Kiyoharu Aizawa

University of Tokyo, Japan

Title: Movie Map and Beyond – Exploring in a City

Abstract: In this talk, we introduce our Movie Map project, which will enable users to explore a given city area using 360 degree videos. Movie Map is originally well known as Aspen Movie Map, that was created more than forty years ago for Surrogate Travel providing virtual driving views in the city. It was based on analog technology – stop motion film camera and analog optical disc storage. It needed a huge effort and never made again. In our project, we have been trying to build Movie Map using technology today and create new functionalities beyond it. Using 360 videos captured along streets in a certain area of a city, we can quickly build an interactive Movie Map -- dividing videos into segments by intersections, synthesizing turning views.   By connecting the video segments and turning views, we can explore the area of the city. We also demonstrate an initial prototype in some areas.

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.


Ophir Frieder

Georgetown University, USA

Title: Searching Multimedia Documents

Abstract: Searching traditional, textual document collections is arguably well understood. However, not all documents are conventional or purely textual. Such is the case for multimedia artifacts.  We explore search in non-traditional environments where queries lack content or context, documents are natively non-digital or include components that are not textual, or a combination thereof. We address machine readability and its implication on search. We overview component segmentation and integration as a search process. We describe the processing of search queries that are informationally deficient in interactive sessions. We then comment on the evaluation of the selected efforts presented and highlight their history from concept to practice. We conclude with a brief commentary on ongoing efforts.

Bio: Ophir Frieder focuses on scalable information processing systems with particular emphasis on health informatics. He is a Fellow of the AAAS, ACM, AIMBE, IEEE, and NAI, and a Member of SIGIR Academy, Academia Europaea, and the European Academy of Sciences and Arts. Heavily involved with industrial efforts, he is the Lead Science and Technology Advisor for Aurora Forge and Chief Scientific Officer of Invaryant, Inc. He is a member of the computer science faculty at Georgetown University and the biostatistics, bioinformatics and biomathematics faculty in the Georgetown University Medical Center.

 

Pavel Zezula

Masaryk University, Czech Republic

Similarity Search for Multimedia Data

 

Abstract: As the current multimedia digital data is weekly structured or unstructured at all, access to required objects is only possible through similarity of their salient features or properties. Accordingly, similarity searching is playing more and more important role in development of multimedia processing applications. In the last twenty years, similarity search technology has matured and many centralized, distributed, and even peer-to-peer architectures have been proposed and implemented. However, the use of similarity searching in numerous potential applications is still a challenge. In the talk, we first explain complexity of the similarity phenomenon and shortly survey the current state of the art in the metric similarity search indexing technology. Their application in the image retrieval, image classification, face recognition, and stream processing will shortly be illustrated. Finally, we concentrate on the content-based retrieval in human motion-capture data. Applications will be illustrated by online prototype implementations. Future research challenges in similarity searching will conclude the talk.

Bio: Pavel Zezula is a professor of Informatics at the Masaryk University, Brno, Czech Republic specializing in research and education in management of data. He spent more than ten years in Italy, cooperating with the Italian National Research Council in Pisa and the University of Bologna. He is co-author of the Similarity Search: The Metric Space Approach book, published by Springer US. He has published more than 120 peer reviewed conference and 40 journal papers with the total count acceding in Scholar Google 7350 citations - he has supervised over 20 PhD students. He participated in more than 20 European projects and received the IBM SUR award for his activities in the “Web Search Similarity Search in Multimedia Data”. Currently is Prof Zezula heading at Masaryk University the DISA (Data Intensive Systems and Applications) laboratory, concentrating on research in Large-Scale Multimodal Data Interpretation. He is a steering committee member of SISAP (Similarity Search and Applications) series of international conferences.