Nonlinear Low-Rank Matrix Completion for Human Motion Recovery.
IEEE Transactions on Image Processing(2018)
摘要
Human motion capture data has been widely used in many areas, but it involves a complex capture process and the captured data inevitably contains missing data due to the occlusions caused by the actor's body or clothing. Motion recovery, which aims to recover the underlying complete motion sequence from its degraded observation, still remains as a challenging task due to the nonlinear structure an...
更多查看译文
关键词
Kernel,Kinematics,Matrix converters,Manifolds,Task analysis,Hilbert space,Training
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络