Abstract— This paper proposes a sparsity driven shape registration method for occluded facial feature localization. Most current shape registration methods search landmark locati...
If a moving image is more expressive than words or than a still image, then an animated facial expression can explain more in depth the feelings of a virtual character. Facial ani...
Human gait and activity analysis from video is presently attracting a lot of attention in the computer vision community. In this paper, we analyze the role of two of the most impo...
Ashok Veeraraghavan, Amit K. Roy Chowdhury, Rama C...
In previous work [8] a computational framework was demonstrated that allows a mobile robot to autonomously evolve models its own body for the purposes of adaptive behavior generat...
This paper presents an approach to recover body motions from multiple views using a 3D skeletal model. It takes, as input, foreground silhouette sequences from multiple viewpoints...