Computational Regularity - human movements and visual symmetry

Abstract: Symmetry is an essential mathematical concept, as well as a ubiquitous, observable phenomenon in nature, science and art. Either by evolution or by design, symmetry implies an efficiency coding that makes it universally appealing, especially so in machine visual perception of the real world. Dr Liu  shall illustrate recent progress in the area of computational regularity, a generalized form of computational symmetry. Also presented are recent results on understanding human perception of wallpaper patterns using neuroimaging (EEG, fMRI), crowd-sourcing with deep learning, and a symmetry-based Turing test to tell humans and robots apart. Finally, Dr Liu will present some results on human motion analysis (dance, tai chi, gait).

Bio: Yanxi Liu received her Ph.D. degree in computer science for group theory applications in robotics assembly planning from University of Massachusetts (Amherst, MA, USA) under the direction of late Robin Popplestone. She is currently a full professor in the School of Electrical Engineering and Computer Science, Pennsylvania State University where she co-directs the Lab for Perception, Action and Cognition (LPAC) and the Human Motion Lab for Taiji (Tai Chi) Research. Dr. Liu's research interests span a wide range of applications in computer vision, computer graphics, robotics, human perception and computer aided diagnosis in medicine, with a central theme on computational symmetry.