Dr. Liu is a professor of EECS at Penn State University (PSU), University Park, USA, trained in physics/EE, computer science and theoretical robotics/AI (Ph.D. MA, USA; Postdoc, France).With an NSF (USA) research-education fellowship award, she spent one year at DIMACS (NSFcenter for DIscrete MAthematics and Theoretical Computer Science) before joining the faculty of the Robotics Institute, Carnegie Mellon University for ten years. Currently at PSU, she is the director of the Human Motion Capture Lab for Smart Health and co-directs the Lab for Perception, Action and Cognition (LPAC). Dr. Liu has been a visiting professor at Stanford University, ETH Zurich, Tsinghua University and Google/MSR/MSRA. She is currently on sabbatical at CMU. A central theme of Dr. Liu's research is on group theory-based“computational regularity” in multimodality datasets (funded continuously by US NSF, including a prestigious multidisciplinary INSPIRE grant and a current NSF Robust Intelligence core medium grant on “Vision to Dynamics”) with diverse applications in robotics, human/machine perception, human activity in sports and in health. Dr. Liu is the leading author for the book on “Computational Symmetry in Computer Vision and Computer Graphics”, and chaired three international competitions at CVPR, ECCV, ICCV on Computer Vision algorithms for Detecting Symmetry in the Wild. In April 2013, Dr. Liu organized the first Taiji and Advanced Technology for Smart Health Symposium in US. Her industrial visits, Google Mountain View, Microsoft Silicon Valley/Uber, resulted in two granted US patents respectively. She served as a co-program chair for Computer Vision and Pattern Recognition (CVPR) Conference 2017 and Winter Conference on Applications of Computer Vision (WACV) 2019, area chairs for all major computer vision conferences (CVPR/ECCV/ICCV/MICCAI), and an associate editor for IEEE Transaction of Pattern Analysis and Machine Intelligence (PAMI).
Abstract
From gait, dance to martial art, human movements provide rich, complex yet coheren spatiotemporal patterns reflecting characteristics of a group or an individual. We develop computational methods for motion perception from multimodal data. In particular, we advance our understanding of physics from visual input by constructive models to learn dynamics from kinematics. In this talk, I present a trilogy on understanding human movements:
(1) Gait analysis from video data: A group theoretical analysis of periodic patterns offers both effective viewing angle categorization and human identification from similar viewpoints.
(2) Dance analysis and synthesis (mocap, music, Mechanical Turks): we explore the complex relationship between human perception of dance quality/dancer's gender and dance movements. Using a novel multimedia dance-texture representation,our learning-based method is applied for dance segmentation, analysis and synthesis of new dancers.
(3) Taiji (Tai Chi) movements understanding from kinematics to dynamics (mocap, video, foot pressure): we investigate Taiji sequences (5 min) performed by subjects from beginners to masters to understand the quantified relation between pose and stability.
