BIO: Hao (Richard) Zhang is a professor in the School of Computing Science at Simon Fraser University (SFU), Canada, where he directs the computer graphics (GrUVi) lab and serves as the inaugural director of the Professional Masters Program in Visual Computing. He obtained his Ph.D. from the University of Toronto, and MMath and BMath degrees from the University of Waterloo. Richard’s research is in computer graphics with special interests in geometric modeling, shape analysis, 3D content creation, machine learning, as well as computational design and fabrication. He has been an editor-in-chief of Computer Graphics Forum and a program chair for SGP 2013, SIGGRAPH Asia 2014 Course, Graphics Interface 2015, among others, and will be a conference chair for the International Geometry Summit in 2019. Richard received a National Science and Engineering Research Council of Canada Discovery Accelerator Award in 2014, best paper awards from SGP 2008 and CAD/Graphics 2017, a Faculty of Applied Sciences (FAS) Research Excellence Award at SFU in 2014, and a National Science Foundation of China (NSFC) Overseas Outstanding Young Researcher Award in 2015. He has been a visiting professor at Stanford University, Shandong University, and Shenzhen University.

Abstract: Computer graphics is traditionally defined as a field which covers all aspects of computer-assisted image synthesis. An introductory class to graphics mainly teaches how to turn an explicit model description including geometric and photometric attributes into one or more images. Under this classical and arguably narrow definition, computer graphics corresponds to a ‘‘forward’’ (synthesis) problem, in contrast to computer vision, which traditionally battles with the inverse (analysis) problem. In this talk, I would offer my view of what the NEW computer graphics is, especially in the current age of machine learning and data-driven computing. I will first remind ourselves several well-known data challenges that are unique to graphics problems. Then, by altering the above classical definition of computer graphics, perhaps only slightly, I show that to do the synthesis right, one has to first ‘‘understand’’ the task and solve various inverse problems. In this sense, graphics and vision are converging, with data and learning playing key roles in both fields. A recurring challenge however is a general lack of “Big 3D Data”, which graphics research is expected to address. I will show you a quick sampler of our recent works on data-driven and learning-based syntheses of 3D shapes and virtual scenes. Finally, I want to explore a new perspective for the synthesis problem to mimic a higher-level human capability than pattern recognition and understanding.

Bio: Trista is an entrepreneur, tech executive and computer scientist with 20 years of experience. She is currently the Chief Scientist of Machine Learning at Inventec, the top server and consumer-electronics manufacturer in the world. Previously, Trista held leadership positions at several startups and research labs. While leading Cognitive Networks' core algorithms and data science, she lifted the company's customer counts and traffics by more than 10x. Cognitive Networks was acquired by Vizio. Trista founded Fotolugu, a B2B computer vision company that helped companies monetizing images and videos. At Intel, she helped develop OpenCV, the most widely adopted computer vision library in the world. At Nvidia, she architected Nvidia's first video processor. Trista received her Ph.D. from Carnegie Mellon University. Her research interests include machine learning, computer vision, artificial intelligence, multimedia big data, and robotics.

Abstract: Artificial intelligence, dormant for decades, is making a big comeback as the new electricity. AI will and is already transforming all aspects of life, from email spam filter, news feed optimization, to helping medical diagnosis. Modern AI is especially good in the field of computer vision. It can reach or even exceed human-level understanding of the visual world. This talk aims at the three W’s of AI: 1) what is AI in computer vision? 2) how do we apply AI to real-world problems? from problem definition, data preparation, model selection, to solution delivery; 3) why does AI work? How do we unveil the secret of the magic black box? Interpretability of an AI system is crucial for its trustworthiness, ethics in adopting such an AI system, and the future of AI.

BIO: Yoshinori Dobashi is an associate professor at Hokkaido University in the graduate school of information science and technology, Japan since 2000. His research interests center in computer graphics including lighting models. Dobashi received his BE, ME and Ph.D in Engineering in 1992, 1994, and 1997, respectively, from Hiroshima University. He worked at Hiroshima City University from 1997 to 2000 as a research associate. His work has been awarded from eurographics, the society for art and science, etc. He received The Commendation for Science and Technology by the Minister of Education, Culture, Sports, Science and Technology in 2014.

Abstract: Visual simulation is fun. We can create highly realistic images by simulating optical interaction between light and virtual objects. Realistic animation of complex phenomena can be generated by solving their governing equations such as Navier-Stokes equations for fluid phenomena. We can also synthesize realistic sound with the techniques for visual simulation. Visual simulation has opened a new way of digital fabrication as well. In this talk, I will introduce our research results on these topics. The topics include cloud simulation/rendering, aerodynamic sound simulation, real-time rendering, fluid simulation/editing, and goal-based caustics/reflector fabrication.

BIO: Toshihiko YAMASAKI, Associate Professor Department of Information and Communication Engineering, Graduate School of Information Science and Technology, The University of Tokyo He received the B.S. degree, the M.S. degree, and the Ph.D. degree from The University of Tokyo in 1999, 2001, and 2004, respectively. He is currently an Associate Professor at Department of Information and Communication Engineering, Graduate School of Information Science and Technology, The University of Tokyo. He was a JSPS Fellow for Research Abroad and a visiting scientist at Cornell University from Feb. 2011 to Feb. 2013. His current research interests include multimedia big data analysis, pattern recognition, machine learning, and so on.

Abstract: Our research group is interested in why and how we are attracted to specific persons, content, and services. We have been analyzing such “attractiveness” by using big multimedia data. In this talk, I will briefly introduce some of our representative works that are related to computer graphics such as presentation slide design coaching, makeup recommendation, and so on.