Abstract This paper proposes a Qualitative Normalised Templates (QNTs) framework for solving the human motion classification problem. In contrast to other human motion classifica...
We synthesize new human body motions from existing motion data. We divide the body of an animated character into several parts, such as to upper and lower body, and partition the m...
Won-Seob Jang, Won-Kyu Lee, In-Kwon Lee, Jehee Lee
We present a novel approach to tracking 2D human motion in uncalibrated monocular videos. Human motion usually exhibits timevarying patterns, and we propose to use locally learnt ...
We advocate the use of Gaussian Process Dynamical Models (GPDMs) for learning human pose and motion priors for 3D people tracking. A GPDM provides a lowdimensional embedding of hu...
This paper presents an unsupervised learning algorithm that can derive the probabilistic dependence structure of parts of an object (a moving human body in our examples) automatic...