This KEYNOTE page introduces 3 KEYNOTE1-3 and 2 INVITED LECTURE1-2.
KEYNOTE 1 (9:00-9:40, 5th Jan)
Speaker: Kokichi Sugihara (Meiji University, Japan)
Title: Difficulty in representing 3D shapes by 2D images due to optical illusion.
(Meiji Institute for Advanced Study of Mathematical Sciences, Meiji University)
Abstract:Impossible objects were originally proposed as imaginary 3D structures that cannot be realized as real physical objects. However, several tricks were found to construct real objects whose projections match impossible objects. This in turn means it is not easy to judge whether a given image represents a real object or not. We show various types of real objects and real motions that look impossible, and consider why our brains cannot avoid 3D optical illusion. This might give us some hints to decrease misunderstanding in communication by images.
Profile:Kokichi Sugihara graduated from the University of Tokyo in 1971, worked at Electrotechnical Laboratory, Nagoya University, the University of Tokyo and Meiji University, and is now a Meiji University distinguished professor emeritus as well as a professor emeritus of the University of Tokyo. His research area is mathematical engineering. In his research on computer vision, he found a method for constructing 3D objects from “impossible figures,” and extended his research interest to human vision and optical illusion. Constructing mathematical models of human vision systems, he created various new classes of impossible objects. He won the first prize three times (2010, 2013 and 2018) and the second prize twice (2015 and 2016) in the Best Illusion of the Year Contest.
KEYNOTE 2 (10:00-10:40, 5th Jan)
Speaker： Guang-Bin Huang (Nanyang Technological University, Singapore)
Title：Extreme Learning Machines (ELM) – When ELM and Deep Learning Synergize
(Professor of School of Electrical and Electronic Engineering,Nanyang Technological University, Singapore)
Abstract: One of the most curious in the world is how brains produce intelligence. The objectives of this talk are three-folds: 1) There exists some convergence between machine learning and biological learning. Although there exist many different types of techniques for machine learning and also many different types of learning mechanism in brains, Extreme Learning Machines (ELM) as a common learning mechanism may fill in the gap between machine learning and biological learning. In fact, ELM theories have been validated by more and more direct biological evidences recently. ELM theories point out that the secret learning capabilities of brains may be due to the globally ordered and structured mechanism but with locally random individual neurons in brains, and such a learning system happens to have regression, classification, sparse coding, clustering, compression and feature learning capabilities, which are fundamental to cognition and reasoning; 2) Single hidden layer of ELM unifies Support Vector Machines (SVM), Principal Component Analysis (PCA), Non-negative Matrix Factorization (NMF); 3) ELM provides some theoretical support to the universal approximation and classification capabilities of Convolutional Neural Networks (CNN). In addition to the good performance in small to medium datasets, hierarchical ELM is catching up with Deep Learning in some benchmark big datasets which Deep Learning used to perform well.
Profile:Guang-Bin Huang is a Full Professor in the School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore. He was a Nominee of Singapore President Science Award (2016, 2017, 2018 and 2019), was awarded by Thomson Reuters “Highly Cited Researcher” (in two fields: Engineering and Computer Science) and listed in Thomson Reuters’s “The World’s Most Influential Scientific Minds” since 2014. He received the best paper award from IEEE Transactions on Neural Networks and Learning Systems (2013). His two works on Extreme Learning Machines (ELM) have been listed by Google Scholar in 2017 as Top 2 and Top 7, respectively in its “Classic Papers: Articles That Have Stood The Test of Time” – Top 10 in Artificial Intelligence.
He is Principal Investigator of BMW-NTU Joint Future Mobility Lab on Human Machine Interface and Assisted Driving, Principal Investigator (data and video analytics) of Delta – NTU Joint Lab, Principal Investigator (Scene Understanding) of ST Engineering – NTU Corporate Lab, and Principal Investigator (Marine Data Analysis and Prediction for Autonomous Vessels) of Rolls Royce – NTU Corporate Lab. He has led/implemented several key industrial projects (e.g., Chief architect/designer and technical leader of Singapore Changi Airport Cargo Terminal 5 Inventory Control System (T5 ICS) Upgrading Project, etc).
KEYNOTE 3 (9:00-9:40, 6th Jan)
Speaker: Dr. Jeongil Seo (ETRI, South Korea)
Title: Virtual view synthesis of light field images for supporting 6 degrees-of-freedom
(Immersive Media Research Section, ETRI)
Abstract: To provide high immersion feeling to users experiencing immersive media such as VR, a technology for synthesizing and rendering a virtual viewpoint according to the user’s 6 degrees-of-freedom movement at high speed and high quality is required. In this speech, methodologies of virtual view synthesizing from sparse light field images and estimated depth information are introduced, and some algorithmic enhancements to improve the quality of virtual views and synthesizing speed are presented.
Profile: Jeongil Seo was born in Goryoung, Korea, in 1971. He received the Ph.D. degree in electronics from Kyoungpook National University (KNU), Daegu, Korea, in 2005 for his work on audio signal processing systems. He was worked as a member of engineering staff at the Laboratory of Semiconductor, LG-semicon, Cheongju, Korea, from 1998 until 2000. He has worked as a director at the Immersive Media Research Section, Electronics and Telecommunications Research Institute (ETRI), Daejeon, Korea, since 2000. His research activities include audio and video coding, immersive video (panorama, 360 video, light field video and etc.) processing, and realistic broadcasting systems. Also, he has participated multimedia international standard activities (MPEG) including audio coding, video coding, and immersive video processing from 2002.
INVITED LECTURE 1 (16:40-17:10, 5th Jan)
Speaker: Prof.Tsutomu Nagayama ( Kagoshima university, Japan)
Title:How to realize invisible cloak with metamaterial
Abstract: The concept of transformation electromagnetics has been presented for highly manipulating electromagnetic waves by media mimicking the transformed coordinate system. Based on this concept, we can realize invisible cloaks to hide an object or illusions to mimic scattered waves from a non-existent object. Recently, twodimensional (2-D) distributed full-tensor anisotropic metamaterial models have been proposed in order to design various media on the basis of transformation electromagnetics, and a 2-D invisible carpet cloak for hiding an object on a flat surface (or other devices) has been realized. In this presentation, the theory of the metamaterial
models and how to realize invisible cloaks are introduced.
Profile: Tsutomu Nagayama received the B. E., M. E., and Ph. D. degrees in electrical and electronics engineering from Yamaguchi University, Yamaguchi, Japan, in 2011, 2013, and 2016, respectively. He joined the Faculty of Engineering, Kagoshima University, Kagoshima, Japan, in 2016, where he is an Assistant Professor now. His research is concerned with metamaterials based on the concept of transformation electromagnetics or transformation acoustics. He is a member of the Institute of Electrical and Electronics Engineering.
INVITED LECTURE 2 (17:10-17:40, 5th Jan)
Speaker: Akiyo Makino (*) and Prof. Junne Kikata ( Kagoshima university, Japan)
Title:Color planning for local place branding: case study of Kagoshima
Abstract: This study demonstrates a process for color planning for local place branding in Kagoshima prefecture. Colors which most closely related to prefectural features were shown to a group of over 1,500 locals who were asked to identify those which they most closely associated with Kagoshima. The resulting selections were organized into 18 palettes. These palettes were then applied to product design, environmental design, and communications design. In total there were 13 cases of use. These were evaluated through interviews and public reaction. This presentation demonstrates that the contribution of citizen participation in color selection can support local cultural and socioeconomic development.
Profile: Akiyo Makino was born in Aichi, Japan, in 1980. She has worked as a project assistant professor, Kagoshima University, Japan, since 2016. She is also a Ph.D. student who belongs to Graduate School of Science and Engineering, Kagoshima University, Japan. She is studying about issues related to color planning for local place branding. She is a member of the Architectural Institute of Japan, the City Planning Institute of Japan, and the Color Science Association of Japan.