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

12 篇 会议

馆藏范围

12 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

10 篇 工学
- 7 篇 计算机科学与技术...
- 7 篇 软件工程
- 2 篇 机械工程
- 2 篇 仪器科学与技术
- 2 篇 控制科学与工程
- 1 篇 电气工程
- 1 篇 电子科学与技术（可...
- 1 篇 信息与通信工程
5 篇 理学
- 3 篇 数学
- 3 篇 统计学（可授理学、...
- 1 篇 物理学
- 1 篇 系统科学
2 篇 管理学
- 2 篇 图书情报与档案管...
2 篇 艺术学
- 2 篇 设计学（可授艺术学...

主题

2 篇 kernel
2 篇 object recogniti...
1 篇 computer science
1 篇 conferences
1 篇 logistics
1 篇 hierarchical sys...
1 篇 computational co...
1 篇 regression analy...
1 篇 convergence
1 篇 image retrieval
1 篇 content addressa...
1 篇 pattern recognit...
1 篇 event detection
1 篇 visualization
1 篇 databases
1 篇 trajectory
1 篇 semantics
1 篇 algorithm design...
1 篇 image processing
1 篇 feature extracti...

机构

7 篇 graduate univers...
6 篇 key lab. of inte...
4 篇 department of co...
2 篇 peking universit...
2 篇 key laboratory o...
2 篇 chinese academy ...
2 篇 key lab. of inte...
1 篇 key lab of intel...
1 篇 department of co...
1 篇 department of co...
1 篇 university of th...
1 篇 university of ne...
1 篇 microsoft resear...
1 篇 university of te...
1 篇 graduate univers...
1 篇 national univers...
1 篇 institute of dig...
1 篇 graduate school ...
1 篇 ibm research t. ...
1 篇 key lab of intel...

作者

8 篇 tian qi
7 篇 huang qingming
5 篇 jiang shuqiang
4 篇 gao wen
4 篇 zhang shiliang
3 篇 qi tian
3 篇 qin lei
3 篇 qingming huang
2 篇 shuqiang jiang
2 篇 cheng zhongwei
2 篇 hua gang
1 篇 jin jesse s.
1 篇 zhongwei cheng
1 篇 li shipeng
1 篇 shuhui wang
1 篇 shiliang zhang
1 篇 yijuan lu
1 篇 ma siwei
1 篇 cui yue
1 篇 luo suhuai

语言

12 篇 英文

检索条件"机构=Key Lab of Intelli. Info. Process"

共 12 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：

Human group activity analysis with fusion of motion and appearance info.mation 11

Human group activity analysis with fusion of motion and appe...

引用

19th ACM International Conference on Multimedia ACM Multimedia 2011, MM'11

作者： Cheng, Zhongwei Qin, Lei Huang, Qingming Jiang, Shuqiang Yan, Shuicheng Tian, Qi Graduate University of Chinese Academy of Sciences Beijing 100190 China Key Lab of Intelli. Info. Process. Inst. of Comput. Tech CAS Beijing 100190 China National University of Singapore Electrical and Computer Engineering Singapore 117576 Singapore Department of Computer Science University of Texas San Antonio TX 78249 United States

ISBN: (纸本)9781450306164

Human activity analysis is an important and challenging task in video content analysis and understanding. In this paper, we focus on the activity of small human group, which involves countable persons and complex interactions. To cope with the variant number of participants and inherent interactions within the activity, we propose a hierarchical model with three layers to depict the characteristics at different granularities. In traditional methods, group activity is represented mainly based on motion info.mation, such as human trajectories, but ignoring discriminative appearance info.mation, e.g. the rough sketch of a pose style. In our approach, we take advantage of both the motion and the appearance info.mation in the spatiotemporal activity context under the hierarchical model. These features are inhomogeneous. Therefore, we employ multiple kernel learning methods to fuse the features for group activity recognition. Experiments on a surveillance-like human group activity database demonstrate the validity of our approach and the recognition performance is promising. Copyright 2011 ACM.

关键词： Hierarchical systems

来源：评论

学校读者我要写书评

暂无评论

ObjectBook construction for large-scale semantic-aware image retrieval

ObjectBook construction for large-scale semantic-aware image...

引用

3rd IEEE International Workshop on Multimedia Signal processing, MMSP 2011

作者： Zhang, Shiliang Tian, Qi Huang, Qingming Gao, Wen Key Lab. of Intelli. Info. Process. Inst. of Comput. Tech. CAS Beijing 100190 China Department of Computer Science University of Texas San Antonio TX78249 United States Graduate University Chinese Academy of Sciences Beijing 100049 China Peking University No. 5 Yiheyuan Road Beijing 100871 China

ISBN: (纸本)9781457714337

Automatic image annotation assigns semantic labels to images thus presents great potential to achieve semantic-aware image retrieval. However, existing annotation algorithms are not scalable to this emerging need, both in terms of computational efficiency and the number of tags they can deal with. Facilitated by recent development of the large-scale image category recognition data such as ImageNet, we extrapolate from it a model for scalable image annotation and semantic-aware image retrieval, namely ObjectBook. The element in the ObjectBook, which is called an ObjectWord, is defined as a collection of discriminative image patches annotated with the corresponding objects. We take ObjectBook as a high-level semantic preserving visual vocabulary, and hence are able to easily develop efficient image annotation and inverted file indexing strategies for large-scale image collections. The proposed retrieval strategy is compared with state-of-the-art algorithms. Experimental results manifest that the ObjectBook is both discriminative and scalable for large-scale semantic-aware image retrieval. © 2011 IEEE.

关键词： Image retrieval

来源：评论

学校读者我要写书评

暂无评论

Music video affective understanding using feature importance analysis 10

Music video affective understanding using feature importance...

引用

ACM International Conference on Image and Video Retrieval, ACM-CIVR 2010

作者： Cui, Yue Jin, Jesse S. Zhang, Shiliang Luo, Suhuai Tian, Qi University of Newcastle Callaghan 2308 NSW Australia Key Lab. of Intelli. Info. Process. Inst. of Comput. Tech. CAS Beijing 100190 China University of Texas San Antonio TX 78249 United States

ISBN: (纸本)9781450301176

Music video is a popular type of entertainment by viewers. Currently, the novel indexing and retrieval approach based on the affective cues contained in music videos becomes more and more attractive to users. Music video affective analysis and understanding is one of the most popular topics in current multimedia community. In this paper, we propose a novel feature importance analysis approach to select most representative arousal and valence features for arousal and valence modeling. Compared with state-of-the-art work by Zhang on music video affective analysis, our main contributions are in the following aspects: (1) Another 3 affect-related features are extracted to enrich the feature set and exploit their correlation with arousal and valence. (2) All extracted features are ordered via feature importance analysis, and then optimal feature subset is selected after ordering. (3) Different regression methods are compared for arousal and valence modeling in order to find the fittest estimation function. Our method achieves 33.39% and 42.17% deduction in terms of mean absolute error compared with Zhang's method. Experimental results demonstrate our proposed method has a considerable improvement on music video affective understanding. Copyright © 2010 ACM.

关键词： Regression analysis

来源：评论

学校读者我要写书评

暂无评论

Fast rate-distortion optimized transform for Intra coding

Fast rate-distortion optimized transform for Intra coding

引用

28th Picture Coding Symposium, PCS 2010

作者： Zhao, Xin Zhang, Li Ma, Siwei Gao, Wen Key Lab. of Intelli. Info. Process. Inst. of Comput. Tech. CAS Beijing 100190 China Graduate University of Chinese Academy of Sciences Beijing 100049 China Institute of Digital Media Peking University Beijing 100871 China

ISBN: (纸本)9781424471348

In our previous work, the rate-distortion optimized transform (RDOT) is introduced for Intra coding, which is featured by the usage of multiple offline-trained transform matrix candidates. The proposed RDOT achieves remarkable coding gain for KTA Intra coding, while maintaining almost the same computational complexity at the decoder. However, at the encoder, the computational complexity is increased drastically by the expensive rate-distortion (R-D) optimized selection of transform matrix. To resolve this problem, in this paper, we propose a fast RDOT scheme using macroblock- and block-level R-D cost thresholding. With the proposed method, unnecessary mode trials and R-D evaluations of transform matrices can be efficiently skipped from the mode decision process. Extensive experimental results show that, with negligible coding performance degradation, about 88.9% of the total encoding time is saved by the proposed method. © 2010 IEEE.

关键词： Computational complexity

来源：评论

学校读者我要写书评

暂无评论

Multiple Kernel Learning with High Order Kernels

Multiple Kernel Learning with High Order Kernels

引用

International Conference on Pattern Recognition

作者： Shuhui Wang Shuqiang Jiang Qingming Huang Qi Tian Key Laboratory of Intelli. Info. Process. Institute of Computer Tech Chinese Academy and Sciences Beijing China

ISBN: (纸本)9781424475421

Previous Multiple Kernel Learning approaches (MKL) employ different kernels by their linear combination. Though some improvements have been achieved over methods using single kernel, the advantages of employing multiple kernels for machine learning are far from being fully developed. In this paper, we propose to use “high order kernels” to enhance the learning of MKL when a set of original kernels are given. High order kernels are generated by the products of real power of the original kernels. We incorporate the original kernels and high order kernels into a unified localized kernel logistic regression model. To avoid over-fitting, we apply group LASSO regularization to the kernel coefficients of each training sample. Experiments on image classification prove that our approach outperforms many of the existing MKL approaches.

关键词： Kernel Visualization Logistics Training Boosting Approximation methods Convergence

来源：评论

学校读者我要写书评

暂无评论

Group activity recognition by gaussian processes estimation

Group activity recognition by gaussian processes estimation

引用

International Conference on Pattern Recognition

作者： Cheng, Zhongwei Qin, Lei Huang, Qingming Jiang, Shuqiang Tian, Qi Graduate University of Chinese Academy of Sciences Beijing 100190 China Key Lab. of Intelli. Info. Process Inst. of Comput. Tech. CAS Beijing 100190 China Department of Computer Science University of Texas San Antonio TX 78249 United States

ISBN: (纸本)9780769541099

Human action recognition has been well studied recently, but recognizing the activities of more than three persons remains a challenging task. In this paper, we propose a motion trajectory based method to classify human group activities. Gaussian processes are introduced to represent human motion trajectories from a probabilistic perspective to handle the variability of people's activities in group. With respect to the relationships of persons in group activities, three discriminative descriptors are designed, which are Individual, Dual and Unitized Group Activity Pattern. We adopt the Bag of Words approach to solve the problem of unbalanced number of persons in different activities. Experiments are conducted on the human group-activity video database, and the results show that our approach outperforms the state-of-the-art. © 2010 IEEE.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

Multiple kernel learning with high order kernels

Multiple kernel learning with high order kernels

引用

2010 20th International Conference on Pattern Recognition, ICPR 2010

作者： Wang, Shuhui Jiang, Shuqiang Huang, Qingming Tian, Qi Key Lab. of Intelli. Info. Process Inst. of Comput. Tech. CAS Beijing 100190 China Graduate School Chinese Academy of Sciences 100190 Beijing China Department of Computer Science University of Texas San Antonio TX 78249 United States

ISBN: (纸本)9780769541099

Previous Multiple Kernel Learning approaches (MKL) employ different kernels by their linear combination. Though some improvements have been achieved over methods using single kernel, the advantages of employing multiple kernels for machine learning are far from being fully developed. In this paper, we propose to use "high order kernels" to enhance the learning of MKL when a set of original kernels are given. High order kernels are generated by the products of real power of the original kernels. We incorporate the original kernels and high order kernels into a unified localized kernel logistic regression model. To avoid over-fitting, we apply group LASSO regularization to the kernel coefficients of each training sample. Experiments on image classification prove that our approach outperforms many of the existing MKL approaches. © 2010 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Action recognition using spatial-temporal context

Action recognition using spatial-temporal context

引用

International Conference on Pattern Recognition

作者： Hu, Qiong Qin, Lei Huang, Qingming Jiang, Shuqiang Tian, Qi Key Lab. of Intelli. Info. Process. Inst. of Comput. Tech. CAS Beijing 100190 China Graduate University of Chinese Academy of Sciences Beijing 100190 China Department of Computer Science University of Texas San Antonio TX 78249 United States

ISBN: (纸本)9780769541099

The spatial-temporal local features and the bag of words representation have been widely used in the action recognition field. However, this framework usually neglects the internal spatial-temporal relations between video-words, resulting in ambiguity in action recognition task, especially for videos "in the wild". In this paper, we solve this problem by utilizing the volumetric context around a video-word. Here, a local histogram of video-words distribution is calculated, which is referred as the "context" and further clustered into contextual words. To effectively use the contextual info.mation, the descriptive video-phrases (ST-DVPs) and the descriptive video-cliques (ST-DVCs) are proposed. A general framework for ST-DVP and ST-DVC generation is described, and then action recognition can be done based on all these representations and their combinations. The proposed method is evaluated on two challenging human action datasets: the KTH dataset and the YouTube dataset. Experiment results confirm the validity of our approach. © 2010 IEEE.

关键词： Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Building contextual visual vocabulary for large-scale image applications

Building contextual visual vocabulary for large-scale image ...

引用

18th ACM International Conference on Multimedia ACM Multimedia 2010, MM'10

作者： Zhang, Shiliang Huang, Qingming Hua, Gang Jiang, Shuqiang Gao, Wen Tian, Qi Key Lab. of Intelli. Info. Process. Inst. of Comput. Tech. CAS Beijing 100190 China Graduate University of Chinese Academy of Sciences Beijing 100049 China IBM Research T. J. Watson Center NY 10523 United States Peking University No. 5 Yiheyuan Road Beijing 100871 China Computer Science Depart. University of Texas San Antonio TX 78249 United States

ISBN: (纸本)9781605589336

Not withstanding its great success and wide adoption in Bag-of-visual Words representation, visual vocabulary created from single image local features is often shown to be ineffective largely due to three reasons. First, many detected local features are not stable enough, resulting in many noisy and non-descriptive visual words in images. Second, single visual word discards the rich spatial contextual info.mation among the local features, which has been proven to be valuable for visual matching. Third, the distance metric commonly used for generating visual vocabulary does not take the semantic context into consideration, which renders them to be prone to noise. To address these three confrontations, we propose an effective visual vocabulary generation framework containing three novel contributions: 1) we propose an effective unsupervised local feature refinement strategy;2) we consider local features in groups to model their spatial contexts;3) we further learn a discriminant distance metric between local feature groups, which we call discriminant group distance. This group distance is further leveraged to induce visual vocabulary from groups of local features. We name it contextual visual vocabulary, which captures both the spatial and semantic contexts. We evaluate the proposed local feature refinement strategy and the contextual visual vocabulary in two large-scale image applications: large-scale near-duplicate image retrieval on a dataset containing 1.5 million images and image search re-ranking tasks. Our experimental results show that the contextual visual vocabulary shows significant improvement over the classic visual vocabulary. Moreover, it outperforms the state-of-the-art Bundled Feature in the terms of retrieval precision, memory consumption and efficiency. © 2010 ACM.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Group Activity Recognition by Gaussian processes Estimation

Group Activity Recognition by Gaussian Processes Estimation

引用

International Conference on Pattern Recognition

作者： Zhongwei Cheng Lei Qin Qingming Huang Shuqiang Jiang Qi Tian Chinese Academy and Sciences Beijing China Key Laboratory of Intelli. Info. Process. Institute of Computer Tech Chinese Academy and Sciences Beijing China University of the Chinese Academy of Sciences Beijing Beijing CN Department of Computer Science University of Texas San Antonio TX USA

ISBN: (纸本)9781424475421

关键词： Trajectory Humans Gaussian processes Databases Conferences Feature extraction Kernel

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2页 << < 1 2 > >>

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：