Prof. Junyu Dong
Ocean University of China, China
Prof. Junyu Dong received his BSc and MSc from the Department of Applied Mathematics at Ocean University of China in 1993 and 1999 respectively, and received his PhD in November 2003 in Heriot-Watt University, UK. He is currently a professor and the Dean of Faculty of Information Science and Engineering at Ocean University of China. His research interests include 3D underwater imaging and machine learning with applications in marine science. He has been the principal investigator of more than 10 research projects supported by NSFC, MOST and other funding agencies. He has published more than 100 major journal and conference papers. He is the Editor-in-Chief of Journal of Intelligent Marine Technology and Systems, and also a Chairman of Qingdao Chapter of the Association for Computing Machinery (ACM).
Speech Title: "Underwater 3D reconstruction with interactive VR applications"
Abstract: Three-dimensional reconstruction faces great challenges in underwater environment, as images are blurred due to light absorption, scattering and refraction in the imaging process. Currently the demand for high-accuracy underwater 3D reconstruction is huge, especially in safety and environmental monitoring In this talk, I will present methods and systems for accurate 3D reconstruction in underwater environment. I will show the potential use of 3D reconstruction results in interactive control of underwater remote operated vehicles with VR facilities.
Prof. Xiao-Jun Wu
Jiangnan University, China
Xiao-Jun Wu received his B.S. degree in mathematics from Nanjing Normal University, Nanjing, PR China in 1991 and M.S. degree in 1996, and Ph.D. degree in Pattern Recognition and Intelligent System in 2002, both from Nanjing University of Science and Technology, Nanjing, PR China, respectively. He was a fellow of United Nations University, International Institute for Software Technology (UNU/IIST) from 1999 to 2000. From 1996 to 2006, he taught in the School of Electronics and Information, Jiangsu University of Science and Technology where he was an exceptionally promoted professor. He joined Jiangnan University in 2006 where he is currently a distinguished professor in the School of Artificial Intelligence and Computer Science, Jiangnan University. He won the most outstanding postgraduate award by Nanjing University of Science and Technology. He has published more than 400 papers in his fields of research. He was a visiting postdoctoral researcher in the Centre for Vision, Speech, and Signal Processing (CVSSP), University of Surrey, UK from 2003 to 2004, under the supervision of Professor Josef Kittler. His current research interests are pattern recognition, computer vision, fuzzy systems, and neural networks. He owned several domestic and international awards because of his research achievements. Currently, he is a Fellow of IAPR and AAIA respectively.
Speech Title: "An Exploration on Explainable Sparse/Low Rank Deep Learning Models for Multimodal Visual Fusion"
Abstract: There is a huge amount of visual information in the construction of smart city (SC) in which the visual fusion is a very important topic. Deep Learning (DL) has found very successful applications in numerous different domains with impressive results. Visual Fusion (VisF) algorithms based on sparse/low rank DL models and their applications will be presented in this talk in the context of SC. Initially, a brief introductory overview of related concepts and algorithms will be presented. Then, explainable sparse/low rank DL models will be analyzed. A comprehensive analysis of DL models will be offered and their typical applications will be discussed, including Image Quality Enhancement, Object Tracking, Multi-Modal Image Fusion, Video Style Transformation, and Deep Fake of Facial Images respectively.
Prof. Yi Yang
Zhejiang University, China
Prof. Yi Yang is a Chair Professor at Zhejiang University. His research interests include machine learning and its applications to multimedia content analysis and computer vision. He has received a number of prestigious awards, including the Google Faculty Research Award, the AWS Machine Learning Awards, and the Top Lifetime Achiever Award by The Australian. He has been a Clarivate Analytics Highly Cited Researcher for the past five consecutive years. His research group has won more than 40 awards in international scientific research competitions. He served as associate editors of 7 important international journals and area chairs in a number of major international conferences in his research field. He has received over 57,000 Google Scholar citations and his H-index is 115.
Speech Title: "Digital Human Generation Based on Multiple Knowledge Representations"
Abstract: In this talk, I will first discuss the challenges in the generation of virtual digital humans, and then analyze the advantages of multiple knowledge representations for robust virtual human generation. Later, I will discuss the research progress of digital human applications such as digital human reconstruction and multi-modal digital human generation. I will discuss methods that incorporate structural prior information such as geometry information in digital human reconstruction. In terms of multi-modal digital human generation, I will discuss methods for generating digital humans from inputs such as audio and text. I will discuss recent knowledge-informed methods and structured representation learning mechanisms. Finally, I will discuss recent studies on the combination of knowledge and data.