检索结果-内蒙古大学图书馆

24th ACM multimedia Conference, MM 2016

作者： Wang, Meng Fang, Yi NYU Multimedia and Visual Computing Lab Dept. of ECE NYU Abu Dhabi United Arab Emirates Dept. of CSE NYU Tandon School of Engineering United States

ISBN: (纸本)9781450336031

Identifying accurate correspondences information among different shapes is of great importance in shape analysis such as shape registration, segmentation and retrieval. This paper aims to develop a paradigm to address the challenging issues posed by shape structural variation and symmetry ambiguity. Specifically, the proposed research developed a novel shape signature based on local diffusion map on 3D surface, which is used to identify the shape correspondence through graph matching process. The developed shape signature, named local diffusion map signature (LDMS), is obtained by projecting heat diffusion distribution on 3D surface into 2D images along the surface normal direction with orientation determined by gradients of heat diffusion field. The local diffusion map signature is able to capture the concise geometric essence that is deformation-insensitive and symmetry-aware. Experimental results on 3D shape correspondence demonstrate the superior performance of our proposed method over other state-of-the-art techniques in identifying correspondences for non-rigid shapes with symmetry ambiguity. © 2016 ACM.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

Global consistent shape correspondence for efficient and effective active shape models 16

Global consistent shape correspondence for efficient and eff...

引用

24th ACM multimedia Conference, MM 2016

作者： Wang, Meng Fang, Yi NYU Multimedia and Visual Computing Lab Dept. of ECE NYU Abu Dhabi United Arab Emirates Dept. of ECE NYU Tandon School of Engineering United States

ISBN: (纸本)9781450336031

Finding the accurate corresponded landmarks from a collection of shape instances plays critical role in constructing active shape models (ASMs). We have developed a global consistent shape correspondence paradigm for efficient and effective active shape models to address challenging issues in statistical shape modelling. Specifically, in this paper, we developed techniques to perform a fast multiple shape matching to identify global consistent shape correspondence from a set of training shape instances via efficient low-rank recovery optimization. High quality ASMs can then be constructed based on the identified corresponded points. The entire process is unsupervised without manual annotation as well as free of selection of anatomically significant point. Experimental results on mobile hand image data demonstrate the superior performance of our proposed method over other state-of-the-art techniques like MDL in constructing active shape models. © 2016 ACM.

关键词： 3d shape correspondence non-rigid shape matching 3d shape signature

来源：评论

学校读者我要写书评

暂无评论

A 3D Virtual Environment for Training Teachers to Identify Bullying

A 3D Virtual Environment for Training Teachers to Identify B...

引用

Mediterranean Electrotechnical Conference

作者： Kalliopi-Evangelia Stavroulia Antri Ruiz-Harisiou Elena Manouchou Kyriakos Georgiou Francesca Sella Andreas Lanitis Visual Media Computing Lab Department of Multimedia and Graphic Arts Cyprus University of Technology Limassol Cyprus

ISBN: (纸本)9781509000593

Incidents involving bullying in schools present a difficult challenge for educators who need to identify potentially dangerous behaviors in comparison to 'innocent' types of interstudent interactions. In this paper we investigate the use of a dedicated Virtual Reality application as a means of training educators to identify alarming bullying activities. The Virtual Reality environment simulates a typical middle school, where different bullying-related incidents take place. The virtual environment is visualized using a Virtual Reality headset in conjunction with eye tracking techniques that facilitate user interaction. In order to make realistic animations that resemble human motions, state of the art motion tracking equipment was used for generating realistic avatar movements. According to the scenario of the application, the user witness different types of student behavior and he/she has to take decisions on how to control and deal with the situation. The prototype was tested by active teachers who reported that the incidents within the simulation were similar to real life experiences and suggested that the application could be used in teacher training education providing inexperienced teachers feedback on how to recognize and manage bullying.

关键词： bullying virtual learning environments teacher training

来源：评论

学校读者我要写书评

暂无评论

A Feasibility Study on Using Virtual Reality for Understanding Deficiencies of High School Students

A Feasibility Study on Using Virtual Reality for Understandi...

引用

Mediterranean Electrotechnical Conference

作者： Elena Manouchou Kalliopi-Evangelia Stavroulia Antri Ruiz-Harisiou Kyriakos Georgiou Francesca Sella Andreas Lanitis Visual Media Computing Lab Department of Multimedia and Graphic Arts Cyprus University of Technology Limassol Cyprus

ISBN: (纸本)9781509000593

A significant number of high school students face different types of problems that prevent them from attending adequately classes. On the other hand teachers are faced with the daunting task of identifying and addressing problems faced by students. Correcting actions towards student deficiencies imply that teachers are able to fully understand the implications on student activities caused by different types of problems. In this paper we describe a feasibility study that aims to assess the potential of using Virtual Reality as a tool for training teachers to fully understand the difficulties of students suffering from different types of deficiencies. As part of the proposed work, teachers are given the opportunity to participate in a virtual class in the role of students that face certain deficiencies allowing them to experience problems faced by students so that teachers learn how to deal effectively with such cases in real classrooms. In our preliminary investigation we concentrated our attention on the problem of myopia so that teachers who participated in the experiment had the opportunity to attend a class as visually impaired persons. The results of this preliminary investigation indicate that teachers who participated in the experiment showed increased awareness and understanding of the problem. Furthermore, the results revealed the potential of such application for teacher training.

关键词： virtual learning environments vision disorders teacher training

来源：评论

学校读者我要写书评

暂无评论

On the Development and Evaluation of a Serious Game for Forensic Examination Training

On the Development and Evaluation of a Serious Game for Fore...

引用

Mediterranean Electrotechnical Conference

作者： Maria Drakou Andreas Lanitis Visual Media Computing Lab Dept. of Multimedia and Graphic Arts Cyprus University of Technology Limassol Cyprus

ISBN: (纸本)9781509000593

Training for forensic investigations is an important aspect of the overall training procedure in Police Academies around the world. However, the overall complexity of forensic examinations and the sensitive nature of data available in crime scenes limit the possibility of exposing police cadets in different types of real crime scenes. In this paper the plausibility of using dedicated computer games and Virtual Environments for forensic examination training is investigated in order to support the development of computer-based systems for training cadets to perform forensic examinations. This effort, that was carried out in cooperation with the local Police Authorities, involved the collection of information of procedures adopted during forensic investigations, the design and implementation of a computer game to support relevant educational activities and the evaluation phase where the end product was thoroughly evaluated. The results of the evaluation indicate that it is plausible to use dedicated computer games as part of training for forensic examinations.

关键词： virtual reality forensic examination serious game

来源：评论

学校读者我要写书评

暂无评论

Learned binary spectral shape descriptor for 3D shape correspondence

Learned binary spectral shape descriptor for 3D shape corres...

引用

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

作者： Xie, Jin Wang, Meng Fang, Yi NYU Multimedia and Visual Computing Lab United Arab Emirates Department of Electrical and Computer Engineering New York University Abu Dhabi United Arab Emirates Department of Electrical and Computer Engineering NYU Tandon School of Engineering United States

ISBN: (纸本)9781467388511

Dense 3D shape correspondence is an important problem in computer vision and computer graphics. Recently, the local shape descriptor based 3D shape correspondence approaches have been widely studied, where the local shape descriptor is a real-valued vector to characterize the geometrical structure of the shape. Different from these realvalued local shape descriptors, in this paper, we propose to learn a novel binary spectral shape descriptor with the deep neural network for 3D shape correspondence. The binary spectral shape descriptor can require less storage space and enable fast matching. First, based on the eigenvectors of the Laplace-Beltrami operator, we construct a neural network to form a nonlinear spectral representation to characterize the shape. Then, for the defined positive and negative points on the shapes, we train the constructed neural network by minimizing the errors between the outputs and their corresponding binary descriptors, minimizing the variations of the outputs of the positive points and maximizing the variations of the outputs of the negative points, simultaneously. Finally, we binarize the output of the neural network to form the binary spectral shape descriptor for shape correspondence. The proposed binary spectral shape descriptor is evaluated on the SCAPE and TOSCA 3D shape datasets for shape correspondence. The experimental results demonstrate the effectiveness of the proposed binary shape descriptor for the shape correspondence task.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral Image Classification with Markov Random Fields and a Convolutional Neural Network

arXiv

引用

arXiv 2017年

作者： Cao, Xiangyong Zhou, Feng Xu, Lin Meng, Deyu Xu, Zongben Paisley, John IEEE IEEE School of Mathematics and Statistics Xi’an Jiaotong University Xi’an710049 China National Laboratory of Radar Signal Processing Xidian University Xi’an China NYU Multimedia and Visual Computing Lab New York University Abu Dhabi United Arab Emirates Department of Electrical Engineering & Data Science Institute Columbia University New YorkNY United States Columbia University China Scholarship Council

This paper presents a new supervised classification algorithm for remotely sensed hyperspectral image (HSI) which integrates spectral and spatial information in a unified Bayesian framework. First, we formulate the HSI classification problem from a Bayesian perspective. Then, we adopt a convolutional neural network (CNN) to learn the posterior class distributions using a patch-wise training strategy to better use the spatial information. Next, spatial information is further considered by placing a spatial smoothness prior on the labels. Finally, we iteratively update the CNN parameters using stochastic gradient decent (SGD) and update the class labels of all pixel vectors using α-expansion min-cut-based algorithm. Compared with other state-of-the-art methods, the proposed classification method achieves better performance on one synthetic dataset and two benchmark HSI datasets in a number of experimental settings. Copyright © 2017, The Authors. All rights reserved.

关键词： Spectroscopy

来源：评论

学校读者我要写书评

暂无评论

Learned Binary Spectral Shape Descriptor for 3D Shape Correspondence

Learned Binary Spectral Shape Descriptor for 3D Shape Corres...

引用

IEEE Conference on Computer Vision and Pattern Recognition

作者： Jin Xie Meng Wang Yi Fang NYU Multimedia and Visual Computing Lab UAE Department of Electrical and Computer Engineering New York University Abu Dhabi Department of Electrical and Computer Engineering NYU Tandon School of Engineering

ISBN: (纸本)9781467388528

Dense 3D shape correspondence is an important problem in computer vision and computer graphics. Recently, the local shape descriptor based 3D shape correspondence approaches have been widely studied, where the local shape descriptor is a real-valued vector to characterize the geometrical structure of the shape. Different from these real-valued local shape descriptors, in this paper, we propose to learn a novel binary spectral shape descriptor with the deep neural network for 3D shape correspondence. The binary spectral shape descriptor can require less storage space and enable fast matching. First, based on the eigenvectors of the Laplace-Beltrami operator, we construct a neural network to form a nonlinear spectral representation to characterize the shape. Then, for the defined positive and negative points on the shapes, we train the constructed neural network by minimizing the errors between the outputs and their corresponding binary descriptors, minimizing the variations of the outputs of the positive points and maximizing the variations of the outputs of the negative points, simultaneously. Finally, we binarize the output of the neural network to form the binary spectral shape descriptor for shape correspondence. The proposed binary spectral shape descriptor is evaluated on the SCAPE and TOSCA 3D shape datasets for shape correspondence. The experimental results demonstrate the effectiveness of the proposed binary shape descriptor for the shape correspondence task.

关键词： Descriptors 3D shape Spectral shape images computer vision Neural network Correspondence Binary Output Structural shapes tige

来源：评论

学校读者我要写书评

暂无评论

Robust enhancement of depth images from Kinect sensor

Robust enhancement of depth images from Kinect sensor

引用

IEEE Annual International Symposium Virtual Reality

作者： A B M Tariqul Islam Christian Scheel Renato Pajarola Oliver Staadt Visual Computing Lab University of Rostock Germany Visualization and MultiMedia Lab University of Zürich Switzerland

We propose a new method to fill missing or invalid values in depth images generated from the Kinect depth sensor. To fill the missing depth values, we use a robust least median of squares (LMedS) approach. We apply our method for telepresence environments, where Kinects are used very often for reconstructing the captured scene in 3D. We introduce a modified 1D LMedS approach for efficient traversal of consecutive image frames. Our approach solves the unstable nature of depth values in static scenes that is perceived as flickering. We obtain very good result both for static and moving objects inside a scene.

关键词： Three-dimensional displays Cameras Electronic mail Color Noise Robustness Indexes

来源：评论

学校读者我要写书评

暂无评论

Color Object Recognition via Cross-Domain Learning on RGB-D Images

Color Object Recognition via Cross-Domain Learning on RGB-D ...

引用

IEEE International Conference on Robotics and Automation

作者： Yawen Huang Fan Zhu Ling Shao Alejandro F. Frangi the Center for Computational Imaging and Simulation Technologies in Biomedicine (CISTIB) Department of Electronic and Electrical Engineering The University of Sheffield Sheffield United Kingdom the Multimedia and Visual Computing Lab Department of Electrical and Computer Engineering New York University Abu Dhabi Abu Dhabi the Computer Vision and Artificial Intelligence Group Department of Computer Science and Digital Technologies Northumbria University Newcastle upon Tyne United Kingdom

ISBN: (纸本)9781467380270

This paper addresses the object recognition problem using multiple-domain inputs. We present a novel approach that utilizes labeled RGB-D data in the training stage, where depth features are extracted for enhancing the discriminative capability of the original learning system that only relies on RGB images. The highly dissimilar source and target domain data are mapped into a unified feature space through transfer at both feature and classifier levels. In order to alleviate cross-domain discrepancy, we employ a state-of-the-art domain-adaptive dictionary learning algorithm that updates image representations in both domains and the classifier parameters simultaneously. The proposed method is trained on a RGB-D Object dataset and evaluated on the Caltech-256 dataset. Experimental results suggest that our approach can lead to significant performance gain over the state-of-the-art methods.

关键词： RGB-D enhancing discriminative capability

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：