This paper presents a framework to automatically detect and recover the occluded facial region. We first derive a Bayesian formulation unifying the occlusion detection and recover...
We introduce a novel energy minimization method to decompose a video into a set of super-resolved moving layers. The proposed energy corresponds to the cost of coding the sequence...
We propose a novel approach to reduce spatially varying motion blur using a hybrid camera system that simultaneously captures high-resolution video at a low-frame rate together wi...
Yu-Wing Tai, Hao Du, Michael S. Brown, Stephen Lin
In this paper we study face recognition across ages within a real passport photo verification task. First, we propose using the gradient orientation pyramid for this task. Discard...
Visual trackan,g cou,ld be treeted as a param,eter estim.ation. problem, of target representastionbased on observations in im,age sequ.ences. A rich,er target represen,tation, wou...