检索结果-内蒙古大学图书馆

1st International Conference on Human Interaction and Emerging Technologies, IHIET 2019

作者： Zavlanou, Christina Lanitis, Andreas Visual Media Computing Lab Department of Multimedia and Graphic Arts Cyprus University of Technology 31 Archbishop Kyprianos Street 3603 Limassol Cyprus Research Centre on Interactive Media Smart Systems and Emerging Technologies Nicosia Cyprus

ISBN: (纸本)9783030256289

Age-related changes significantly affect elderly users’ interaction with specific products and services. Nevertheless, the challenges experienced by elderly users are difficult to be perceived and understood, especially by younger people. Inspired by the concept of aging suits, we propose a Virtual Reality-based approach, where age-related visual impairments are simulated in virtual environments. The aim is to provide an approximation of the experience of viewing and interacting with a product, from the perspective of elderly persons with specific age-related visual problems. The effectiveness of the proposed approach is examined through an experiment involving package design evaluation. The experimental results demonstrate that Virtual Reality can play an important role on understanding the challenges that elderly users face, thus support the design of elderly-friendly products. © 2020, Springer Nature Switzerland AG.

关键词： Product design

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

ADAPTIVE WAVELET TRANSFORMER NETWORK FOR 3D SHAPE REPRESENTATION LEARNING 10

ADAPTIVE WAVELET TRANSFORMER NETWORK FOR 3D SHAPE REPRESENTA...

引用

10th International Conference on Learning Representations, ICLR 2022

作者： Huang, Hao Fang, Yi NYU Multimedia and Visual Computing Lab United States Abu Dhabi United Arab Emirates NYU Tandon School of Engineering New York University United States New York University Abu Dhabi United Arab Emirates

We present a novel method for 3D shape representation learning using multi-scale wavelet decomposition. Previous works often decompose 3D shapes into complementary components in spatial domain at a single scale. In this work, we study to decompose 3D shapes into sub-bands components in frequency domain at multiple scales, resulting in a hierarchical decomposition tree in a principled manner rooted in multi-resolution wavelet analysis. Specifically, we propose Adaptive Wavelet Transformer Network (AWT-Net) that firstly generates approximation or detail wavelet coefficients per point, classifying each point into high or low sub-bands components, using lifting scheme at multiple scales recursively and hierarchically. Then, AWT-Net exploits Transformer to enhance the original shape features by querying and fusing features from different but integrated sub-bands. The wavelet coefficients can be learned without direct supervision on coefficients, and AWT-Net is fully differentiable and can be learned in an end-to-end fashion. Extensive experiments demonstrate that AWT-Net achieves competitive performance on 3D shape classification and segmentation benchmarks. © 2022 ICLR 2022 - 10th International Conference on Learning Representationss. All rights reserved.

关键词： Wavelet decomposition

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

Performance driven face animation via non-rigid 3D tracking 09

Performance driven face animation via non-rigid 3D tracking

引用

17th ACM International Conference on multimedia, MM'09, with Co-located Workshops and Symposiums

作者： Zhang, Wei Wang, Qiang Tang, Xiaoou Department of Information Engineering Chinese University of Hong Kong Hong Kong Hong Kong Visual Computing Group Microsoft Research Asia Beijing China Multimedia Lab. Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China

ISBN: (纸本)9781605586083

In this demo, a performance driven 3D face animation system is proposed. The proposed system consists of two key components: a robust non-rigid 3D tracking module and a MPEG4 compliant facial animation module. Firstly, the facial motion is tracked from source videos which contain both the rigid 3D head motion (6 DOF) and the non-rigid expression variations. Afterward, the tracked facial motion is parameterized via estimating a set of MPEG4 facial animation parameters(FAP). As the final step, these FAP values are transferred to the MPEG4-compliant face model for the animation purpose. The proposed tracking and animation system has a strong generalization ability and can be used in the indoor environment with no additional assumptions.

关键词： Animation

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

Height estimation from single aerial images using a deep ordinal regression network

arXiv

引用

arXiv 2020年

作者： Li, Xiang Wang, Mingyang Fang, Yi NYU Multimedia and Visual Computing Lab NYU Tandon and Abu Dhabi United Arab Emirates NYU Multimedia and Visual Computing Lab NYU Tandon United States Department of Electrical and Computer Engineering New York University Abu Dhabi United Arab Emirates

Understanding the 3D geometric structure of the Earth’s surface has been an active research topic in photogrammetry and remote sensing community for decades, serving as an essential building block for various applications such as 3D digital city modeling, change detection, and city management. Previous researches have extensively studied the problem of height estimation from aerial images based on stereo or multiview image matching. These methods require two or more images from different perspectives to reconstruct 3D coordinates with camera information provided. In this paper, we deal with the ambiguous and unsolved problem of height estimation from a single aerial image. Driven by the great success of deep learning, especially deep convolution neural networks (CNNs), some researches have proposed to estimate height information from a single aerial image by training a deep CNN model with large-scale annotated datasets. These methods treat height estimation as a regression problem and directly use an encoder-decoder network to regress the height values. In this paper, we proposed to divide height values into spacing-increasing intervals and transform the regression problem into an ordinal regression problem, using an ordinal loss for network training. To enable multi-scale feature extraction, we further incorporate an Atrous Spatial Pyramid Pooling (ASPP) module to extract features from multiple dilated convolution layers. After that, a post-processing technique is designed to transform the predicted height map of each patch into a seamless height map. Finally, we conduct extensive experiments on ISPRS Vaihingen and Potsdam datasets. Experimental results demonstrate significantly better performance of our method compared to the state-of-the-art methods. Copyright © 2020, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Meta-Learning 3D Shape Segmentation Functions

arXiv

引用

arXiv 2021年

作者： Hao, Yu Huang, Hao Yuan, Shuaihang Fang, Yi NYU Multimedia and Visual Computing Lab New York University Abu Dhabi Abu Dhabi United Arab Emirates

Learning robust 3D shape segmentation functions with deep neural networks has emerged as a powerful paradigm, offering promising performance in producing a consistent part segmentation of each 3D shape. Generalizing across 3D shape segmentation functions requires robust learning of priors over the respective function space and enables consistent part segmentation of shapes in presence of significant 3D structure variations. Existing generalization methods rely on extensive training of 3D shape segmentation functions on large-scale labeled datasets. In this paper, we proposed to formalize the learning of a 3D shape segmentation function space as a meta-learning problem, aiming to predict a 3D segmentation model that can be quickly adapted to new shapes with no or limited training data. More specifically, we define each task as unsupervised learning of shape-conditioned 3D segmentation function which takes as input points in 3D space and predicts the part-segment labels. The 3D segmentation function is trained by a self-supervised 3D shape reconstruction loss without the need for part labels. Also, we introduce an auxiliary deep neural network as a meta-learner which takes as input a 3D shape and predicts the prior over the respective 3D segmentation function space. We show in experiments that our meta-learning approach, denoted as Meta-3DSeg, leads to improvements on unsupervised 3D shape segmentation over the conventional designs of deep neural networks for 3D shape segmentation functions. Copyright © 2021, 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

3DMotion-Net: Learning Continuous Flow Function for 3D Motion Prediction

3DMotion-Net: Learning Continuous Flow Function for 3D Motio...

引用

2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Shuaihang Yuan Xiang Li Anthony Tzes Yi Fang NYU Multimedia and Visual Computing Lab USA New York University Abu Dhabi UAE New York University USA

ISBN: (数字)9781728162126

ISBN: (纸本)9781728162133

This paper deals with predicting future 3D motions of 3D object scans from the previous two consecutive frames. Previous methods mostly focus on sparse motion prediction in the form of skeletons. While in this paper, we focus on predicting dense 3D motions in the form of 3D point clouds. To approach this problem, we propose a self-supervised approach that leverages the power of the deep neural network to learn a continuous flow function of 3D point clouds that can predict temporally consistent future motions and naturally bring out the correspondences among consecutive point clouds at the same time. More specifically, in our approach, to eliminate the unsolved and challenging process of defining a discrete point convolution on 3D point cloud sequences to encode spatial and temporal information, we introduce a learnable latent code to represent the temporal-aware shape descriptor, which is optimized during the model training. Moreover, a temporally consistent motion Morpher is proposed to learn a continuous flow field which deforms a 3D scan from the current frame to the next frame. We perform extensive experiments on D-FAUST, SCAPE, and TOSCA benchmark data sets. The results demonstrate that our approach is capable of handling temporally inconsistent input and produces consistent future 3D motion while requiring no ground truth supervision.

关键词： Training Solid modeling Three-dimensional displays Shape Convolution Benchmark testing Decoding

来源：评论

学校读者我要写书评

暂无评论

Learning Object-Specific Distance From a Monocular Image

Learning Object-Specific Distance From a Monocular Image

引用

International Conference on Computer Vision (ICCV)

作者： Jing Zhu Yi Fang NYU Multimedia and Visual Computing Lab USA New York University USA New York University Abu Dhabi UAE

ISBN: (数字)9781728148038

ISBN: (纸本)9781728148045

Environment perception, including object detection and distance estimation, is one of the most crucial tasks for autonomous driving. Many attentions have been paid on the object detection task, but distance estimation only arouse few interests in the computer vision community. Observing that the traditional inverse perspective mapping algorithm performs poorly for objects far away from the camera or on the curved road, in this paper, we address the challenging distance estimation problem by developing the first end-to-end learning-based model to directly predict distances for given objects in the images. Besides the introduction of a learning-based base model, we further design an enhanced model with a keypoint regressor, where a projection loss is defined to enforce a better distance estimation, especially for objects close to the camera. To facilitate the research on this task, we construct the extented KITTI and nuScenes (mini) object detection datasets with a distance for each object. Our experiments demonstrate that our proposed methods outperform alternative approaches (e.g., the traditional IPM, SVR) on object-specific distance estimation, particularly for the challenging cases that objects are on a curved road. Moreover, the performance margin implies the effectiveness of our enhanced method.

关键词： Estimation Feature extraction Cameras Predictive models Task analysis Roads Training

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：