KIWAIT/IFMIA 2023 Keynote speakers:
Prof.Weisi L.Lin, Nanyang Technological University, Singapore
Prof.Yoko Yamakata, The University of Tokyo, Japan
Dr.Kim HeungMook,ETRI Assistant Vice President, Korea
IFMIA Keynote speakers: add soon
IWAIT Invited speakers:
- Prof.In Kyu Park, Inha University,Korea
- Prof.Masayuki Tanimoto,Nagoya University, Nagoya Industrial Science Research Institute, Japan
- Jong-Il Park, Hanyang University, Korea
Modling Visual Signals for Human and Machine Uses
Speaker: Prof. Weisi L.Lin , Nanyang Technological University, Singapore
Abstract: This talk firstly discusses how to model various visual signals (images, videos, graphics, 3D point clouds, and so on) for humans as the ultimate users. Since humans have developed unique characteristics in perception over the long evolution, effective perceptual signal modeling, processing and evaluation facilitate meaningful optimization of system performance and utilioty of available resources (bandwidth, memory, battery, computation, device cost/size, etc). The related topics include visual attention/saliency, just-noticeable difference (JND), quality of experience (QoE), and different application scenarios.
Machines are expected to become the ultimate users for a rapidly increasing amount of visual signals in this AI era, and therefore as the second part of the talk, we will investigate into the said concepts to be extended with machine tasks, including early examples of machine- oriented JND, and saliency and quality models for 3D point clouds. Finally, possible further research directions will be highlighted, inclusive of exploration toward true multimedia that consists of hearing, smell, touch and even taste aspects as well.
Biography: Weisi Lin is an active researcher in intelligent image processing, perception-based signal modelling and assessment, video compression, and multimedia communication. He had been the Lab Head, Visual Processing, in Institute for Infocomm Research (I 2 R)，Singapore. He is a Professor in School of Computer Science and Engineering, Nanyang Technological University, where he also served as the Associate Chair (Research).
Food Computing for Human and Planet Health
Speaker: Prof. Yoko Yamakata, The University of Tokyo, Japan
Abstract: This keynote introduces food computing technologies for human and planet health. First, let us focus on human health. We are developing RecipeLog and FoodLog Athl, smartphone applications that allow users to upload a photo of a meal, identify the name of the meal through image recognition, calculate nutritional values such as energy, protein, fat, and carbohydrates based on the recipe, and create a food log. Traditionally, dietary management for patients and athletes involved manual analysis by dietitians based on patients’ manual food records, but under and over-reporting, in addition to high human costs for analysis, has been problematic. Our experiments have shown that information obtained by our application is more accurate and at lower human cost than manual recording.
The latter part of the talk will introduce food computing for the planet’s health. In the process of producing food, earth resources are mined to obtain phosphate fertilizer and to extract fuel for breeding and transportation. By calculating the amount of this mining for each food ingredient, it was estimated that, for example, an average of 5.2kg of soil is mined to provide one serving of beef stew. Our goal is to visualize these facts in a way accessible to ordinary people and to change their behavior in making food choices better for all.
Biography: Prof. Yoko Yamakata received her Ph.D. from the Graduate School of Informatics, Kyoto University, in 2006. She served as an expert researcher at NICT and as a lecturer and an associate professor at Kyoto University before becoming a JSPS Research Fellow at the University of Tokyo in 2015; from 2016 to 2017, she was an international visiting researcher at the University of Sussex, UK, working on natural language processing research in recipes. From 2019 to present, she is currently an Associate Professor at the University of Tokyo. Her research interests include multimedia processing, especially in cooking and eating activities. She is serving as the general chair of the Food Computing Workshops CEA21 and CEA++22, and a member of the organizing committees of ICMR2022 and ACM Multimedia Asia 2022 and 2023.
Introduction to Media R&D of ETRI
Speaker: Dr. Kim HeungMook, ETRI Assistant Vice President, Korea
Abstract: This talk introduces the research achievements and the current research topics of ETRI on Media technology which include terrestrial broadcast, audio and video compression, immersive media, media intelligence by AI, and digital holography. And in the latter part of the talk, the future direction of ETRI Media R&D which pursues hyper-realistic spatial media experience will be introduced based on the analysis of recent technology advancements and relevant technologies.
Biography: Dr. HeungMook Kim is an Assistant Vice President who is leading the Media Research Division of ETRI. He has actively participated in the development of transmission technology for terrestrial broadcasting especially for ATSC 1.0 and 3.0. Also he has participated in international standards development in ATSC, DVB, and FOBTV. He was a visiting researcher at the Polytechnic University of Valencia, Spain in 2019 studying on Broadcast and Broadband convergence. His current research interests include multi-platform media delivery and hyper-realistic spatial media.
IWAIT Invited Speakers
Invite Lecture 1: 3D Virtual Human Modeling for Mataverse Applications
Speaker: Prof. In Kyu Park, Inha University, Korea
Abstract: 3D virtual human modeling is the key element of metaverse applications where the gap between the applications’ demand and the level of the SoTA techniques exist. In this talk, I will first introduce the recent trend of 3D human modeling techniques in computer vision and graphics fields. Then, I will introduce the outcome of my recent project during the last 3 years. Finally I will provide the future anticipation of 3D human modeling techniques for metaverse applications.
Biography: In Kyu Park received the B.S., M.S., and Ph.D. degrees from Seoul National University in 1995, 1997, and 2001, respectively, all in electrical engineering and computer science. From September 2001 to March 2004, he was a Member of Technical Staff at Samsung Advanced Institute of Technology. Since March 2004, he has been with the School of Information and Communication Engineering, Inha University, where he is a full professor. From January 2007 to February 2008, he was an exchange scholar at Mitsubishi Electric Research Laboratories. From September 2014 to August 2015, he was a visiting associate professor at MIT Media Lab. From July 2018 to June 2019, he was a visiting scholar at the Center for Visual Computing in University of California, San Diego. Dr. Park’s research interests include the joint area of computer vision and graphics, including computational photography and 3D shape reconstruction with more focus on human face and body. He is a senior member of IEEE and a member of ACM.
Invite Lecture 2: FTV Standardization in MPEG Promoted by a Professor
Speaker: Prof. Masayuki Tanimoto, Nagoya University, Nagoya Industrial Science Research Institute, Japan
Abstract: FTV (Free-viewpoint Television) enables users to view a 3D scene by freely changing their viewpoint, as we do naturally in the real world. FTV is an ultimate 3DTV and ranks as the top of visual media. FTV is immersive media that integrate real and virtual worlds. FTV was realized by developing novel ray capture, processing and display technologies. I have been promoting FTV standardization in 3 phases since 2001. Most of MPEG members come from industry. However, many professors are working actively in MPEG. Moreover, some students are working actively. MPEG provide students with a very good opportunity to improve their skills and accumulate experiences. Here, I talk about my experience in MPEG and how a professor continues FTV activity for 20 years. My recent work on next-generation FTV is also mentioned.
Biography: Masayuki Tanimoto received the B.E., M.E., and Dr.E. degrees in electronic engineering from the University of Tokyo in 1970, 1972, and 1976, respectively. He worked at Nagoya University from 1976 to 2012. Currently, he is an Emeritus Professor at Nagoya University and a Senior Research Fellow at Nagoya Industrial Science Research Institute. He developed TAT (Time-Axis Transform) system for HDTV compression. TAT system became one of the two candidates for HDTV satellite broadcast system in Japan. He also developed FTV (Free-viewpoint Television). He has been promoting FTV standardization in MPEG. He was the president of the ITE (Institute of Image Information and Television Engineers). He is Honorary Member of the ITE, Fellow of the IEICE (Institute of Electronics, Information, and Communication Engineers) and IEEE Life Fellow. He received the ITE Distinguished Achievement and Contributions Award, the IEICE Achievement Award, and the Commendation for Science and Technology by the Minister of Education, Culture, Sports, Science, and Technology.
Invite Lecture 3: Toward Real World Metaverse
Speaker: Jong-Il Park, Hanyang University, Korea
Abstract: Metaverse is emerging fast as a practical way of enriching our everyday lives as well as realizing the digital transformation. Metaverse phenomenon today is largely owing to the rise of experiential media and the rapid spread of a non-face-to-face society due to COVID-19. Metaverse can be divided into a pure virtual world-based one and a mixture of reality and virtuality. As the number of virtual world increases, the scarcity of the real world will become more prominent, and the real world-based metaverse will have more important industrial value. Real-world metaverse provides real-virtual convergence services in a wide area simultaneously to numerous users with various heterogeneous terminals. In this talk, various examples of real world metaverse are explained. Next, our latest research that implements the manipulation and transformation of the real world by the virtual world in real-time are introduced. This implies that the real world and the virtual world can interact symmetrically in both directions. Finally, the prospects and promotion strategies of real-world metaverse are discussed.
Biography: Jong-Il Park is a professor at Department of Computer Science, Hanyang University, Seoul, Korea, a founder and CEO of ARIA Edge Co., and the Chairman of Metaverse Future Forum, Korea. He received the BS, MS, and PhD degrees in electronics engineering from Seoul National University, Korea, in 1987, 1989, and 1995, respectively. He started doing AR research at NHK Science and Technology Research Laboratories, Tokyo from 1992. In 1995, he worked on technical strategies for digital broadcasting at Korean Broadcasting Institute. From 1996 to 1999, he was involved in various projects on AR/VR and 3D computer vision at the ATR Media Integration and Communication Research Laboratories, Kyoto, Japan. He has been with Hanyang University since 1999. During sabbatical leaves, he has worked at Univ. of Florence, Italy, Univ. of Tokyo, Japan, Columbia Univ., USA, and LG Electronics, Korea. He has published more than 200 refereed papers in the field of computer vision/graphics, virtual and augmented reality, computational imaging and display, and human-computer interaction.