Abstract. We propose a new method for face recognition under arbitrary pose and illumination conditions, which requires only one training image per subject. Furthermore, no limitat...
Discriminative approaches to human pose inference involve mapping visual observations to articulated body configurations. Current probabilistic approaches to learn this mapping ha...
Global Motion Estimation (GME) is an important part in the object-based applications. In this paper, a fast progressive model refinement (FPMR) GME algorithm is proposed. It can s...
3D human pose recovery is considered as a fundamental step in view-invariant human action recognition. However, inferring 3D poses from a single view usually is slow due to the la...
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...