IEEE Conference on Virtual Reality (IEEE VR) 

3rd Workshop
Data4XR

Datasets for Developing Intelligent XR Applications 

Orlando, FL, USA - March 17, 2024

Introduction

Whenever AI researchers want to propose different data-driven models, datasets are the most fundamental resource. They can develop state-of-the-art AI algorithms to achieve excellent prediction performance with easy access to standard datasets. However, when XR researchers decide to import these algorithms for developing intelligent immersive interactive applications, the need for publicly available datasets arises as a challenge despite advanced AI algorithms being developed.

Many works related to datasets have been published, e.g., MINIST, ImageNet, CIFAR-10, etc. To unleash the full power of XR, the community also needs standard datasets for developing data-driven models with machine/deep learning. The workshop on Datasets for Developing Intelligent XR Applications (Data4XR), hosted by the IEEE VR 2024, proposes a meaningful platform for domain researchers to find valuable resources and develop interdisciplinary collaborations. It aims to promote XR research by involving more AI methods, and thus contribute to next-generation XR. 

 Scope

The workshop invites researchers to submit 1) research papers that integrate AI methods into XR studies, 2) technical papers aimed towards introducing published datasets that can be easily accessed and used to develop data-driven models, 3) position papers describing ethics, early-stage concepts, and preliminary ideas for sharable dataset creation and standardization in XR. The submission could be 4-6 pages on any of the following topics but not limited to:

Program

The workshop will be held on Sunday March 17th, 2024. All times are in Orlando time (UTC-4).

 Invited Speaker

Dr. Miao WANG

Miao Wang is an Associate Professor at the State Key Laboratory of Virtual Reality Technology and Systems, Beihang University. His research interests include redirected locomotion and immersive experience in virtual environments, virtual character reconstruction and animation, and neural scene representations and synthesis for VR. Miao completed his Ph.D. in Computer Science at Tsinghua University in 2016 and subsequently pursued postdoctoral research at the same institution before joining Beihang University in 2018. He possesses a publication record with over 40 papers such as ACM TOG, IEEE TVCG, IEEE VR and ISMAR. Since 2020, he has held roles as a program committee member for prominent IEEE VR and ISMAR conferences.

Title: Efficient Locomotion in Large-Scale Virtual Environments

Abstract: In large-scale VR applications, users expect to be able to move freely and interact naturally within virtual environments that far exceed the physical constraints of actual spaces. However, discrepancies in scale and structure between the limited physical environment in which users are situated and the virtual reality scenes they inhabit, as well as among distributed multiple user physical environments, may lead to inconsistent semantics in spatial interactions, mismatched collaborative interaction contexts for multiple users, significantly diminishing both immersion and interaction efficiency. In this talk, I will introduce the endeavors of our group in developing locomotion methods as well as an open-source library and benchmark for redirected walking. These efforts are propelling us toward breaking free from the limitations of physical environment on immersive scene interaction.

 Important dates

 Submission Guidelines

All paper submissions must be in English and must comprise 6 pages maximum, NOT including references. All Data4XR Workshop Paper submissions must be prepared in IEEE Computer Society VGTC format (https://tc.computer.org/vgtc/publications/conference/) and submitted in PDF format. We highly encourage authors to use the LaTeX template. However, authors who choose to use the MS Word template should ensure that the PDF submission matches the PDF format template.

A DOUBLE-BLIND review process will be used. This means that both the authors and the reviewers should remain anonymous to each other. Submissions (including citations) should not contain information that identifies the authors, their institutions, funding sources, or their places of work. Relevant previous work by the authors should be cited in the third person to preserve anonymity. Authors should work diligently to ensure that their submissions do not expose their identities either through carelessness or intentionality. Authors that have questions/issues around double-blind submission policy should contact the conference chairs at the above-mentioned email address.

IEEE VR Workshops proceedings will be published electronically through the IEEE Digital Library.


NOTE: papers rejected from the IEEE VR conference track are encouraged to be resubmitted if they can fit the topic of this workshop. In this case, the authors have to submit 1) the revised version of the paper, 2) the review report from the conference reviewers, 3) one page summary of rebuttal.

Organizing Committee

Yuyang WANG

The Hong Kong University of Science and Technology (Guangzhou), China

Jean-Rémy CHARDONNET

Arts et Métiers Institute of Technology, France


Lik-Hang (Paul) LEE

The Hong-Kong Polytechnic University, China

Pan HUI

The Hong Kong University of Science and Technology (Guangzhou), China

 Contacts

If you have any questions, please contact Yuyang Wang (yuyangwang[at]hkust-gz.edu.cn), Jean-Rémy Chardonnet (jean-remy.chardonnet[at]ensam.eu), Lik-Hang (Paul) Lee (lik-hang.lee[at]polyu.edu.hk) or Pan Hui (panhui[at]ust.hk).