检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Liu, Qian Chen, Bei Liu, Haoyan Lou, Jian-Guang Fang, Lei Zhou, Bin Zhang, Dongmei State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University China State Key Lab of Software Development Environment Beihang University China Microsoft Research Beijing China

Context-dependent semantic parsing has proven to be an important yet challenging task. To leverage the advances in context-independent semantic parsing, we propose to perform follow-up query analysis, aiming to restate context-dependent natural language queries with contextual information. To accomplish the task, we propose STAR, a novel approach with a well-designed two-phase process. It is parser-independent and able to handle multifarious follow-up scenarios in different domains. Experiments on the FollowUp dataset show that STAR outperforms the state-of-the-art baseline by a large margin of nearly 8%. The superiority on parsing results verifies the feasibility of follow-up query analysis. We also explore the extensibility of STAR on the SQA dataset, which is very promising. Copyright © 2019, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Improved BP classifier via distance for sample reduction

引用

Journal of computers (Taiwan) 2019年第2期30卷 1-13页

作者： Wen, Jia Deng, Jia Liu, Peng-Fei Wang, Hong-Jun Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Yanshan University Qinhuangdao China School of Information Science and Engineering Yanshan University Qinhuangdao China State Key Laboratory of Software Engineering of Hebei Province Yanshan University Qinhuangdao China

The BP neural network algorithm is a commonly used technique in the classification field of pattern recognition, which iterates training samples continuously to obtain the decision boundary, until the error reaches the convergence precision. However, due to the extensive redundancy of training samples, this carpet-like training method can easily lead to slow network convergence and low classification performance. In this paper, from the view of sample, a novel BP training method called improved BP Classifier algorithm using Distance for Sample Reduction (DRBP) is proposed. Through the sample weight to get the new training sample, which are the near of the classification interface like support vector, and then iterative training BP classifier to solve the classification issue. The main function of this method is to keep the original sample information, realize the sample reduction, and improve the generalization ability of the BP neural network. First, point sets is used to visualize the training process. And then use 10 sets of the University of California Irvine (UCI) to verify the effectiveness and superiority of our experiments. Finally through Cross-validation, the classification error rate of 10 sets of UCI datasets tested by DRBP training method is lower than that of standard BP neural network (STBP). So the result of the experiment showed that the method of the combined distance sample reduce with BP network can significantly enhance the generalization ability of BP network. © 2019 computer Society of the Republic of China. All rights reserved.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Inception classification and object detection based joint-CNN for indoor scene classification

Inception classification and object detection based joint-CN...

引用

2018 International MultiConference of Engineers and computer Scientists, IMECS 2018

作者： Tian, Yarding Zhang, Weitong Zhang, Qieshi Lu, Gang School of Computer Science Shaanxi Normal University Xi'an China Shenzhen Key Laboratory of Virtual Reality and Human Interaction Technology Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China

ISBN: (纸本)9789881404886

While convolutional neural network (CNN) has been successfully used in many fields including single-label scene classification, it is vital to note that real world scenes generally contain multiple semantics and multi-label, especially in the indoor scene classification due to its content complexity. At the same time, most approaches try to make the network much deeper to make sure that they can extract more detail information. However, the deeper network will cause a lot of problems such as the increase of computational costs and network costs and so on. In order to solve these problems, this paper presents a novel framework which called Joint-CNN based on the proposed special label extraction and network structure. Extensive experiments on various data sets show that our method has enhanced the performance on MIT indoor67 and SUN397 data sets. © 2018 Newswood Limited. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Procedural Placement of Existing Building Models in virtual Cities

Procedural Placement of Existing Building Models in Virtual ...

引用

International Conference on virtual Reality and Visualization (ICVRV)

作者： Cando Efren Xun Luo Andres Adolfo Navarro Newball Andres Navarro Cadavid Carlos Lozano-Garzón School of Computer Science and Engineering Tianjin University of Technology Tianjin China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China Pontifical Javeriana University ICESI University Los Andes University

ISBN: (数字)9781728147529

ISBN: (纸本)9781728147536

Procedural urban scene generation can show a lot of insights about infrastructure, organization and development of a city, and find itself many applications in different fields. On the other hand, in many cases the available information from satellite images and terrestrial dataset is limited, leaving considerable blank spaces in the generated virtual city. How to fill the blank spaces in order to obtain a more realistic scene is thus an important problem to be solved by designers. Designers usually spent enormous time and effort to create three-dimensional (3D) urban models using 3D modeling software. Importing building models manually one by one to cover the blank spaces in a large urban setting can be labor-intensive and also means high cost of time. Enlightened by these observations, this study is aimed at the design and implementation of an algorithm focusing on 1) the identification and positioning of blank spaces in a virtual urban area and 2) the automatic filling of such blank spaces, importing 3D models of existing buildings from a database.

关键词： virtual reality Visualization

来源：评论

学校读者我要写书评

暂无评论

Geographic information science in the era of geospatial big data: A cyberspace perspective

引用

The Innovation 2022年第5期3卷 21-22页

作者： Xintao Liu Min Chen Christophe Claramunt Michael Batty Mei-Po Kwan Ahmad MSenousi Tao Cheng Josef Strobl Arzu Cöltekin John Wilson Temenoujka Bandrova Milan Konecny Paul MTorrens Fengyuan Zhang Li He Jinfeng Wang Carlo Ratti Olaf Kolditz Alexander Klippel Songnian Li Hui Lin Guonian Lu Department of Land Surveying and Geo-Informatics Hong Kong Polytechnic UniversityHong Kong SARKowloonChina Key Laboratory of Virtual Geographic Environment(Ministry of Education of PRC) Nanjing Normal UniversityNanjing 210023China The French Naval Academy Research Institute 29240 Lanveoc-PoulmicFrance The Bartlett Centre for Advanced Spatial Analysis(CASA) University College London(UCL)WC1E 6BT LondonUK Institute of Space and Earth Information Science The Chinese University of Hong KongHong Kong SARShatin 999077China Department of Civil Engineering Cairo University12613 CairoEgypt SpaceTimeLab Department of CivilEnvironmental and Geomatic EngineeringUniversity College London(UCL)WC1E 6BT LondonUK Department of Geoinformatics University of Salzburg5020 SalzburgAustria Institute of Interactive Technologies(IIT) University of Applied Sciences and Arts Northwestern Switzerland FHNW5210 WindischSwitzerland Spatial Sciences Institute University of Southern CaliforniaLos AngelesCA 90007USA Laboratory on Cartography Department of Photogrammetry and CartographyUniversity of ArchitectureCivil Engineering and Geodesy1164 SofiaBulgaria Laboratory on Geoinformatics and Cartography Department of GeographyMasaryk University61137 BrnoCeskáRepublika Computer Science and Engineering Tandon School&Center for Urban Science+ProgressNew York UniversityNew YorkNY 10012USA School of Humanities and Social Science Xi’an Jiaotong UniversityXi’an 710049China Institute of Geographic Sciences and Natural Resources Research Chinese Academy of SciencesBeijing 100101China Department of Urban Studies and Planning Massachusetts Institute of TechnologyCambridgeMA 02139USA Centre for Environmental Research Helmholtz Centre for Environmental Research-UFZ04318 LeipzigGermany Laboratory of Geo-information Science and Remote Sensing Wageningen University&ResearchWageningen 6708the Netherlands Department of Civil Engineering Toronto Metropolitan UniversityTorontoON M5B 2K3Canada School of Geography and Env

The advent of information and communication technology and the Internet of Things have led our society toward a digital *** proliferation of personal computers,smartphones,intelligent autonomous sensors,and pervasive network interactions with individuals have gradually shifted human activities from offline to online and from in person to *** transformation has brought a series of challenges in a variety of fields,such as the dilemma of placelessness,some aspects of timelessness(no time relevance),and the changing relevance of distance in the field of geographic information science(GIScience).In the last two decades,“cyber thinking”in GIScience has received significant attention from different *** instance,human activities in“cyberspace”need to be reconsidered when coupled with the geographic space to observe the first law of geography.

关键词： computer cyber instance

来源：评论

学校读者我要写书评

暂无评论

Learning local feature descriptor with motion attribute for vision-based localization

arXiv

引用

arXiv 2019年

作者： Song, Yafei Zhu, Di Li, Jia Tian, Yonghong Li, Mingyang AI Labs Alibaba Group Hangzhou311121 China National Engineering Laboratory for Video Technology School of Electronics Engineering and Computer Science Peking University Beijing100871 China National Key Laboratory of Virtual Reality Technology and System School of Computer Science and Engineering Beihang University Beijing100191 China

In recent years, camera-based localization has been widely used for robotic applications, and most proposed algorithms rely on local features extracted from recorded images. For better performance, the features used for open-loop localization are required to be short-term globally static, and the ones used for re-localization or loop closure detection need to be long-term static. Therefore, the motion attribute of a local feature point could be exploited to improve localization performance, e.g., the feature points extracted from moving persons or vehicles can be excluded from these systems due to their unsteadiness. In this paper, we design a fully convolutional network (FCN), named MD-Net, to perform motion attribute estimation and feature description simultaneously. MD-Net has a shared backbone network to extract features from the input image and two network branches to complete each sub-task. With MD-Net, we can obtain the motion attribute while avoiding increasing much more computation. Experimental results demonstrate that the proposed method can learn distinct local feature descriptor along with motion attribute only using an FCN, by outperforming competing methods by a wide margin. We also show that the proposed algorithm can be integrated into a vision-based localization algorithm to improve estimation accuracy significantly. Copyright © 2019, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Spatial Pyramid Pooling based Convolutional Autoencoder Network for Loop Closure Detection

Spatial Pyramid Pooling based Convolutional Autoencoder Netw...

引用

IEEE International Conference on Real-time Computing and Robotics (RCAR)

作者： Rong Xiang Yuan Liu Qieshi Zhang Jun Cheng School of Computer Science and Information Security Guilin University of Electronic Technology GuangXi China Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China The Chinese University of Hong Kong Hong Kong China

ISBN: (数字)9781728137261

ISBN: (纸本)9781728137278

Loop closure detection is a crucial module in simultaneous localization and mapping (SLAM), which reduces accumulative error in building environment map. Traditional appearance-based methods for loop closure detection are vulnerable to environmental variations as they mainly rely on hand-crafted features. The convolutional neural networks (ConvNets) can automatically learn feature representation from original image, and it is more robust to illumination changes. However, the ConvNets methods may fail when the viewpoint changes significantly due to it extract global features. In order to solve the problem mentioned above, in this paper, we design an unsupervised network which combines the advantage of the traditional and ConvNets methods, and propose a new module named spatial pyramid pooling based convolution autoencoder (SPP-CAE). We evaluate the performance of the proposed method on several open datasets using precision-recall metric. The results show that our method is feasible for detecting loops and is more robust than state-of-the-art methods.

关键词： Feature extraction Convolution Lighting Visualization Training Simultaneous localization and mapping Network architecture

来源：评论

学校读者我要写书评

暂无评论

Procedural Animation Generation technology of virtual Fish Flock

Procedural Animation Generation Technology of Virtual Fish F...

引用

International Conference on virtual Reality and Visualization (ICVRV)

作者： Andrea Pilco Xun Luo Andres Adolfo Navarro Newball Claudia Zúñiga Carlos Lozano-Garzón School of Computer Science and Engineering Tianjin University of Technology Tianjin China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China Pontifical Javeriana University Santiago Cali University Los Andes University

ISBN: (数字)9781728147529

ISBN: (纸本)9781728147536

Flocking refers to the collective and coherent motion of a large group of animals. In this paper, a procedural animation generation technology of virtual fish flock is described. In our work, each animated character, symbolized by fish, is implemented as an independent actor that navigates according to its local perception of the environment. Motion of the actor obeys the laws of simulated physics, and a set of behaviors are programmed into it by the animator. Flocking behaviors of separation, alignment and cohesion are be recreated. As such, there is no need to script the motions of each individual fish. These kinds of systems are commonly employed when constructing a large-scale battle or a herd of animals. With this work, we are able to simulate flocking behavior using autonomous agents with simple movement rules.

关键词： Conferences virtual reality Visualization

来源：评论

学校读者我要写书评

暂无评论

Fine-Grained Thyroid Nodule Classification via Multi-Semantic Attention Network

Fine-Grained Thyroid Nodule Classification via Multi-Semanti...

引用

IEEE International Conference on Bioinformatics and Biomedicine

作者： Shuai Li Yuting Guo Wenfeng Song Zhennan Pang Aimin Hao Bo Zhang Hong Qin State Key Laboratory of Virtual Reality Technology and Systems Beihang University Department of Ultrasound Chinese Academy of Medical Science & Peking Union Medical College Hospital Department of Computer Science Stony Brook University

ISBN: (纸本)9781728118680

Thyroid nodule classification in ultrasound images has gained great momentum based on deep convolutional neural networks in recent years. Nevertheless, it is still challenging to intelligently classify the fine-grained thyroid nodules, which is significant for the subsequent clinical treatments. The difficulties mainly stem from four aspects: few fine-grained training dataset, highly-variable appearances of intra-class nodules, overall-similar characteristics of inter-class nodules, and the low resolution and contrast degree of the ultrasonic images as well as the influence of intrinsic speckle noises. In this paper, we propose a multi-semantic attention networks (MSAN) for fine-grained thyroid nodule classification in ultrasound images. Specifically, we employ a main network branch for coarse granularity feature extraction, which only focuses on the benign and malignant characteristics, and simultaneously employ multi-semantic network branches to extract discriminative features from the fine-grained pathological categories. Meanwhile, we introduce an self-attention scheme together with global average pooling (GAP) in our network, which facilitates to learn from the dynamically-selected nodule regions ranging from local to global. Extensive experiments demonstrate that, our MSAN gives rise to significant improvement of classification accuracy and outperforms the state-of-the-art methods.

关键词： Thyroid ultrasonography Multi-label learning Self-attention Fine-grained classification Convolutional neural networks Thyroid Nodule Taxonomy Ultrasonography nodule Network speckle noise

来源：评论

学校读者我要写书评

暂无评论

Pfa-scannet: Pyramidal feature aggregation with synergistic learning for breast cancer metastasis analysis

arXiv

引用

arXiv 2019年

作者： Zhao, Zixu Lin, Huangjing Chen, Hao Heng, Pheng-Ann Department of Computer Science and Engineering Chinese University of Hong Kong Hong Kong Imsight Medical Technology Co. Ltd. Hong Kong Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China

Automatic detection of cancer metastasis from whole slide images (WSIs) is a crucial step for following patient staging and prognosis. Recent convolutional neural network based approaches are struggling with the trade-off between accuracy and computational efficiency due to the difficulty in processing large-scale gigapixel WSIs. To meet this challenge, we propose a novel Pyramidal Feature Aggregation ScanNet (PFA-ScanNet) for robust and fast analysis of breast cancer metastasis. Our method mainly benefits from the aggregation of extracted local-to-global features with diverse receptive fields, as well as the proposed synergistic learning for training the main detector and extra decoder with semantic guidance. Furthermore, a high-efficiency inference mechanism is designed with dense pooling layers, which allows dense and fast scanning for gigapixel WSI analysis. As a result, the proposed PFA-ScanNet achieved the state-of-the-art FROC of 90.2% on the Camelyon16 dataset, as well as competitive kappa score of 0.905 on the Camelyon17 leaderboard. In addition, our method shows leading speed advantage over other methods, about 7.2 min per WSI with a single GPU, making automatic analysis of breast cancer metastasis more applicable in the clinical usage. Copyright © 2019, The Authors. All rights reserved.

关键词： Diseases

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：