学术讲座-Statistical Analysis of Trajectories on Manifolds
发布者: 科研处 更新日期: 2019-09-11 访问次数: 10
讲座题目Statistical Analysis of Trajectories on Manifolds
主办单位信息科学与工程学院
联合主办单位
讲 座 人苏敬勇讲 座人
职 称
副高主持人潘正祥
讲座类型自然科学讲座对象全校师生时 间2019-09-11 10:30
地 点信息学院C1-206会议室




Dr. Jingyong Su is an associate professor in the department of  Mathematics & Statistics at Texas Tech University, USA. He completed a Ph.D.  in statistics at the Florida State University in 2013. Previously, he received  both B.S. and M.S. degrees in electrical engineering from Harbin Institute of  Technology in 2006 and 2008 respectively. His current research interests include  statistics on manifolds, pattern recognition, computer vision and medical  imaging. Dr. Su has published multiple papers on top-rated journals and  conferences, such as IEEE TPAMI, IJCV, Annals of Applied Statistics, JIVC, CSDA,  CVPR and ICPR etc.
讲  座
主要内容
In this research we proposed a comprehensive framework for  registration and analysis of manifold-valued processes. Functional data analysis  in Euclidean spaces has been explored extensively in literature. But we study a  dierent problem in the sense that functions to be studied take values on  nonlinear manifolds, rather than in vector spaces. Manifold-valued data appear  frequently in shape and image analysis, computer vision, biomechanics and many  others. The non-linearity of the manifolds requires development of new  methodologies suitable for analysis of manifold-valued data. We propose a  comprehensive framework for joint registration and analysis of multiple  manifold-valued processes. The goals are to take temporal variability into  account, derive a rate-invariant metric and generate statistical summaries  (sample mean, covariance etc.), which can be further used for registering and  modeling multiple trajectories.


打印此页】 【顶部】 【关闭窗口