Kiyuharu Aizawa

University of Tokyo, Japan

Virtual Exploration in a City -- Renovation of Movie Map


Abstract: In this talk, we introduces our work on a Movie Map, which will enable users to explore a given city area using 360 degree videos. Visual exploration of a city is always needed. Nowadays, we are familiar with Google Street View (GSV) that is an interactive visual map. Despite the wide use of GSV, it provides sparse images of streets, which often confuses users and lowers user satisfaction. Forty years ago, a video-based interactive map was created -- it is well-known as Aspen Movie Map. Movie Map uses videos instead of sparse images and improves the user experience dramatically. However, Aspen Movie Map was based on analog technology with a huge effort and never built again. Thus, we renovate the Movie Map using state-of-the-art technology. We build a new Movie Map system with an interface for exploring cities. Using 360 videos captured along streets in a certain area of a city, we can build an interactive Movie Map -- dividing videos into segments by intersections, synthesizing turning views.   

By connecting the video segments following the specified movement in an area, we can watch a walking view along a street. We demonstrate the system in the talk.

Bio: Kiyoharu Aizawa received the B.E., the M.E., and the Dr.Eng. degrees in Electrical Engineering all from the University of Tokyo, in 1983, 1985, and 1988, respectively. He is currently a Professor at Department of Information and Communication Engineering of the University of Tokyo. He was a Visiting Assistant Professor at University of Illinois from 1990 to 1992. His research interest is in multimedia applications, image processing, and computer vision.

He received Young Engineer Award (1987) and Best Paper Award (1990,1998), Achievement Award (1991), Electronics Society Award (1999) from IEICE Japan, and Fujio Frontier Award (1998), Best Paper Award (2002,2009), Achievement Award (2013, 2021),  from ITE Japan. He received the IBM Japan Science Prize in 2002. He is on the Editorial Boards of IEEE MultiMedia, ACM TOMM, APSIPA Transactions on Signal and Information Processing, and International Journal of Multimedia Information Retrieval. He served as the Editor in Chief of the Journal of ITE Japan, an Associate Editor of IEEE Trans. Image Processing, IEEE Trans. CSVT and IEEE Trans. Multimedia. He was the president of ITE and ISS society of IEICE, 2019 and 2018, respectively. He is a Vice President of IEICE and VRSJ. He has served a number of international and domestic conferences; he was a General co-Chair of ACM Multimedia 2012 and ACM ICMR2018. He is a Fellow of IEEE, IEICE, ITE, and a council member of Science Council of Japan.

Mark Liao

Academic Sinica, Taiwan

YOLOv4 & Scaled YOLOv4 and Their Applications to Smart Transportation


Abstract:  YOLOv4 has been ranked first in the world object detection competition for two and a half months.  It defeated the R&D teams of international companies such as Google, Amazon, Facebook, Microsoft, and Qualcomm.  The birth of YOLOv4 is actually closely related to a project ``Development of Smart Transportation System.’’

This project is funded by the Ministry of Science and Technology, and it has led to a four-year cooperative relationship between the Academia Sinica and the listed company Elan Electronics.  This keynote speech will explain in detail the beginning and end of the implementation of this smart transportation project, and how to develop YOLOv4, the fastest and most accurate object detector in the world during the execution of the project.

Bio: Mark Liao received his Ph.D degree in electrical engineering from Northwestern University in 1990. In July 1991, he joined the Institute of Information Science, Academia Sinica, Taiwan and currently, is a Distinguished Research Fellow and Director.  He has worked in the fields of multimedia information processing, computer vision, pattern recognition, multimedia protection, and artificial intelligence for more than 30 years.  He was appointed as an Honorary Chair Professor of National Chiao-Tung University from 2016 to 2019.  He received the Young Investigators' Award from Academia Sinica in 1998; the Distinguished Research Award from the National Science Council in 2003, 2010 and 2013; the Academia Sinica Investigator Award in 2010; the TECO Award from the TECO Foundation in 2016, and the 64th Academic Award from the Ministry of Education in 2020.  His professional activities include: President, Image Processing and Pattern Recognition Society of Taiwan (2006-08); Editorial Board Member, ACM Computing Surveys (2018 – present), IEEE Signal Processing Magazine (2010-13); Associate Editor, IEEE Transactions on Image Processing (2009-13), IEEE Transactions on Information Forensics and Security (2009-12) and IEEE Transactions on Multimedia (1998-2001).  He has been a Fellow of the IEEE since 2013.