|
Keynote Speakers
 

Prof. Qinping Zhao

Beihang University, China
Academician of Chinese Academy of Engineering

赵沁平,北京航空航天大学计算机学院教授,博士生导师,中国工程院院士

 

赵沁平教授多年来在计算机科学领域进行虚拟现实技术和人工智能基础研究,先后承担了国家自然科学基金重大、重点项目、国家863计划、973计划、国防科技预先研究等20余项国家科研任务。
作为我国最早从事虚拟现实技术的研究者之一,坚持开展虚拟现实技术的研究、开发与应用。建立了我国第一个基于广域专用计算机网络的可支持异地分布式虚拟现实应用的支撑环境DVENET;主持研制了具有自主知识产权的分布交互仿真应用程序开发与运行平台
BH _RTI、和实时三维图形平台天绘;基于上述成果组织开发了若干有影响的虚拟现实应用系统。
创建了中国计算机学会虚拟现实与可视化技术专业委员会。兼任《中国科学》F辑、《计算机研究与发展》副主编,《计算机学报》、《软件学报》等学术刊物编委。在国际、国内学术刊物和国际学术会议发表学术论文180余篇,出版专著3部。获国家发明专利授权50 余项。获国家科技进步一等奖1项、国家科技进步二等奖2项、国家技术发明二等奖1项,获省部级科技奖9项。已培养博士60余人,硕士近百人。

 

 

 

Ruigang Yang
CTO, Inceptio.ai
University of Kentucky, USA
杨睿刚, 美国肯塔基大学,Inceptio.ai CTO

 

Ruigang Yang is CTO of Inceptio.ai. He was the Chief Scientist for 3D Vision at Baidu Research where he led the Robotics and Autonomous Driving Lab (RAL). He is a full professor of Computer Science at the University of Kentucky (on leave). He obtained his PhD degree from University of North Carolina at Chapel Hill and his MS degree from Columbia University. His research interests span over computer graphics and computer vision, in particular in 3D reconstruction and 3D data analysis. He has published over 100 papers, which, according to Google Scholar, has received over 14000 citations with an h-index of 61 (as of 2017). He has received a number of awards, including US NSF Career award in 2004 and the Dean’s Research Award in 2013.

In this talk, I will present our recent work in 3D reconstruction and image synthesis, including texture mapping, reconstruction of glassy and shinning objets, and novel face synthesis method to make VR conferences possible. If time permits, I will also talk about a new method in simulation for autonamous driving, which has been accepted by Science Robotics and reported on the first page of China Daily.

 

 

Prof. Duh,
La Trobe University, Australia
杜本麟, 澳大利亚乐卓博大学, 计算机与信息技术学院院长

 

Professor Duh is the Head and Professor of Department of Computer Science and Information Technology at La Trobe University; Visiting Professor in the Academy of Arts at Tsinghua University and Adjunct Professor in the Graduate Institute of Journalism at National Taiwan University. He received his degrees in psychology, industrial design and engineering respectively and did his postdoctoral training in NASA-Johnson Space Centre involving in virtual reality project. He was a faculty member in Nanyang Technological University and Interactive & Digital Media Institute, National University of Singapore, and University of Tasmania, Australia.
Prof. Duh is a Fellow of British Computer Society, Fellow of the Institution of Engineering and Technology, Companion/Fellow of Engineer Australia, ACM Distinguished Speaker; the Australian National Representative of IFIP TC on HCI; Co-Chiar of IEEE SMC TC on Visual Analytics and Communication; Steering committee member of IEEE ISMAR. He has published more than 150 conference and journal papers in HCI area and received more than 4,700 citations. Professor Duh has served the program/organizing committee for IEEE/ACM International Symposium of Mixed and Augmented Reality (ISMAR) and IEEE Virtual Reality for years. His research focuses on augmented/virtual reality, user experience and interaction design.

杜本麟教授是澳大利亚乐卓博大学计算机与信息技术学院院长。曾任教于新加坡南洋理工大学,新加坡国立大学与澳大利亚塔斯马尼亚大学; 也曾担任清华大学美术与设计学院客座教授,台湾大学新闻研究所、印度韦洛尔科技大学计算机与工程学院兼任教授。澳大利亚计算机学会塔斯马尼亚州理事,北塔斯马尼亚州旅游局董事。目前他也是澳大利亚信息通信技术学院院长委员会、澳大利亚联邦科学与工业研究组织CSIRO/Data61大学规划委员会的委员。

杜教授是一位拥有跨领域研究背景与国际化的学者,研究方向在虚拟现实与增强现实的人机交互,用户体验与交互设计。他是英国工程技术学会会士,英国计算机学会会士,澳大利亚工程师学会会士,ACM杰出讲座 (ACM Distinguished Speaker),国际信息处理联合会人机交互专委会澳州国家代表。IEEE System, Man and Cybernetics Society Visual Analytics and Communication专委会主席。杜教授已发表超过一百五十篇在人机交互设计、数字媒体领域高品质的期刊与研讨会论文,Google Scholar 他引超过 4,700次。部分文章得过论文奖以及高引用率论文;担任超过十七个会议主题演讲和五十个以上的邀请讲座。也担任许多期刊的客座主编,编委,主编,顶级研讨会的大会主席与程序委员会主席。杜教授是增强现实顶会 IEEE ISMAR 2019 与 2020 年的大会主席。

 

 

 

Prof. Wei-Shi Zheng

Sun Yat-sen University, China
郑伟诗, 中山大学

 

Dr. Wei-Shi Zheng is now a Professor with Sun Yat-sen University. His research interests include person/object association and activity understanding in visual surveillance, and the related large-scale machine learning algorithm. He has ever served as area chairs of ICCV, CVPR, BMVC and IJCAI. He is an associate editor of Pattern Recognition. He has ever joined Microsoft Research Asia Young Faculty Visiting Programme. He is a recipient of Excellent Young Scientists Fund of the National Natural Science Foundation of China, and a recipient of Royal Society-Newton Advanced Fellowship of United Kingdom. HOMEPAGE: https://isee-ai.cn/~zhwshi

Topic:Graph-based Action Assessment

Abstract:We present a new model to assess the performance of actions from videos by graph-based joint relation modelling. Action assessment is an emerging research direction in the computer vision community, and it aims to evaluate the standard degree of the action execution with fine-grained descriptions of the visual cues. Previous research works of action assessment mainly focused on the whole scene, including the performer's body and background, yet they ignored the detailed joint interactions. This is insufficient for fine-grained and accurate action assessment since the motion quality of each joint is dependent on its neighboring joints. To address this problem, we propose to learn the detailed joint motion based on the joint relations. We build trainable Joint Relation Graphs, and analyze joint motion on them. We develop two novel modules, namely the Joint Commonality Module and the Joint Difference Module, for joint motion learning. The Joint Commonality Module models the local motion of body parts, and the Joint Difference Module models the motion differences of joints within body parts. The proposed method is further developed to address long-term action assessment. In this talk, we will demonstrate how these developments are applied to assess the operations of chemistry experiments in high school.

郑伟诗博士,中山大学计算机学院教授、副院长、机器智能与先进计算教育部重点实验室副主任。他主要面向大规模智能视频监控里的行人身份识别与行为分析。关于面向大规模监控网络下的行人追踪问题,他在国内外较早和持续深入开展跨视域行人重识别的研究,发表一系列以跨视域度量学习为主线的研究工作,并最近集中展开无监督和弱标注学习建模,力图解决“大数据小标注”下的图像视频分析问题。他已发表170余篇主要学术论文,其中在IEEE Trans. on PAMI(T-PAMI)发表12篇、International Journal of Computer Vision(IJCV)发表3篇、国际A类学术会议论文75篇。他SCI他引3500多次,Google Scholar引用1万多次,担任Pattern Recognition、《自动化学报》等期刊的编委,担任ICCV、CVPR、IJCAI 、BMVC等Area Chair。他是国际IEEE 多媒体系统与应用(MSA)技术委员会委员和国际IEEE 视觉信号处理与通信(VSPC)技术委员会委员。他主持国家重点研发课题一项、国家自然科学基金委-广东大数据科学中心中集成项目重点课题一项及其他5个国家级项目。获全国2020水下目标检测算法赛光学图像赛项一等奖、获CVPR等国际顶级学术会议竞赛第一名3次。获中国图象图形学学会自然科学奖一等奖、广东省自然科学奖一等奖、广东省自然科学奖二等奖等;获国家优秀青年科学基金、英国皇家学会牛顿高级学者基金和广东省创新领军人才项目支持。