检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Li, Xiaomeng Yu, Lequan Fu, Chi-Wing Fang, Meng Heng, Pheng-Ann Department of Computer Science and Engineering Chinese University of Hong Kong Hong Kong Shenzhen Key Laboratory of Virtual Reality and Human Interaction Technology Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China Tencent AI Lab United States

The goal of few-shot learning is to recognize new visual concepts with just a few amount of labeled samples in each class. Recent effective metric-based few-shot approaches employ neural networks to learn a feature similarity comparison between query and support examples. However, the importance of feature embedding, i.e., exploring the relationship among training samples, is neglected. In this work, we present a simple yet powerful baseline for few-shot classification by emphasizing the importance of feature embedding. Specifically, we revisit the classical triplet network from deep metric learning, and extend it into a deep K-tuplet network for few-shot learning, utilizing the relationship among the input samples to learn a general representation learning via episode-training. Once trained, our network is able to extract discriminative features for unseen novel categories and can be seamlessly incorporated with a non-linear distance metric function to facilitate the few-shot classification. Our result on the miniImageNet benchmark outperforms other metric-based few-shot classification methods. More importantly, when evaluated on completely different datasets (Caltech-101, CUB-200, Stanford Dogs and Cars) using the model trained with miniImageNet, our method significantly outperforms prior methods, demonstrating its superior capability to generalize to unseen classes. Copyright © 2019, The Authors. All rights reserved.

关键词： Image classification

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

A Novel Nonlinear Parameter Estimation Method of Soft Tissues

引用

Genomics, Proteomics & Bioinformatics 2017年第6期15卷 371-380页

作者： Qianqian Tong Zhiyong Yuan Mianlun Zheng Xiangyun Liao Weixu Zhu Guian Zhang School of Computer Wuhan University Shenzhen Key Laboratory of Virtual Reality and Human Interaction Technology Shenzhen Institutes of Advanced TechnologyChinese Academy of Sciences

The elastic parameters of soft tissues are important for medical diagnosis and virtual surgery simulation. In this study, we propose a novel nonlinear parameter estimation method for soft tissues. Firstly, an in-house data acquisition platform was used to obtain external forces and their corresponding deformation values, To provide highly precise data for estimating nonlinear param- eters, the measured forces were corrected using the constructed weighted combination forecasting model based on a support vector machine （WCFM_SVM）. Secondly, a tetrahedral finite element parameter estimation model was established to describe the physical characteristics of soft tissues, using the substitution parameters of Young＇s modulus and Poisson＇s ratio to avoid solving compli- cated nonlinear problems. To improve the robustness of our model and avoid poor local minima, the initial parameters solved by a linear finite element model were introduced into the parameter estimation model. Finally, a self-adapting Levenberg-Marquardt （LM） algorithm was presented, which is capable of adaptively adjusting iterative parameters to solve the established parameter estimation model. The maximum absolute error of our WCFM SVM model was less than 0.03 Newton, resulting in more accurate forces in comparison with other correction models tested. The maximum absolute error between the calculated and measured nodal displacements was less than 1.5 mm, demonstrating that our nonlinear parameters are precise.

关键词： Nonlinear parameter estimation Finite element method Substitution parameters Force correction Self-adapting Levenberg-Marquardt algorithm

来源：评论

学校读者我要写书评

暂无评论

Revisiting Shadow Detection: A New Benchmark Dataset for Complex World

arXiv

引用

arXiv 2019年

作者： Hu, Xiaowei Wang, Tianyu Fu, Chi-Wing Jiang, Yitong Wang, Qiong Heng, Pheng-Ann The Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong Shenzhen Key Laboratory of Virtual Reality and Human Interaction Technology Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China

Shadow detection in general photos is a nontrivial problem, due to the complexity of the real world. Though recent shadow detectors have already achieved remarkable performance on various benchmark data, their performance is still limited for general real-world situations. In this work, we collected shadow images for multiple scenarios and compiled a new dataset of 10,500 shadow images, each with labeled ground-truth mask, for supporting shadow detection in the complex world. Our dataset covers a rich variety of scene categories, with diverse shadow sizes, locations, contrasts, and types. Further, we comprehensively analyze the complexity of the dataset, present a fast shadow detection network with a detail enhancement module to harvest shadow details, and demonstrate the effectiveness of our method to detect shadows in general situations. Copyright © 2019, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Measuring insight into multi-dimensional data from a combination of a scatterplot matrix and a HyperSlice visualization 8th

Measuring insight into multi-dimensional data from a combina...

引用

8th International Conference on Digital human Modeling and Applications in Health, Safety, Ergonomics, and Risk Management, DHM 2017, held as part of 19th International Conference on human-computer interaction, HCI 2017

作者： Valdez, André Calero Gebhardt, Sascha Kuhlen, Torsten W. Ziefle, Martina Human-Computer Interaction Center RWTH Aachen University Campus-Boulevard 57 Aachen Germany Virtual Reality Group RWTH Aachen University Kopernikusstr. 6 Aachen Germany

ISBN: (纸本)9783319584652

Understanding multi-dimensional data and in particular multi-dimensional dependencies is hard. Information visualization can help to understand this type of data. Still, the problem of how users gain insights from such visualizations is not well understood. Both the visualizations and the users play a role in understanding the data. In a case study, using both, a scatterplot matrix and a HyperSlice with six-dimensional data, we asked 16 participants to think aloud and measured insights during the process of analyzing the data. The amount of insights was strongly correlated with spatial abilities. Interestingly, all users were able to complete an optimization task independently of self-reported understanding of the data. © Springer International Publishing AG 2017.

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

Anchor-based nearest class mean loss for convolutional neural networks

arXiv

引用

arXiv 2018年

作者： Hao, Fusheng Cheng, Jun Wang, Lei Wang, Xinchao Cao, Jianzhong Hu, Xiping Tao, Dapeng Xi'an Institute of Optics and Precision Mechanics CAS China University of Chinese Academy of Sciences Shenzhen Key Laboratory of Virtual Reality and Human Interaction Technology Shenzhen Institutes of Advanced Technology CAS Department of Computer Science Stevens Insititute of Technology

Discriminative features are critical for machine learning applications. Most existing deep learning approaches, however, rely on convolutional neural networks (CNNs) for learning features, whose discriminant power is not explicitly enforced. In this paper, we propose a novel approach to train deep CNNs by imposing the intra-class compactness and the inter-class separability, so as to enhance the learned features' discriminant power. To this end, we introduce anchors, which are predefined vectors regarded as the centers for each class and fixed during training. Discriminative features are obtained by constraining the deep CNNs to map training samples to the corresponding anchors as close as possible. We propose two principles to select the anchors, and measure the proximity of two points using the Euclidean and cosine distance metric functions, which results in two novel loss functions. These loss functions require no sample pairs or triplets and can be efficiently optimized by batch stochastic gradient descent. We test the proposed method on three benchmark image classification datasets and demonstrate its promising results. Copyright © 2018, The Authors. All rights reserved.

关键词： Anchors

来源：评论

学校读者我要写书评

暂无评论

AGlobal benchmark of algorithms for segmentinglate gadolinium-enhanced cardiac magnetic resonance imaging

arXiv

引用

arXiv 2020年

作者： Xiong, Zhaohan Xia, Qing Hu, Zhiqiang Huang, Ning Bian, Cheng Zheng, Yefeng Vesal, Sulaiman Ravikumar, Nishant Maier, Andreas Yang, Xin Heng, Pheng-Ann Ni, Dong Li, Caizi Tong, Qianqian Si, Weixin Puybareau, Elodie Khoudli, Younes Géraud, Thierry Chen, Chen Bai, Wenjia Rueckert, Daniel Xu, Lingchao Zhuang, Xiahai Luo, Xinzhe Jia, Shuman Sermesant, Maxime Liu, Yashu Wang, Kuanquan Borra, Davide Masci, Alessandro Corsi, Cristiana De Vente, Coen Veta, Mitko Karim, Rashed Preetha, Chandrakanth Jayachandran Engelhardt, Sandy Qiao, Menyun Wang, Yuanyuan Tao, Qian Nuñez-Garcia, Marta Camara, Oscar Savioli, Nicolo Lamata, Pablo Zhao, Jichao Auckland Bioengineering Institute University of Auckland Auckland New Zealand State Key Lab of Virtual Reality Technology and Systems Beihang University Beijing China School of Electronics Engineering and Computer Science Peking University Beijing China SenseTime Inc Shenzhen China Tencent Jarvis Laboratory Shenzhen China Pattern Recognition Lab Friedrich-Alexander-Universität Erlangen-Nürnberg Erlangen Germany Department of Computer Science and Engineering Chinese University of Hong Kong Hong Kong National-Regional Key Technology Engineering Laboratory for Medical Ultrasound School of Biomedical Engineering Shenzhen University Shenzhen China School of Computer Science Wuhan University Wuhan China Shenzhen Key Laboratory of Virtual Reality and Human Interaction Technology Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China Epita Research and Development Laboratory Paris France Department of Computing Imperial College London London United Kingdom School of Naval Architecture Shanghai Jiao Tong University Ocean & Civil Engineering Shanghai China School of Data Science Fudan University Shanghai China Epione Research Group Universite Cote d'Azur Inria Sophia Antipolis France Harbin Institute of Technology School of Computer Science and Technology Harbin China Department of Electric University of Bologna Electronic and Information Engineering Cesena Italy Department of Biomedical Engineering Eindhoven University of Technology Eindhoven Netherlands School of Biomedical Engineering and Imaging Sciences Kings College London London United Kingdom Faculty of Electrical Engineering and Information Technology University of Magdeburg Magdeburg Germany Heidelberg University Hospital Germany Biomedical Engineering Center Fudan University Shanghai China Department of Radiology Leiden University Medical Center Leiden Netherlands Department of Information and Communication Technologies Universitat Pompeu Fabra Barcelona Spain D

Segmentation of cardiac images, particularly late gadolinium-enhanced magnetic resonance imaging (LGE-MRI)widely used for visualizing diseased cardiacstructures, is a crucial first step for clinical diagnosis and treatment. However, direct segmentation ofLGE-MRIsischallenging due to *** most clinical studies have relied on manual and labor-intensive approaches, automatic methods are of high interest, particularly optimized machine learning *** address this, we organized the "2018 Left Atrium Segmentation Challenge" using 154 3D LGE-MRIs, currently the world's largest cardiac LGE-MRI dataset, and associated labels of the left atriumsegmented by three medical experts,ultimately attractingthe participation of27 international teams. In this paper, extensive analysis of the submitted algorithms using technical and biological metrics was performed by undergoing subgroup analysis and conducting hyper-parameter analysis,offeringan overall picture ofthe major design choices of convolutional neural networks(CNNs) and practical considerations for achieving state-of-the-art left atrium segmentation. Results show the top methodachieved a dice score of 93.2%and a mean surface to a surface distance of 0.7mm, significantly outperforming prior state-of-the-art. Particularly, our analysisdemonstrated that double, sequentially usedCNNs, in which a first CNN is used for automatic region-of-interestlocalization and a subsequent CNN is used for refinedregional segmentation, achieved far superiorresults than traditional methods and pipelinescontaining *** findings from this study can potentially be extended to other imaging datasets and modalities, having an impact on the wider medical imaging *** large-scale benchmarking study makes a significant step towards much-improved segmentation methods for cardiac LGE-MRIs, and will serveas animportant benchmark for evaluating and comparing the future works in the field. Copyright © 2020, Th

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Deep Multi-Model Fusion for Single-Image Dehazing

Deep Multi-Model Fusion for Single-Image Dehazing

引用

International Conference on computer Vision (ICCV)

作者： Zijun Deng Lei Zhu Xiaowei Hu Chi-Wing Fu Xuemiao Xu Qing Zhang Jing Qin Pheng-Ann Heng South China University of Technology Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institutes of Advanced Technology CAS The Chinese University of Hong Kong State Key Laboratory of Subtropical Building Science Guangdong Provincial Key Lab of Computational Intelligence and Cyberspace Information Sun Yat-sen University The Hong Kong Polytechnic University CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology CAS

ISBN: (数字)9781728148038

ISBN: (纸本)9781728148045

This paper presents a deep multi-model fusion network to attentively integrate multiple models to separate layers and boost the performance in single-image dehazing. To do so, we first formulate the attentional feature integration module to maximize the integration of the convolutional neural network (CNN) features at different CNN layers and generate the attentional multi-level integrated features (AMLIF). Then, from the AMLIF, we further predict a haze-free result for an atmospheric scattering model, as well as for four haze-layer separation models, and then fuse the results together to produce the final haze-free image. To evaluate the effectiveness of our method, we compare our network with several state-of-the-art methods on two widely-used dehazing benchmark datasets, as well as on two sets of real-world hazy images. Experimental results demonstrate clear quantitative and qualitative improvements of our method over the state-of-the-arts.

关键词： Atmospheric modeling Predictive models Scattering Computational modeling Neural networks computer vision Solid modeling

来源：评论

学校读者我要写书评

暂无评论

The use of semantics in the CrossCult H2020 project 2nd

The use of semantics in the CrossCult H2020 project

引用

2nd COST Action IC1302 International KEYSTONE Conference on Semantic Keyword-Based Search on Structured Data Sources, IKC 2016

作者： Bampatzia, Stavroula Bravo-Quezada, Omar Gustavo Antoniou, Angeliki Nores, Martín López Wallace, Manolis Lepouras, George Vassilakis, Costas Human-Computer Interaction and Virtual Reality Lab Department of Informatics and Telecommunications University of the Peloponnese Tripolis22 131 Greece GIHP4C Research Group Universidad Politécnica Salesiana Cuenca Ecuador Department of Telematics Engineering AtlantTIC Research Centre University of Vigo Vigo Spain Knowledge and Uncertainty Research Laboratory Department of Informatics and Telecommunications University of the Peloponnese Tripolis22 131 Greece

ISBN: (纸本)9783319536392

CrossCult is a newly started project that aims to make reflective history a reality in the European cultural context. In this paper we examine how the project aims to take advantage of advances in semantic technologies in order to achieve its goals. Specifically, we see what the quest for reflection is and, through practical examples from two of the project’s flagship pilots, explain how semantics can assist in this direction. © Springer International Publishing AG 2017.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Towards automatic semantic segmentation in volumetric ultrasound 20th

Towards automatic semantic segmentation in volumetric ultra...

引用

20th International Conference on Medical Image Computing and computer-Assisted Intervention, MICCAI 2017

作者： Yang, Xin Yu, Lequan Li, Shengli Wang, Xu Wang, Na Qin, Jing Ni, Dong Heng, Pheng-Ann Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong Hong Kong Department of Ultrasound Affliated Shenzhen Maternal and Child Healthcare Hospital of Nanfang Medical University Shenzhen China National-Regional Key Technology Engineering Laboratory for Medical Ultrasound School of Biomedical Engineering Health Science Center Shenzhen University Shenzhen China School of Nursing Centre for Smart Health The Hong Kong Polytechnic University Hong Kong Hong Kong Shenzhen Key Laboratory of Virtual Reality and Human Interaction Technology Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China

ISBN: (纸本)9783319661810

3D ultrasound is rapidly emerging as a viable imaging modality for routine prenatal examinations. However, lacking of efficient tools to decompose the volumetric data greatly limits its widespread. In this paper, we are looking at the problem of volumetric segmentation in ultrasound to promote the volume-based, precise maternal and fetal health monitoring. Our contribution is threefold. First, we propose the first and fully automatic framework for the simultaneous segmentation of multiple objects, including fetus, gestational sac and placenta, in ultrasound volumes, which remains as a rarely-studied but great challenge. Second, based on our customized 3D Fully Convolutional Network, we propose to inject a Recurrent Neural Network (RNN) to flexibly explore 3D semantic knowledge from a novel, sequential perspective, and therefore significantly refine the local segmentation result which is initially corrupted by the ubiquitous boundary uncertainty in ultrasound volumes. Third, considering sequence hierarchy, we introduce a hierarchical deep supervision mechanism to effectively boost the information flow within RNN and further improve the semantic segmentation results. Extensively validated on our in-house large datasets, our approach achieves superior performance and presents to be promising in boosting the interpretation of prenatal ultrasound volumes. Our framework is general and can be easily extended to other volumetric ultrasound segmentation tasks. © 2017, Springer International Publishing AG.

关键词： Ultrasonics

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：