检索结果-内蒙古大学图书馆

arXiv 2018年

作者： Wu, Shu Tang, Yuyuan Zhu, Yanqiao Wang, Liang Xie, Xing Tan, Tieniu Center for Research on Intelligent Perception and Computing National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences University of Chinese Academy of Sciences School of Computer and Communication Engineering University of Science and Technology Beijing School of Software Engineering Tongji University Microsoft Research Asia

The problem of session-based recommendation aims to predict user actions based on anonymous sessions. Previous methods model a session as a sequence and estimate user representations besides item representations to make recommendations. Though achieved promising results, they are insufficient to obtain accurate user vectors in sessions and neglect complex transitions of items. To obtain accurate item embedding and take complex transitions of items into account, we propose a novel method, i.e. Session-based Recommendation with Graph Neural Networks, SR-GNN for brevity. In the proposed method, session sequences are modeled as graph-structured data. Based on the session graph, GNN can capture complex transitions of items, which are difficult to be revealed by previous conventional sequential methods. Each session is then represented as the composition of the global preference and the current interest of that session using an attention network. Extensive experiments conducted on two real datasets show that SR-GNN evidently outperforms the state-of-the-art session-based recommendation methods consistently. Copyright © 2018, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Key technique research on desktop virtualization in cloud environment

引用

International Journal of Modeling, Simulation, and Scientific Computing 2017年第2期8卷 232-240页

作者： Zhuohui Shen Liqin Guo Baocun Hou Hongyan Quan ShuangShuang Zhou College of Computer Science and Software Engineering East China Normal University P.R.China State Key Laboratory of Intelligent Manufacturing System Technology Beijing Institute of Electronic System Engineering P.R.China Beijing Aerospace Smart Manufacturing Technology Development Co.Ltd P.R.China

Desktop Virtualization is an essential problem in cloud manufacturing to make full use of shared resources so as to meet the practical application *** this paper,an efficient virtualization solution for desktop transferring is presented for sharing *** strategy is not limited to transfer desktops between virtual machines(VMs),transmission between virtual and physical machines is also achieved.A three-layer systemic structure based on web environment is proposed in the *** employ the application program library Libvirt and kernel-based virtual machine(KVM)technique to manage VMs with dynamic customization scheme,which gains better virtualization per***,we present two different schemes for desktop graphics *** is based on the transport protocol virtual network computing(VNC),and the other adopts the simple protocol for independent computing environment(SPICE),which both achieve more satisfactory *** validity of our scheme is demonstrated on some experimental results and systemic qualitative evaluation is also provided.

关键词： Virtualization KVM VNC VM SPICE.

来源：评论

学校读者我要写书评

暂无评论

Deep Multi-Metric Learning for Person Re-Identification

Deep Multi-Metric Learning for Person Re-Identification

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Yongxin Ge Xinqian Gu Min Chen Hongxing Wang Dan Yang Key Laboratory of Dependable Service Computing in Cyber Physical Society Ministry of Education (Chongqing University) Chongqing China Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing China School of Big Data & Software Engineering Chongqing University Chongqing China

In this paper, to exploit more discriminative information of the global-body and body-parts features, we present a novel deep multi-metric learning (DMML) network for person re-identification under the triplet framework. The main novelty of our learning framework lies in two aspects: 1) Unlike most existing metric learning-based approaches, which learn only one distance metric for comparison, our DMM-L method aims to learn different metrics for the global-body and body-parts features respectively by using convolutional neural network (CNN); 2) A new multi-metric loss function is proposed to train the DMML network, under which the distance of each negative pair is greater than that of each positive pair by a predefined margin, and the correlations of different metrics are maximized. Compared with the previous person re-identification methods that have shown state-of-the-art performances, our DMML approach can achieve competitive results on the challenging CUHK03, CUHKOl, VIPeR and iLIDS datasets.

关键词： Measurement Image color analysis Feature extraction Training Machine learning Kernel Learning systems

来源：评论

学校读者我要写书评

暂无评论

A Second-Order Variational Framework for Joint Depth Map Estimation and Image Dehazing

A Second-Order Variational Framework for Joint Depth Map Est...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Ryan Wen Liu Shengwu Xiong Huisi Wu Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Nanjing University of Science and Technology Nanjing China School of Computer Science and Technology Wuhan University of Technology Wuhan China College of Computer Science and Software Engineering Shenzhen University Shenzhen China

ISBN: (纸本)9781538646595

Outdoor images captured in poor weather conditions (e.g., fog or haze) commonly suffer from reduced contrast and visibility. Increasing attention has recently been paid to single image dehazing, i.e., improving image contrast and visibility. It is generally thought that the dehazing performance highly depends on the accurate depth information. In this work, we first obtain the initial depth map by using the popular dark channel prior. A unified second-order variational framework is then proposed to refine the depth map and restore the haze-free image. The introduced second-order framework has the capacity of preserving important structures in both depth map and haze-free image. Furthermore, the proposed framework performs well for several different types of haze situations. The resulting optimization problems related to depth map estimation and latent image restoration can be effectively handled using the primal-dual algorithm under a two-step numerical framework. The effectiveness of our proposed method has been demonstrated by comparing the imaging performance with several state-of-the-art dehazing methods.

关键词： Optimization TV Estimation Image restoration Imaging Navigation Computer science

来源：评论

学校读者我要写书评

暂无评论

Seam carving algorithm based on saliency 1st

Seam carving algorithm based on saliency

引用

1st International Conference on Smart Vehicular Technology, Transportation, Communication and Applications, VTCA 2017

作者： Lin, Wen Zhang, Fuquan Lian, Renbao Xu, Lin Chen, Xueyun Kuang, Linghong School of Electronic Information Science Fujian Jiangxia University Fuzhou University Town Fuzhou350108 China School of Software Beijing Institute of Technology Beijing100081 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou350121 China Innovative Information Industry Research Institute Fujian Normal University Fuzhou350300 China Institute of Information Engineering Longyan University Town DongXiao XinLuo District Longyan364012 China School of Information Science and Engineering Fujian University of Technology Fuzhou University Town Fuzhou350118 China

ISBN: (纸本)9783319707297

This paper proposes a seam carving algorithm based on saliency. This algorithm makes saliency detection to the source image. Images are classified according to the gray-scale of saliency detection. Adding different energy protection methods, it can protect the foreground area of a subject and detailed areas of the edge. Then the cumulative energy map is calculated. According to the principle of deleting the minimum energy pixel, single pixel-wide carves chosen to be deleted or copied. The experimental result shows that the algorithm avoids image restoration caused by extracting too many pixels in saliency area and non equal-ratio scaling. It reduces the deformed structures caused by displacement of edge pixel and also improves the integrity of algorithm. © Springer International Publishing AG 2018.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Predicting commercial activeness over urban big data

引用

Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 2017年第3期1卷 1-20页

作者： Yang, Su Wang, Minjie Wang, Wenshan Sun, Yi Gao, Jun Zhang, Weishan Zhang, Jiulong Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University 825 Zhangheng Rd Shanghai201203 China Department of Software Engineering China University of Petroleum Qingdao266580 China School of Computer Science Xian University of Technology Xian710048 China

This study aims at revealing how commercial hotness of urban commercial districts (UCDs) is shaped by social contexts of surrounding areas so as to render predictive business planning. We define social contexts for a given region as the number of visitors, the region functions, the population and buying power of local residents, the average price of services, and the rating scores of customers, which are computed from heterogeneous data including taxi GPS trajectories, point of interests, geographical data, and user-generated comments. Then, we apply sparse representation to discover the impactor factor of each variable of the social contexts in terms of predicting commercial activeness of UCDs under a linear predictive model. The experiments show that a linear correlation between social contexts and commercial activeness exists for Beijing and Shanghai based on an average prediction accuracy of 77.69% but the impact factors of social contexts vary from city to city, where the key factors are rich life services, diversity of restaurants, good shopping experience, large number of local residents with relatively high purchasing power, and convenient transportation. This study reveals the underlying mechanism of urban business ecosystems, and promise social context-aware business planning over heterogeneous urban big data. © 2017 Association for Computing Machinery.

关键词： Ecosystems

来源：评论

学校读者我要写书评

暂无评论

Research on Hot Topics Discovery Based on Short Texts of Online Reviews

引用

Journal of Physics: Conference Series 2019年第1期1288卷

作者： Zhenyan Liu Yueshi Qiu Zhe Zhang Limin Mao Xiaohan Zheng Beijing Key Laboratory of Software Security Engineering Technology School of computer science & Technology Beijing Institute of Technology Beijing 100081 China Academy of Intelligent Collaborative Cloud System China Aerospace Science and Industry Corporation Limited Beijing 100048 China

The two crucial issues for hot topics discovery based on online reviews are that the sparsity of short text features and the 'long tail' phenomenon of hot topics. This paper focuses on these two key issues, and proposes an improved similarity calculation method to calculate the similarity of short texts, and a novel clustering algorithm based on the time factor and dynamic adjustment of comparison times to automatically discard a large number of outliers. Moreover, the validity and advancement of the new method are presented by comparative experiments using real data sets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Efficient Classification of Benign and Malignant Thyroid Tumors Based on Characteristics of Medical Ultrasonic Images

Efficient Classification of Benign and Malignant Thyroid Tum...

引用

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

作者： Junying Chen Haijun You IEEE Guangzhou Key Laboratory of Robotics and Intelligent Software School of Software Engineering South China University of Technology

ISBN: (纸本)9781509001668

As the health issue is being concerned by more and more people,the workload of a clinical doctor becomes *** there are many images to diagnose every day for a medical ultrasonic doctor,image pattern recognition and classification technologies for medical ultrasonic images are necessary to reduce the workload of the clinical *** major image pattern recognition methods include Bayesian pattern classifier,support vector machine method,and neural network *** image pattern classification methods present good image classification performance but require large training dataset and long training *** such,efficient characteristics-based image pattern classification methods were discussed in this paper,standard deviation classification method and aspect ratio classification *** were applied to the recognition and classification of benign and malignant thyroid tumors on medical ultrasonic *** image pattern recognition methods were built upon the inherent characteristics of the benign and malignant thyroid tumors which were presented on the ultrasonic *** efficient classification methods interpreted in the paper demonstrated good classification performance,which verified that the characteristics-based image pattern classification methods can be utilized in effective image classifier construction.

关键词： thyroid tumor classification image processing pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Information tracing model based on PageRank

引用

网络与信息安全学报 2017年第8期3卷 68-76页

作者： LI Qian LAI Jia-wei XIAO Yun-peng WU Bin Beijing Key Laboratory of Intelligent Telecommunications Software and Multimedia Beijing University of Posts and Telecommunications Chongqing Engineering Laboratory of Network and Information Security Chongqing University of Posts and Telecommunications

In social network, original publisher and important nodes in the diffusion process can be traced by analyzing the spreading network of a hot topic. The participated users and spreading network structure of a hot topic build an information tracing model, which mines the source and important diffusion nodes. Firstly, it analyzed the development trend of a hot topic and extracts the users involved. Secondly, it established a user network according to the following relationship of the users involved. Thirdly, the contribution rate of users on the development of the hot topic was initialized, and the Page Rank algorithm was used to construct the information tracing model. Finally, the Top k users were selected as the information publisher and important users of the hot topic according to the contribution rate. Experimental results showed that our model can effectively discover the hot topic of the publisher and important users.

关键词：计算机网络网络管理应用程序信息安全

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection Based on Spatio-Temporal and Sparse Features of Network Traffic in VANETs

Anomaly Detection Based on Spatio-Temporal and Sparse Featur...

引用

2019 IEEE Global Communications Conference (GLOBECOM)

作者： Laisen Nie Huizhi Wang Shimin Gong Zhaolong Ning Mohammad S. Obaidat Kuei-Fang Hsiao School of Electronics and Information Northwestern Polytechnical University Xi'an P.R.China Qingdao Research Institute of Northwestern Polytechnical University Qingdao P.R.China School of Intelligent Systems Engineering Sun Yat-sen University China State Key Laboratory for Novel Software Technology Nanjing University China ECE Department Nazarbayev University Astana Kazakhstan College of Computing and Informatics University of Sharjah UAE The King Abdullah II School of Information Technology The University of Jordan Amman Jordan University of Science and Technology Beijing China Department of Information Management Ming Chuan University Taiwan

ISBN: (数字)9781728109626

ISBN: (纸本)9781728109633

Vehicular Ad-Hoc Networks (VANETs) have received a great attention recently due to their potential and various applications. However, the initial phase of the VANET has many research challenges that need to be addressed, such as the issues of security and privacy protection caused by the openness of wireless communication networks among the city-wide applied regions. Specially, anomaly detection for a VANET has become a challenging problem, due to the changes in the scenario of VANETs comparing with traditional wireless networks. Motivated by this issue, we focus on the problem of anomaly detection in VANETs, and propose an effective anomaly detection approach based on the convolutional neural network in this paper. The proposed approach takes into account the spatio-temporal and sparse features of VANET traffic, and it uses a convolutional neural network architecture and a loss function based on Mahalanobis distance for anomaly detection. Furthermore, a comprehensive assessment is provided to validate the proposed approach, which illustrates the effectiveness of this approach.

关键词： Anomaly detection Feature extraction Vehicular ad hoc networks Kernel Estimation Security Convolutional neural networks

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：