VALSE Webinar改版说明:
自2019年1月起,VALSE Webinar改革活动形式,由过去每次一个讲者的方式改为两种可能的形式:
1)Webinar专题研讨:每次活动有一个研讨主题,先邀请两位主题相关的优秀讲者做专题报告(每人30分钟),随后邀请额外的2~3位嘉宾共同就研讨主题进行讨论(30分钟)。
2)Webinar特邀报告:每次活动邀请一位资深专家主讲,就其在自己熟悉领域的科研工作进行系统深入的介绍,报告时间50分钟,主持人与主讲人互动10分钟,自由问答10分钟。
报告时间:2019年4月17日(星期三)晚上20:00(北京时间)
主题:3D视觉与深度学习
主持人:周晓巍(浙江大学)
报告嘉宾:黄其兴(The University of Texas at Austin)
报告题目:Extreme Relative Pose Estimation for RGB-D Scans via Scene Completion
报告嘉宾:苏昊(University of California, San Diego)
报告题目:Understanding the 3D Environments for Interactions
Panel议题:
三维视觉现在已经有哪些成功应用的案例?以及未来可能将要成熟的应用?
三维视觉未来的发展趋势是什么?哪些三维视觉问题在接下来几年内会成为热点?
深度学习为三维视觉带来了哪些新的可能性?三维视觉里哪些问题中传统方法已经被深度学习所超越,有哪些问题是深度学习目前无法解决的?
三维视觉应用中(比如重建、姿态估计)的训练数据很难标注,如何解决?
目前的三维表达有各种形式,比如点云、网格、体素等等,什么样的表达形式适合什么样的应用场景?未来会不会有一种统一通用的表达形式?
深度学习时代如何培养学生,尤其是博士生?三维视觉方向的学生培养有什么特殊性?
三维视觉有什么特有的研究问题和应用场景?相对应的,这个方向的学生有哪些独特的竞争力?
Panel嘉宾:
黄其兴(The University of Texas at Austin)、苏昊(University of California, San Diego)、施柏鑫(北京大学)、郭裕兰(国防科技大学)、严骏驰(上海交通大学)
*欢迎大家在下方留言提出主题相关问题,主持人和panel嘉宾会从中选择若干热度高的问题加入panel议题!
报告嘉宾:黄其兴(The University of Texas at Austin)
报告时间:2019年4月17日(星期三)晚上20:00(北京时间)
报告题目:Extreme Relative Pose Estimation for RGB-D Scans via Scene Completion
报告人简介:
Qixing Huang is an assistant professor at UT Austin. He obtained his PhD in Computer Science from Stanford University in 2012. From 2012 to 2014 he was a postdoctoral research scholar at Stanford University. Huang was a research assistant professor at Toyota Technological Institue at Chicago from 2014-2016. He received his MS and BS in Computer Science from Tsinghua University. Huang has also interned at Google Street View, Google Research and Adobe Research.
His research spans computer vision, computer graphics, computational biology, and machine learning. In particular, his recent focus is on developing machine learning algorithms (particularly deep learning) that leverage Big Data to solve core problems in computer vision, computer graphics, and computational biology. He is also interested in statistical data analysis, compressive sensing, low-rank matrix recovery, and large-scale optimization, which provide a theoretical foundation for much of his research. He is an area chair of CVPR 2019 and ICCV 2019.
个人主页:
https://www.cs.utexas.edu/~huangqx/
报告摘要:
Estimating the relative rigid pose between two RGB-D scans of the same underlying environment is a fundamental problem in computer vision, robotics, and computer graphics. Most existing approaches allow only limited relative pose changes since they require considerable overlap between the input scans. We introduce a novel approach that extends the scope to extreme relative poses, with little or even no overlap between the input scans. The key idea is to infer more complete scene information about the underlying environment and match on the completed scans. In particular, instead of only performing scene completion from each individual scan, our approach alternates between relative pose estimation and scene completion. This allows us to perform scene completion by utilizing information from both input scans at late iterations, resulting in better results for both scene completion and relative pose estimation. Experimental results on benchmark datasets show that our approach leads to considerable improvements over state-of-the-art approaches for relative pose estimation. In particular, our approach provides encouraging relative pose estimates even between non-overlapping scans.
报告嘉宾:苏昊(University of California, San Diego)
报告时间:2019年4月17日(星期三)晚上20:30(北京时间)
报告题目:Understanding the 3D Environments for Interactions
报告人简介:
Hao Su has been in UC San Diego as Assistant Professor of Computer Science and Engineering since July 2017. He is affiliated with the Contextual Robotics Institute and Center for Visual Computing. He served on the program committee of multiple conferences and workshops on computer vision, computer graphics, and machine learning. He is the Area Chair of CVPR'19, IPC of Pacific Graphics'18, Program Chair of 3DV'17, Publication Chair of 3DV'16, and chair of various workshops at CVPR, ECCV, and ICCV. He is also invited as keynote speakers at workshops and tutorials in NIPS, 3DV and CVPR, S3PM, etc.
Professor Su is interested in fundamental problems in broad disciplines related to artificial intelligence, including machine learning, computer vision, computer graphics, robotics, and smart manufacturing. His work of ShapeNet, PointNet series, and graph CNNs have significantly impacted the emergence and growth of a new field, 3D deep learning. He used to work on ImageNet, a large-scale 2D image database, which is important for the recent breakthrough of computer vision. Applications of Su's research include robotics, autonomous driving, virtual/augmented reality, smart manufacturing, etc.
个人主页:
http://ai.ucsd.edu/~haosu/
报告摘要:
Being able to understand the surrounding in both geometry and physics attributes as we humans do is a key step for building intelligent autonomous agents. This talk will cover a series of research progress in my lab towards this direction, focusing on how machine learning, especially deep learning, can be used to address challenging problems in 3D reconstruction, semantic recognition, and mobility structure induction.
In particular, I will focus on the understanding of object parts. Object parts are handles of actionable information for interaction purposes. Knowing such object part structure and being able to assemble actionable information on parts is thus fundamentally important. I will show how this goal may be achieved by crowd-sourcing as well as algorithmic induction efforts from daily observations.
The content in the talk is based upon latest papers published in SIGGRAPH Asia 2018 and CVPR 2019.
Panel嘉宾:施柏鑫(北京大学)
嘉宾简介:
施柏鑫,分别于2007年、2010年、2013年从北京邮电大学、北京大学、日本东京大学获得工学学士、工学硕士、博士(信息科学与技术)学位。2017年5月入选中组部“千人计划”青年项目。现任北京大学信息科学技术学院数字媒体研究所研究员(“博雅青年学者”)、博士生导师,“相机智能”课题组负责人;北京邮电大学信息与通信工程学院兼职教授、博士生导师。2013至2016年曾先后在麻省理工学院媒体实验室、新加坡科技设计大学、新加坡南洋理工大学从事博士后研究,2016至2017年曾在日本国立产业技术综合研究所人工智能研究中心任研究员。曾获2015年国际计算摄像学大会(ICCP)第二最佳论文,发表于2015年国际计算机视觉大会(ICCV)的论文作为当年最优秀论文之一(1700选9)被邀请投稿至计算机视觉国际期刊(IJCV)。担任亚洲计算机视觉大会ACCV18、英国机器视觉会议BMVC19、国际三维视觉会议3DV19等知名国际会议领域主席;VALSE执行领域主席,CCF计算机视觉专委会委员。
个人主页:
http://www.shiboxin.com
Panel嘉宾:郭裕兰(国防科技大学)
嘉宾简介:
郭裕兰,现任职于国防科技大学电子科学学院。2015年于国防科学技术大学获工学博士学位,2011年至2014年于澳大利亚西澳大学从事访问研究,2016年至2018年在“博新计划”支持下于中科院计算所开展博士后课题研究。主要研究兴趣包括点云特征学习、三维成像、三维目标检测与识别以及三维场景语义分割等基础理论及应用研究。目前已在IEEE TPAMI、IJCV和CVPR等国际期刊和会议上发表论文70余篇,其中ESI热点论文1篇,ESI高被引论文4篇,论文被引用1700余次,合著英文专著1部。目前担任中国图象图形学学会三维视觉专委会秘书长,IET Computer Vision期刊编委。曾担任ACM MM,IJCAI和AAAI等国际会议的程序委员会委员,IEEE TPAMI和IJCV等30余个知名国际期刊的审理人。作为客座编辑在IEEE TPAMI组织专刊一次,在CVPR组织专题讲习班(Tutorial)和研讨会(Workshop)各1次。曾分别获国防科技大学、全军及中国人工智能学会优秀博士学位论文奖。指导研究生获得2016年第十一届中国研究生电子设计竞赛第一名(特等奖)。
个人主页:
http://yulanguo.me/
Panel嘉宾:严骏驰(上海交通大学)
嘉宾简介:
严骏驰,2018年4月起任上海交通大学计算机科学与工程系长聘轨副教授(特别研究员、博士生导师),CCF优博、ACM中国优博提名,于2015年在上海交通大学获得博士学位(委培)。2011年至2018年在IBM中国研究院担任(主管)研究员,2013年在IBM美国沃森研究中心担任访问研究员。于2017年起担任研究院工业视觉首席科学家,主导了华星光电等多家龙头企业的工业检测和预防性维护项目与产品的研发和落地。主要研究方向为机器学习与模式识别,特别是基于时序与结构视角的数据精细化建模。任期刊IEEE TNNLS,PRLetters责任客座编辑,IEEE ACCESS编委,中国图象图形学学会副秘书长、SIGMM中国执委和复旦大学大数据学院校外研究生导师。
个人主页:
http://thinklab.sjtu.edu.cn/
19-09期VALSE在线学术报告参与方式:
长按或扫描下方二维码,关注“VALSE”微信公众号(valse_wechat),后台回复“09期”,获取直播地址。
特别鸣谢本次Webinar主要组织者:
主办AC:周晓巍(浙江大学)
协办AC:郭裕兰(国防科技大学)、严骏驰(上海交通大学)、施柏鑫(北京大学)
责任AC:高盛华(上海科技大学)
活动参与方式:
1、VALSE Webinar活动依托在线直播平台进行,活动时讲者会上传PPT或共享屏幕,听众可以看到Slides,听到讲者的语音,并通过聊天功能与讲者交互;
2、为参加活动,请关注VALSE微信公众号:valse_wechat 或加入VALSE QQ群(目前A、B、C、D、E、F、G、H、I群已满,除讲者等嘉宾外,只能申请加入VALSE J群,群号:734872379);
*注:申请加入VALSE QQ群时需验证姓名、单位和身份,缺一不可。入群后,请实名,姓名身份单位。身份:学校及科研单位人员T;企业研发I;博士D;硕士M。
3、在活动开始前5分钟左右,讲者会开启直播,听众点击直播链接即可参加活动,支持安装Windows系统的电脑、MAC电脑、手机等设备;
4、活动过程中,请不要说无关话语,以免影响活动正常进行;
5、活动过程中,如出现听不到或看不到视频等问题,建议退出再重新进入,一般都能解决问题;
6、建议务必在速度较快的网络上参加活动,优先采用有线网络连接;
7、VALSE微信公众号会在每周四发布下一周Webinar报告的通知及直播链接。
8、Webinar报告的PPT(经讲者允许后),会在VALSE官网每期报告通知的最下方更新[slides]。
9、Webinar报告的视频(经讲者允许后),会更新在VALSE爱奇艺空间,请在爱奇艺关注Valse Webinar进行观看。