933 search results - page 113 / 187 » Fully automatic cross-associations |
124
click to vote
CVPR
2008
IEEE
16 years 8 months ago
2008
IEEE
In this paper, we extend a computationally efficient framework for real-time 3D tracking and segmentation to support deformable subdivision surfaces. Segmentation is performed in a...
193
click to vote
CVPR
2008
IEEE
16 years 8 months ago
2008
IEEE
The objective of this paper is to estimate 2D human pose as a spatial configuration of body parts in TV and movie video shots. Such video material is uncontrolled and extremely ch...
161
click to vote
ICCV
2003
IEEE
16 years 8 months ago
2003
IEEE
The problem considered in this paper is the fully automatic construction of panoramas. Fundamentally, this problem requires recognition, as we need to know which parts of the pano...
151
click to vote
ECCV
2008
Springer
16 years 7 months ago
2008
Springer
Abstract. We propose a fully automatic framework to detect and extract arbitrary human motion volumes from real-world videos collected from YouTube. Our system is composed of two s...
207
click to vote
ECCV
2004
Springer
16 years 7 months ago
2004
Springer
This paper presents a Bayesian framework for multi-cue 3D object tracking of deformable objects. The proposed spatio-temporal object representation involves a set of distinct linea...