检索结果-内蒙古大学图书馆

2016 IEEE Conference on computer Vision and Pattern Recognition, CVPR 2016

作者： Qi, Na Shi, Yunhui Sun, Xiaoyan Yin, Baocai Beijing Key Laboratory of Multimedia and Intelligent Software Technology College of Metropolitan Transportation Beijing University of Technology China Microsoft Research United States Faculty of Electronic Information and Electrical Engineering Dalian University of Technology China

ISBN: (纸本)9781467388511

The conventional sparse model relies on data representation in the form of vectors. It represents the vector-valued or vectorized one dimensional (1D) version of an signal as a highly sparse linear combination of basis atoms from a large dictionary. The 1D modeling, though simple, ignores the inherent structure and breaks the local correlation inside multidimensional (MD) signals. It also dramatically increases the demand of memory as well as computational resources especially when dealing with high dimensional signals. In this paper, we propose a new sparse model TenSR based on tensor for MD data representation along with the corresponding MD sparse coding and MD dictionary learning algorithms. The proposed TenSR model is able to well approximate the structure in each mode inherent in MD signals with a series of adaptive separable structure dictionaries via dictionary learning. The proposed MD sparse coding algorithm by proximal method further reduces the computational cost significantly. Experimental results with real world MD signals, i.e. 3D Multi-spectral images, show the proposed TenSR greatly reduces both the computational and memory costs with competitive performance in comparison with the state-of-the-art sparse representation methods. We believe our proposed TenSR model is a promising way to empower the sparse representation especially for large scale high order signals.

关键词： One dimensional

来源：评论

学校读者我要写书评

暂无评论

Content Adaptive Interpolation Filters for HEVC Framework

Content Adaptive Interpolation Filters for HEVC Framework

引用

Data Compression Conference (DCC)

作者： Xiaojie Liu Wenpeng Ding Yunhui Shi Baocai Yin College of Metropolitan Transportation Beijing Key Laboratory of Multimedia and Intelligent Software Technology Beijing China

Summary form only given. Motion compensation is the key technique to reduce temporal redundancy in video coding. Interpolation filters are adopted to generate the inter frame prediction for motion compensation with fractional pixel accuracy. In existing video coding standards such as H.264/AVC and HEVC, a set of predefined interpolation filters is adopted in motion compensation. However, predefined interpolation filters cannot adapt to the video content, which may compromise the coding efficiency. In this paper, a content adaptive interpolation scheme is proposed for motion compensation. In the proposed scheme, a set of adaptive interpolation filters is derived for each frame as additional interpolation filters to minimize the inter prediction difference. Rate-distortion optimization is employed to choose between the predefined interpolation filters and the derived adaptive interpolation filters to achieve the best coding performance. The proposed scheme is implemented into the HM 12.1 software and. Experimental results show that the proposed scheme achieves 3.18 percent bit rate saving on average compared with HEVC.

关键词： Interpolation Adaptive filters Encoding software Data compression multimedia communication

来源：评论

学校读者我要写书评

暂无评论

A fast sub-pixel motion estimation algorithm for HEVC

A fast sub-pixel motion estimation algorithm for HEVC

引用

International Symposium on Circuits and Systems

作者： Shan Jia Wenpeng Ding Yunhui Shi Baocai Yin Beijing Key Laboratory of Multimedia and Intelligent Software Technology College of Metropolitan Transportation Beijing University of Technology Beijing China School of software technology DLUT Dalian China Beijing Key Laboratory of Multimedia and Intelligent Software Technology Beijing University of Technology Beijing China

ISBN: (纸本)9781479953424

Many fast integer-pixel motion estimation algorithms have been developed for the High Efficiency Video Coding Standard, however the speed of sub-pixel motion estimation still has room for improvement. A fast sub-pixel motion estimation algorithm is proposed in this paper to speed up the sub-pixel search process. First, the proposed scheme skips sub-pixel search process in smooth prediction units. Then a fast sub-pixel search algorithm based on texture direction analysis is proposed to further reduce the computational complexity of subpixel motion estimation. The simulation results show that compared with the Full Sub-pixel Search (FSPS), the encoding complexity of the whole motion estimation process can be reduced by an average of 40.9% with negligible coding performance loss.

关键词： texture direction video coding HEVC motion estimation (ME) subpixel search

来源：评论

学校读者我要写书评

暂无评论

Social network search based on semantic analysis and learning

引用

CAAI Transactions on Intelligence technology 2016年第4期1卷 293-302页

作者： Feifei Kou Junping Du Yijiang He Lingfei Ye Beijing Key Laboratory of Intelligent Telecommunication Software and Multimedia School of Computer Science Beijing University of Posts and Telecommunications Beijing 100876 China

Because of everyone＇s involvement in social networks, social networks are full of massive multimedia data, and events are got released and disseminated through social networks in the form of multi-modal and multi-attribute heterogeneous data. There have been numerous researches on social network search. Considering the spatio-temporal feature of messages and social relationships among users, we summarized an overall social network search framework from the perspective of semantics based on existing researches. For social network search, the acquisition and representation of spatio-temporal data is the basis, the semantic analysis and modeling of social network cross-media big data is an important component, deep semantic learning of social networks is the key research field, and the indexing and ranking mechanism is the indispensable part. This paper reviews the current studies in these fields, and then main challenges of social network search are given. Finally, we give an outlook to the prospect and further work of social network search.

关键词： Semantic analysis Semantic learning Cross-modal Social network search

来源：评论

学校读者我要写书评

暂无评论

Gossip-Based Resource Location Strategy in Interest Community for P2P Networks

引用

Chinese Journal of Electronics 2015年第2期24卷 272-280页

作者： HE Ming ZHANG Yujie MENG Xiangwu School of Computer Science Beijing University of Posts and Telecommunications Beijing Key Laboratory of Intelligent Telecommunications Software and Multimedia

Resource location strategy has become very popular for mass data distribution in complex and dynamic network. Searching for the objects is a fundamental problem to unstructured Peer to peer(P2P) networks. In this paper, we propose a resource location strategy for user requirements, which employs the collaborative exchange of information between peers to construct interest communities. This strategy can gather similar peers and disseminate useful information among them. Furthermore, we design an algorithm in unstructured P2 P systems named Appropriate degree gossip search algorithm(ADGSA). Using this search algorithm, the performance including search success ratio, recall rate and search response time has been improved dramatically. An efficient resource location system with a fast organization of users cluster based on their requirements can be provided, preventing the creation of unliked communities. The simulation results show that our strategy has better search efficiency, short response time and high recall ratio.

关键词： Unstructured P2P network Resource location Interest community Gossip-based search Flooding

来源：评论

学校读者我要写书评

暂无评论

A constrained sparse representation approach for video anomaly detection

A constrained sparse representation approach for video anoma...

引用

2016 IEEE Advanced Information Management,Communicates,Electronic and Automation Control Conference(IMCEC 2016)

作者： Yugen Yi Xiaohui Li Rui Zhao Chao Bi Jianzhong Wang Hui Sun School of Software Jiangxi Normal University College of Computer Science and Information Technology Key Laboratory of Intelligent Information Processing of Jilin UniversitiesNortheast Normal University College of Humanities and Sciences Northeast Normal University

ISBN: (纸本)9781509001668

Sparse representation based anomaly detection algorithms have received a widely interest in recent ***,most of the existing approaches fail to pay attention to the manifold structure of the video data,which has been pointed to be important for data *** overcome this limitation,we develop a new sparse coding algorithm named constrained sparse representation(CSR) for video anomaly detection,which explicitly takes the manifold structure of data into *** assumes that each sample's sparse coding coefficient can be linearly reconstructed by the coding coefficients of its ***,CSR algorithm can obtain relatively smoothly sparse representations along the manifold of *** apply the proposed CSR model to video abnormal event detection task and conduct extensive experiments on the UMN *** experimental results demonstrate that our proposed CSR model performed better than some related algorithms.

关键词： local geometrical structure sparse representation abnormal event detection

来源：评论

学校读者我要写书评

暂无评论

Design and implementation of tourism activity recognition and discovery system 12

Design and implementation of tourism activity recognition an...

引用

12th World Congress on intelligent Control and Automation, WCICA 2016

作者： Yifan, Yuan Junping, Du Dan, Fan Lee, Jangmyung Beijing Key Laboratory of Intelligent Telecommunication Software and Multimedia School of Computer Science Beijing University of Posts and Telecommunications No. 10 Xitucheng Road Haidian District Beijing China Department of Electronics Engineering Pusan National University Busan Korea Republic of

ISBN: (纸本)9781467384148

With the rapid development of technologies, such as cloud computing, big data and so forth, tourism big data has drawn the attention of many scholars. How to make full use of a large amount of raw data from tourism activity, and how to recognize and discover tourism activity quickly, accurately and conveniently from information which is accumulated over a long period have become a new direction of tourism data application. In this paper, text analysis, text classification and other relevant technologies are combined based on text mining. Furthermore, a tourism activity recognition and discovery system is designed and implemented, which has achieved the recognition and discovery of tourism activity from a large amount of information. The research results could contribute to recommending and predicting tourism activity in China. © 2016 IEEE.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

A real-time people number detection algorithm of scenic spot based on density center clustering 12

A real-time people number detection algorithm of scenic spot...

引用

12th World Congress on intelligent Control and Automation, WCICA 2016

作者： Yaomin, Wen Junping, Du Meiyu, Liang Dan, Fan Lee, Jangmyung Beijing Key Laboratory of Intelligent Telecommunication Software and Multimedia School of Computer Science Beijing University of Posts and Telecommunications No. 10 Xitucheng Road Haidian District Beijing China Department of Electronics Engineering Pusan National University Busan Korea Republic of

ISBN: (纸本)9781467384148

In recent years, accidents occur frequently because the people number of scenic spots is lack of control. In this paper, a novel real-time people number detection algorithm of scenic spot based on density center clustering (DPBC) is proposed. Taking account of the complexity of the scenic environment, we use the Gauss mixture model (GMM) to suppress the background interference, extract the feature points from the crowd and cluster these feature points by applying a clustering algorithm based on density center. Then we establish a training set and estimate the people number by using the support vector regression model (SVR). We implement the proposed algorithm based on Opencv and use PETS dataset to validate the effectiveness of our proposed algorithm. Experimental results demonstrate that compared with Aibiol algorithm and Conte algorithm, our proposed algorithm improved the accuracy for estimating the people number in a scenic spot. © 2016 IEEE.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

A RANSAC-ANN based credit risk assessment method for petty loan

引用

Journal of Computational Information Systems 2015年第14期11卷 5079-5089页

作者： Li, Shuang Zhang, Yong Hu, Yongli Guo, Aqi Beijing Key Laboratory of Multimedia and Intelligent Software Technology College of Metropolitan Transportation Beijing University of Technology Beijing China

Micro-credit companies mushroomed in China in recent years. Those companies are requiring a much more efficient and accurate way to assess credit risk. Therefore, there is a growing trend in applying machine learning methods to credit risk analysis recently, such as back propagation artificial neural networks (BPANN), support vector machine (SVM) and etc. These methods have well performances but they are still lack of robustness while processing data with outliers. In this paper, we proposed a new method that combines random sample consensus (RANSAC) and BPANN which will help with dealing data which includes outliers. For validation, two real world credit datasets are used to test the effectiveness of our proposed method. The findings of the study reveal the RANSAC-ANN based method to be a promising alternative for credit risk assessment. ©, 2015, Journal of Computational Information Systems. All right reserved.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

MULTI-FEATURE INDEXING FOR IMAGE RETRIEVAL BASED ON HYPERGRAPH

MULTI-FEATURE INDEXING FOR IMAGE RETRIEVAL BASED ON HYPERGRA...

引用

2016 4th IEEE International Conference on Cloud Computing and Intelligence Systems（IEEE CCIS2016）

作者： Zihang Xu Junping Du Lingfei Ye Dan Fan Beijing Key Laboratory of Intelligent Telecommunication Software and Multimedia School of Computer ScienceBeijing University of Posts and Telecommunications

ISBN: (纸本)9781509012572

Based on the fact that tourism photos on the Internet have a lot of additional information, we proposed a novel tourism image retrieval method based on hypergraph(HMIR). The proposed method utilizes hypergraph to establish the relationship among different types of low-level visual features of images and their additional information(such as shooting locations, user-defined tags, etc.), and the fusion of different features is then performed at the offline indexing stage using random walk and similar image set(SI) replacement. Then Bag of Words method is used for image retrieval at online query stage. During online retrieval stage, we only need to extract local descriptors from queries, and can get semantic-aware retrieval results. Experiments show that compared with several other image retrieval methods based on single feature or multiple feature, the proposed method can improve the performance of image retrieval using different evaluation methods.

关键词： CBIR Indexing Hypergraph Multi-feature Random walk

来源：评论

学校读者我要写书评

暂无评论

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：

请选择收藏分类：

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

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：