检索结果-内蒙古大学图书馆

第35届中国控制会议

作者： LI Haifeng HU Zunhe CHEN Xinwei College of Computer Science and Technology Civil Aviation University of China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Department of Computer Science Minjiang University

ISBN: (纸本)9781509009107

A robust optical flow-based visual odometry method using a single onboard camera is proposed in this *** improve the quality of the noisy optical flows,a correction method across multiple frames is ***,the optical flows in the plane at infinity are detected and removed as these optical flows have very low signal to noise ratio for robot translation ***,a RANSAC approach for robot ego-motion estimation is *** experiments are carried out and the results show that the proposed method is able to estimate the camera trajectory robustly with reasonable accuracy.

关键词： visual odometry optical flows mobile robot

来源：评论

学校读者我要写书评

暂无评论

Variational neural machine translation

Variational neural machine translation

引用

2016 Conference on Empirical Methods in Natural Language processing, EMNLP 2016

作者： Zhang, Biao Xiong, Deyi Su, Jinsong Duan, Hong Zhang, Min Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou215006 China Xiamen University Xiamen361005 China

ISBN: (纸本)9781945626258

Models of neural machine translation are often from a discriminative family of encoder-decoders that learn a conditional distribution of a target sentence given a source sentence. In this paper, we propose a variational model to learn this conditional distribution for neural machine translation: a variational encoder-decoder model that can be trained end-to-end. Different from the vanilla encoder-decoder model that generates target translations from hidden representations of source sentences alone, the variational model introduces a continuous latent variable to explicitly model underlying semantics of source sentences and to guide the generation of target translations. In order to perform efficient posterior inference and large-scale training, we build a neural posterior approximator conditioned on both the source and the target sides, and equip it with a reparameterization technique to estimate the variational lower bound. Experiments on both Chinese-English and English-German translation tasks show that the proposed variational neural machine translation achieves significant improvements over the vanilla neural machine translation baselines. © 2016 Association for Computational Linguistics

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

Enabling fast recovery from unanticipated data access failure in named data networking 16

Enabling fast recovery from unanticipated data access failur...

引用

11th International Conference on Future Internet Technologies, CFI 2016

作者： Hu, Xiaoyan Gong, Jian School of Computer Science and Engineering Southeast University Nanjing China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education China Jiangsu Provincial Key Laboratory of Computer Network Technology China

ISBN: (纸本)9781450341813

We show that an aggregated Interest in Named Data Networking (NDN) may fail to retrieve desired data as the Interest sent upstream in advance is recognized as a duplicate one due to its multipath forwarding and dropped by an upstream node. Furthermore, we introduce NDRUDAF, a mechanism based on negative acknowledgement for the router that aggregates the Interests to detect such unanticipated data access failure and assist the requester whose Interest is aggregated fast recovering from the failure. We qualitatively analyze the performance of the NDN with our proposal NDRUDAF and compare its performance with that of the present NDN. NDRUDAF improves the system performance in case of the unanticipated data access failure in terms of data access delay and network resource utilization efficiency at routers. © Copyright 2016 ACM.

关键词： Routers

来源：评论

学校读者我要写书评

暂无评论

Survey of key technologies on millimeter-wave CMOS integrated circuits

引用

IOP Conference Series: Materials Science and Engineering 2018年第1期351卷

作者： Fei Yu Lei Gao Lixiang Li Shuo Cai Wei Wang Chunhua Wang Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation & School of Computer and Communication Engineering Changsha University of Science and Technology Changsha 410114 China College of Information Science and Engineering Hunan University Changsha 410082 China

In order to provide guidance for the development of high performance millimeter-wave complementary metal oxide semiconductor (MMW-CMOS) integrated circuits (IC), this paper provides a survey of key technologies on MMW-CMOS IC. Technical background of MMW wireless communications is described. Then the recent development of the critical technologies of the MMW-CMOS IC are introduced in detail and compared. A summarization is given, and the development prospects on MMW-CMOS IC are also discussed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Nuclear norm regularized coding with local position-patch and nonlocal similarity for face hallucination

引用

Digital Signal processing 2017年 64卷 107-120页

作者： Guangwei Gao Jian Yang Zhihui Lai Pu Huang Jielin Jiang Hao Gao Dong Yue Institute of Advanced Technology Nanjing University of Posts and Telecommunications Nanjing 210023 PR China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou 350121 PR China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing 210094 PR China College of Computer Science and Software Engineering Shenzhen University Shenzhen 518060 PR China Key Laboratory of Image and Video Understanding for Social Safety Nanjing University of Science and Technology Nanjing 210094 PR China School of Computer and Software Nanjing University of Information Science and Technology Nanjing 210044 PR China

Learning-based face hallucination methods have received much attention and progress in past few decades. Specially, position-patch based approaches have been proposed to replace the probabilistic graph-based or manifold learning-based ones. As opposed to the existing patch based methods, where the input image patch matrix is converted into vectors before combination coefficients calculation, in this paper, we propose to directly use the image matrix based regression model for combination coefficients computation to preserve the essential structural information of the input patch matrix. For each input low-resolution (LR) patch matrix, its combination coefficients over the training image patch matrices at the same position can be computed. Then the corresponding high-resolution (HR) patch matrix can be obtained with the LR training patches replaced by the corresponding HR ones. The nonlocal self-similarities are finally utilized to further improve the hallucination performance. Various experimental results on standard face databases indicate that our proposed method outperforms some state-of-the-art algorithms in terms of both visual quantity and objective metrics.

关键词： Face hallucination Position-patch Matrix based regression Nuclear norm Nonlocal similarity

来源：评论

学校读者我要写书评

暂无评论

Variational neural discourse relation recognizer

Variational neural discourse relation recognizer

引用

2016 Conference on Empirical Methods in Natural Language processing, EMNLP 2016

作者： Zhang, Biao Xiong, Deyi Su, Jinsong Liu, Qun Ji, Rongrong Duan, Hong Zhang, Min Xiamen University Xiamen361005 China Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou215006 China ADAPT Centre School of Computing Dublin City University Ireland Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China

ISBN: (纸本)9781945626258

Implicit discourse relation recognition is a crucial component for automatic discourse-level analysis and nature language understanding. Previous studies exploit discriminative models that are built on either powerful manual features or deep discourse representations. In this paper, instead, we explore generative models and propose a variational neural discourse relation recognizer. We refer to this model as VarNDRR. VarNDRR establishes a directed probabilistic model with a latent continuous variable that generates both a discourse and the relation between the two arguments of the discourse. In order to perform efficient inference and learning, we introduce neural discourse relation models to approximate the prior and posterior distributions of the latent variable, and employ these approximated distributions to optimize a reparameterized variational lower bound. This allows VarNDRR to be trained with standard stochastic gradient methods. Experiments on the benchmark data set show that VarNDRR can achieve comparable results against state-of-the-art baselines without using any manual features. © 2016 Association for Computational Linguistics

关键词： Gradient methods

来源：评论

学校读者我要写书评

暂无评论

A Forward-Secure Multi-Receiver Signcryption Scheme

引用

Journal of Harbin Institute of technology(New Series) 2016年第5期23卷 53-61页

作者： Zhimin Yu Zhengjun Jing Hua Yang Chunsheng Gu Key Laboratory of Cloud Computing and Intelligent Information Processing of Changzhou City Jiangsu University of Technology Changzhou Jiangsu 213001 China College of Computer Nanjing University of Posts and Telecommunications Nanjing 210003 China State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences Beijing 100093 China

In order to protect historical ciphertext when the private key leaked in the broadcasting system,the forward-secure multi-receiver signcryption scheme is designed based on the generic graded multilinear mapping encoding structure,which effectively prevents illegal access from intruder to the ciphertext in the past time period when the private key in current time period is *** the generalization of the existing multilinear mapping encoding system,it proposes the generic graded multilinear mapping encoding structure and the generic graded decision Diffie-Hellman *** of the generic graded multilinear mapping encoding system adopted,almost all candidate multilinear mapping encoding systems can automatically adapt to our *** the assumption of generic graded decision Diffie-Hellman problem,it has proved that the scheme has the information confidentiality and unforgeability in the current time *** putting forward the security model of forward-secure multi-receiver signcryption scheme,and under the assumption of generic graded decision Diffie-Hellman problem,it has proved that the scheme has the message forward-confidentiality and *** with other forward-secure public key encryption schemes,the relationship between our scheme and time periods is sub-linear,so it is less complex.

关键词： multilinear mapping forward-secure multi-receiver signcryption confidentiality unforgeability

来源：评论

学校读者我要写书评

暂无评论

Learning robust and discriminative low-rank representations for face recognition with occlusion

引用

Pattern Recognition 2017年 66卷 129-143页

作者： Guangwei Gao Jian Yang Xiao-Yuan Jing Fumin Shen Wankou Yang Dong Yue Institute of Advanced Technology Nanjing University of Posts and Telecommunications Nanjing China Jiangsu Engineering Laboratory of Big Data Analysis and Control for active distribution network Nanjing University of Posts and Telecommunications Nanjing China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control (Minjiang University) Fuzhou China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China School of Automation Nanjing University of Posts and Telecommunications Nanjing China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China School of Automation Southeast University Nanjing China

For robust face recognition tasks, we particularly focus on the ubiquitous scenarios where both training and testing images are corrupted due to occlusions. Previous low-rank based methods stacked each error image into a vector and then used L 1 or L 2 norm to measure the error matrix. However, in the stacking step, the structure information of the error image can be lost. Depart from the previous methods, in this paper, we propose a novel method by exploiting the low-rankness of both the data representation and each occlusion-induced error image simultaneously, by which the global structure of data together with the error images can be well captured. In order to learn more discriminative low-rank representations, we formulate our objective such that the learned representations are optimal for classification with the available supervised information and close to an ideal-code regularization term. With strong structure information preserving and discrimination capabilities, the learned robust and discriminative low-rank representation (RDLRR) works very well on face recognition problems, especially with face images corrupted by continuous occlusions. Together with a simple linear classifier, the proposed approach is shown to outperform several other state-of-the-art face recognition methods on databases with a variety of face variations.

关键词： Face recognition Low-rank matrix recovery Nuclear norm

来源：评论

学校读者我要写书评

暂无评论

Combining Event-level and Cross-event Semantic information for Event-Oriented Relation Classification by SCNN

Combining Event-level and Cross-event Semantic Information f...

引用

第十五届全国计算语言学学术会议(CCL2016)暨第四届基于自然标注大数据的自然语言处理国际学术研讨会(NLP-NABD-2016)

作者： Siyuan Ding Yu Hong Shanshan Zhu Jianmin Yao Qiaoming Zhu Provincial Key Laboratory of Computer Information Processing Technology Soochow UniversitySuzhouChina

Previous researches on event relation classification primarily rely on lexical and syntactic *** this paper,we use a Shallow Convolutional Neural Network(SCNN)to extract event-level and cross-event semantic features for event relation *** the one hand,the shallow structure alleviates the over-fitting problem caused by the lack of diverse relation *** the other hand,the utilization and combination of event-level and cross-event semantic information help improve relation *** experimental results show that our approach outperforms the state of the art.

关键词： Event Relation Classification Semantic information Frame Embedding SCNN

来源：评论

学校读者我要写书评

暂无评论

Active transfer learning of matching query results across multiple sources

引用

Frontiers of computer Science 2015年第4期9卷 595-607页

作者： Jie XIN Zhiming CUI Pengpeng ZHAO Tianxu HE The Institute of Intelligent Information Processing and Application Soochow University Suzhou 215006 China Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou 215006 China

Entity resolution （ER） is the problem of identi- fying and grouping different manifestations of the same real world object. Algorithmic approaches have been developed where most tasks offer superior performance under super- vised learning. However, the prohibitive cost of labeling training data is still a huge obstacle for detecting duplicate query records from online sources. Furthermore, the unique combinations of noisy data with missing elements make ER tasks more challenging. To address this, transfer learning has been adopted to adaptively share learned common structures of similarity scoring problems between multiple sources. Al- though such techniques reduce the labeling cost so that it is linear with respect to the number of sources, its random sam- piing strategy is not successful enough to handle the ordinary sample imbalance problem. In this paper, we present a novel multi-source active transfer learning framework to jointly select fewer data instances from all sources to train classi- fiers with constant precision/recall. The intuition behind our approach is to actively label the most informative samples while adaptively transferring collective knowledge between sources. In this way, the classifiers that are learned can be both label-economical and flexible even for imbalanced or quality diverse sources. We compare our method with the state-of-the-art approaches on real-word datasets. Our exper- imental results demonstrate that our active transfer learning algorithm can achieve impressive performance with far fewerlabeled samples for record matching with numerous and var- ied sources.

关键词： entity resolution active learning transfer learn-ing convex optimization

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：