15 search results - page 3 / 3 » humo 2007 |
HUMO
2007
Springer
13 years 12 months ago
2007
Springer
We present a method to simultaneously estimate 3d body pose and action categories from monocular video sequences. Our approach learns a lowdimensional embedding of the pose manifol...
HUMO
2007
Springer
13 years 12 months ago
2007
Springer
We propose a new method for human action recognition from video sequences using latent topic models. Video sequences are represented by a novel “bag-of-words” representation, w...
HUMO
2007
Springer
13 years 12 months ago
2007
Springer
In this paper, we suggest to model priors on human motion by means of nonparametric kernel densities. Kernel densities avoid assumptions on the shape of the underlying distribution...
HUMO
2007
Springer
13 years 12 months ago
2007
Springer
Abstract. In this paper we present a novel tool for body-part segmentation and tracking in the context of multiple camera systems. Our goal is to produce robust motion cues over ti...
HUMO
2007
Springer
13 years 12 months ago
2007
Springer
This paper deals with region-of-interest (ROI) segmentation in video sequences. The goal is to determine in one frame the region which best matches, in terms of a similarity measur...