. By embedding the classifier within an EM framework the CNN can easily be trained on 1 million hand images. We demonstrate that the final classifier generalises over both individuals and data sets. The algorithm is evaluated on over 3000 manually labelled hand shape images of 60 different classes which will be released to the community. Furthermore, we demonstrate its use in continuous sign language recog.ition on two publicly available large sign language data sets, where it outperforms the current state-of-the-art by a large margin. To our knowledge no previous work has explored expectation maximization without Gaussian mixture models to exploit weak sequence labels for sign language recog.ition.

关键词： expectation-maximisation algorithm Hand frame level sign language recog.ition images Classifiers

来源：评论

学校读者我要写书评

暂无评论

Deep Learning of Mouth Shapes for Sign language

Deep Learning of Mouth Shapes for Sign Language

引用

International Conference on Computer Vision Workshops (ICCV Workshops)

作者： Oscar Koller Hermann Ney Richard Bowden Human Language Technology & Pattern Recog. RWTH Aachen University Germany Centre for Vision Speech & Signal Processing University of Surrey UK

This paper deals with robust modelling of mouth shapes in the context of sign language recog.ition using deep convolutional neural networks. Sign language mouth shapes are difficult to annotate and thus hardly any publicly available annotations exist. As such, this work exploits related information sources as weak supervision. humans mainly look at the face during sign language communication, where mouth shapes play an important role and constitute natural patterns with large variability. However, most scientific research on sign language recog.ition still disregards the face. Hardly any works explicitly focus on mouth shapes. This paper presents our advances in the field of sign language recog.ition. We contribute in following areas: We present a scheme to learn a convolutional neural network in a weakly supervised fashion without explicit frame labels. We propose a way to incorporate neural network classifier outputs into a HMM approach. Finally, we achieve a significant improvement in classification performance of mouth shapes over the current state of the art.

关键词： Mouth Shape Hidden Markov models Assistive technology Gesture recog.ition Training Neural networks

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1页 << < 1 > >>

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：