364 search results - page 58 / 73 » On-line Boosting and Vision |
ICCV
2007
IEEE
14 years 11 months ago
2007
IEEE
Discriminative methods for visual object category recognition are typically non-probabilistic, predicting class labels but not directly providing an estimate of uncertainty. Gauss...
ICCV
2001
IEEE
14 years 11 months ago
2001
IEEE
We develop a pairwise classification framework for face recognition, in which a class face recognition problem is divided into a set of ? ?? ? two class problems. Such a problem...
ECCV
2008
Springer
14 years 11 months ago
2008
Springer
Abstract. Tree-structured models have been widely used for human pose estimation, in either 2D or 3D. While such models allow efficient learning and inference, they fail to capture...
ECCV
2008
Springer
14 years 11 months ago
2008
Springer
In patch-based object recognition, using a compact visual codebook can boost computational efficiency and reduce memory cost. Nevertheless, compared with a large-sized codebook, it...
ECCV
2008
Springer
14 years 11 months ago
2008
Springer
Object detection and pixel-wise scene labeling have both been active research areas in recent years and impressive results have been reported for both tasks separately. The integra...