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

34 篇 会议
13 篇 期刊文献

馆藏范围

47 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

26 篇 工学
- 16 篇 计算机科学与技术...
- 14 篇 软件工程
- 5 篇 机械工程
- 3 篇 信息与通信工程
- 3 篇 控制科学与工程
- 3 篇 生物工程
- 1 篇 光学工程
- 1 篇 电气工程
- 1 篇 电子科学与技术（可...
- 1 篇 建筑学
- 1 篇 生物医学工程（可授...
8 篇 理学
- 4 篇 数学
- 4 篇 生物学
- 2 篇 物理学
- 2 篇 统计学（可授理学、...
- 1 篇 系统科学
3 篇 管理学
- 2 篇 管理科学与工程(可...
- 1 篇 图书情报与档案管...
1 篇 法学
- 1 篇 社会学

主题

10 篇 visualization
9 篇 semantics
8 篇 feature extracti...
6 篇 image color anal...
5 篇 training
4 篇 image segmentati...
4 篇 image retrieval
4 篇 humans
3 篇 support vector m...
3 篇 image edge detec...
3 篇 data mining
3 篇 clustering algor...
2 篇 conferences
2 篇 indexing
2 篇 task analysis
2 篇 dictionaries
2 篇 videos
2 篇 vectors
2 篇 optimization
2 篇 graph neural net...

机构

18 篇 key lab of intel...
17 篇 university of ch...
12 篇 peng cheng labor...
7 篇 university of sc...
7 篇 chinese academy ...
5 篇 chinese academy ...
5 篇 key lab. of inte...
4 篇 key lab of intel...
4 篇 key laboratory o...
4 篇 harbin institute...
3 篇 australian insti...
3 篇 college of compu...
3 篇 key laboratory o...
3 篇 university of ch...
3 篇 school of comput...
2 篇 harbin institute...
2 篇 university of th...
2 篇 key laboratory o...
2 篇 megvii inc
2 篇 institute of mic...

作者

21 篇 huang qingming
17 篇 qingming huang
9 篇 shuqiang jiang
8 篇 li liang
7 篇 zhang weigang
6 篇 zha zheng-jun
5 篇 jiang shuqiang
5 篇 wang shuhui
4 篇 liang li
4 篇 li guorong
4 篇 weiqiang wang
4 篇 lei qin
4 篇 wen gao
3 篇 qi yuankai
3 篇 chunxi liu
3 篇 yang shijie
3 篇 qin lei
3 篇 liu xinyan
3 篇 zhang yanhao
3 篇 li su

语言

45 篇 英文
2 篇 其他

检索条件"机构=Key Laboratory of Intell. Information Process. Institute of Comput. Technology"

共 47 条记录，以下是21-30 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：

Weakly supervised cross-view action recognition via sequential motion accumulation

Weakly supervised cross-view action recognition via sequenti...

引用

作者： Liu, Yi Qin, Lei Cheng, Zhongwei Zhang, Yanhao Zhang, Weigang Huang, Qingming University of Chinese Academy of Sciences Beijing100049 China Key Lab. of Intell. Info. Process. Inst. of Comput. Tech. Chinese Academy of Sciences China Harbin Institute of Technology Harbin150001 China

ISBN: (纸本)9781479957514

In real application scenarios, the visual observations of the same type of action vary significantly from one view to another. This paper addresses the action recognition problem under the view changes, especially when no labels are available in the target view. A novel feature, called Sequential Motion Accumulation (SMA), is proposed to characterize actions. The SMA descriptor depicts the temporal structure of motion property to explore the distinguishing action characteristics and their invariances across views. Moreover, we propose a weakly supervised categorization approach to generate target-view categorical prior for learning a cross-view metric, which can further improve the recognition accuracy of the SMA descriptor. Our method is verified on the multiview IXMAS dataset, and it achieves superior performance compared with the state-of-the-art methods. © 2014 IEEE.

关键词： Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

DA-CCD: A novel action representation by Deep Architecture of local depth feature

DA-CCD: A novel action representation by Deep Architecture o...

引用

ISBN: (纸本)9781479957514

With the widespread use of depth sensors, it is crucial to provide an effective and efficient solution for human action analysis applications upon the informative depth data. In this paper, we present a generic framework of modeling the human action by deep architecture enhanced local features with depth data. To introduce robust higher-level representations, we augment the adaptive and scalable local depth features in a deep feature learning manner. Specifically, a Deep Architecture of Comparative Coding Descriptor (DA-CCD) is proposed to represent the depth action data. Our approach obtains consistently superior recognition precisions on view specific/non-specific scenarios compared with other leading action representations of depth data on the Huawei/3DLife Dataset. © 2014 IEEE.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

DA-CCD: A NOVEL ACTION REPRESENTATION BY DEEP ARCHITECTURE OF LOCAL DEPTH FEATURE

DA-CCD: A NOVEL ACTION REPRESENTATION BY DEEP ARCHITECTURE O...

引用

IEEE International Conference on Image process.ng

作者： Yi Liu Lei Qin Zhongwei Cheng Yanhao Zhang Weigang Zhang Qingming Huang University of Chinese Academy of Sciences Key Lab. of Intell. Info. Process. Inst. of Comput. Tech. Chinese Academy of Sciences Harbin Institute of Technology

ISBN: (纸本)9781479957521

关键词： Action recognition Local depth feature Deep network

来源：评论

学校读者我要写书评

暂无评论

WEAKLY SUPERVISED CROSS-VIEW ACTION RECOGNITION VIA SEQUENTIAL MOTION ACCUMULATION

WEAKLY SUPERVISED CROSS-VIEW ACTION RECOGNITION VIA SEQUENTI...

引用

IEEE International Conference on Image process.ng

ISBN: (纸本)9781479957521

In real application scenarios, the visual observations of the same type of action vary significantly from one view to another. This paper addresses the action recognition problem under the view changes, especially when no labels are available in the target view. A novel feature, called Sequential Motion Accumulation (SMA), is proposed to characterize actions. The SMA descriptor depicts the temporal structure of motion property to explore the distinguishing action characteristics and their invariances across views. Moreover, we propose a weakly supervised categorization approach to generate target-view categorical prior for learning a cross-view metric, which can further improve the recognition accuracy of the SMA descriptor. Our method is verified on the multi-view IXMAS dataset, and it achieves superior performance compared with the state-of-the-art methods.

关键词： Action recognition Cross view Sequential motion accumulation

来源：评论

学校读者我要写书评

暂无评论

Cross-media topic detection associated with hot search queries 13

Cross-media topic detection associated with hot search queri...

引用

5th International Conference on Internet Multimedia comput.ng and Service, ICIMCS 2013

作者： Xue, Zhe Jiang, Shuqiang Li, Guorong Huang, Qingming Zhang, Weigang University of Chinese Academy of Sciences Beijing 100049 China Key Lab. of Intell. Info. Process. Inst. of Comput. Tech. CAS Beijing 100049 China School of Computer Science and Technology Harbin Institute of Technology Harbin 150001 China

ISBN: (纸本)9781450322522

Although lots of work has been done since NIST proposed the problem of Topic Detection and Tracking (TDT), most of them focus on single media data. Topic detection for cross-media data hasn't been fully investigated. In this paper, we propose an effective method for cross-media topic detection. Unlike traditional topic detection methods that are mainly based on clustering, we consider using hot search queries as guidance to detect topics. Besides, we propose an improved co-clustering method which can be well suited for cross-media data clustering. First, we use queries to detect topics directly, and find the data associated with the topic. Second, we apply our co-clustering method to find the topics existing in the rest of data. Finally, the results obtained by the first two steps are threaded together as topics. Experiments show that our method can effectively detect topics for cross-media data. © 2013 ACM.

关键词： Cluster analysis

来源：评论

学校读者我要写书评

暂无评论

Effectively localize text in natural scene images

Effectively localize text in natural scene images

引用

International Conference on Pattern Recognition

作者： Xiaoqian Liu Ke Lu Weiqiang Wang Chinese Academy of Sciences Beijing China Key Laboratory of Intell. Information Process. Institute of Comput. Technology Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781467322164

In this paper, we present an effective approach to locate scene text in images based on connected components analysis (CCA). Our approach first utilizes a multi-scale adaptive local thresholding operator to convert an image into two complementary binary images. Then, connected components (CCs) are extracted from both of them, which ensures that bright or dark text in contrast to background can be detected. Further, some rules are designed based on stroke features to verify whether a connected component belongs to characters, and the obtained candidate components are further checked on the word level by using a graph to represent spatial relation of different components. Finally, scene text regions are localized by searching the collinear maximum group over the graph. The comparison experiments of the proposed method with some representative state-of-the-art methods, on the challenging dataset ICDAR 2003, show that the proposed approach is very effective, and it is robust to text of different sizes, fonts, colors, as well as orientation of text lines.

关键词： Feature extraction Image color analysis Image edge detection Robustness Videos Learning systems Training

来源：评论

学校读者我要写书评

暂无评论

Theoretical analysis of learning local anchors for classification

Theoretical analysis of learning local anchors for classific...

引用

International Conference on Pattern Recognition

作者： Junbiao Pang Qingming Huang Baocai Yin Lei Qin Dan Wang College of Computer Science and Technology Beijing University of Technology China Key Laboratory of Intell. Information Process. Institute of Comput. Technology Chinese Academy of Sciences China

ISBN: (纸本)9781467322164

In this paper, we present a theoretical analysis on learning anchors for local coordinate coding (LCC), which is a method to model functions for data lying on non-linear manifolds. In our analysis several local coding schemes, i.e., orthogonal coordinate coding (OC-C), local Gaussian coding (LGC), local Student coding (LSC), are theoretically compared, in terms of the upper-bound locality error on any high-dimension data; this provides some insight to understand the local coding for classification tasks. We further give some interesting implications of our results, such as tradeoff between locality and approximation ability in learning anchors.

关键词： Encoding Upper bound Approximation methods Manifolds Educational institutions Vectors Error analysis

来源：评论

学校读者我要写书评

暂无评论

Cross community news event summary generation based on collaborative ranking 12

Cross community news event summary generation based on colla...

引用

4th International Conference on Internet Multimedia comput.ng and Service, ICIMCS 2012

作者： Liu, Chunxi Zhang, Weigang Jiang, Shuqiang Huang, Qingming Graduate University of Chinese Academy of Sciences Beijing 100049 China School of Computer Science and Technology Harbin Institute of Technology Harbin 150001 China Key Lab of Intell. Info. Process. Inst. of Comput. Tech. CAS Beijing 100190 China

ISBN: (纸本)9781450316002

In order to make the users to access their interested news content conveniently, news analysis has been a hot research topic for a long time. However, most of the previous works only focus on news event detection, tracking, etc. Little attention has been paid to news report difference analysis and comparison. News is full of people's cognition of the world. Because of the different background, ideologies, the cognition of the people is different from one to another. Then, the angle of the news report is different accordingly. In this paper we propose a novel scheme to summarize and compare news report from different communities by using news pictures. Two challenges are addressed: similar news reports summary generation and different news reports summary generation. Firstly, news pictures from different sources are downloaded. Then, the bag-of-visual word features are extracted from these pictures to represent their content. After that, based on the similarity and dissimilarity of the pictures from different sources, collaborative ranking is adopted to rank the images to obtain the news similar and difference summaries. Experimental results on the selected news topics are promising and demonstrate that the proposed approach is effective. Copyright © 2012 ACM.

关键词： event analysis co-ranking news summarization

来源：评论

学校读者我要写书评

暂无评论

Motion based perceptual distortion and rate optimization for video coding

Motion based perceptual distortion and rate optimization for...

引用

2012 13th IEEE International Conference on Multimedia and Expo, ICME 2012

作者： Wang, Xi Su, Li Huang, Qingming Liu, Chunxi Duan, Ling-Yu Graduate University Chinese Academy of Sciences Beijing China Key Lab. of Intell. Info. Process. Inst. of Comput. Tech. Chinese Academy of Sciences Beijing China National Engineering Laboratory for Video Technology School of EE and CS Peking University China

ISBN: (纸本)9781467316590

Most conventional distortion metrics regard a video frame as a static image, and seldom exploit using the motion information of video frames in succession. Moreover, these methods usually calculate the visual distortion based on the independent spatial pixels. Recently, many researches show that the way people perceive the video signals is similar to the way filters process.signals in the frequency domain. Therefore, in order to achieve better visual quality, we introduce a novel distortion measurement into the video coding system, which is consistent with human visual perception, and establish a perception-based rate-distortion optimization model. In this paper, we adopt Gabor filter family to decompose the video signals into frequency domain, and combine the video motion information to measure the perceptual distortion. We call it Motion tuned Distortion metric For Video coding (MDFV). After that we set up an MDFV based rate-distortion optimization model to select the best encoding mode. The experimental results show that the proposed approach is effective. © 2012 IEEE.

关键词： Image coding

来源：评论

学校读者我要写书评

暂无评论

Multiscale Browsing through Video Collections in Smartphones Using Scalable Storyboards

Multiscale Browsing through Video Collections in Smartphones...

引用

IEEE International Conference on Multimedia and Expo Workshops (ICMEW)

作者： Luis Herranz Key Laboratory of Intell. Information Process. Institute of Computing Technology Chinese Academy of Sciences Beijing China

This paper explores how multiscale browsing can be integrated with smart phone interfaces to provide enhanced navigation through video collections. We propose a system that allows the user to interactively change the scale of the storyboards, so the user can easily adjust the amount of information provided by them. Three different methods to select key frames are studied, including an efficient method that analyzes the video and creates a scalable description, with very little comput.tional cost. Then, storyboards of any length can be retrieved on demand without any further analysis, which is very convenient to provide fast multiscale navigation. Experimental evaluations show how this method improves the utility of the summaries and enhances user experience.

关键词： Smart phones Browsers Semantics Clustering algorithms Navigation Algorithm design and analysis comput.rs

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5页 << < 1 2 3 4 5 > >>

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：