50 search results - page 4 / 10 » Learning the Probability of Correspondences without Ground T... |
ICPR
2000
IEEE
13 years 12 months ago
2000
IEEE
Thispaper presents a text word extraction algorithm that takes a set of bounding boxes of glyphs and their associated text lines of a given document andpartitions the glyphs into ...
ICIP
2003
IEEE
14 years 9 months ago
2003
IEEE
We present algorithms for automatic feature selection for unsupervised structure discovery from video sequences. Feature selection in this scenario is hard because of the absence ...
CVPR
2004
IEEE
14 years 9 months ago
2004
IEEE
In this paper we perform 3D face tracking on corrupted video sequences. We use a deformable model, combined with a predictive filter, to recover both the rigid transformations and...
ICCV
1998
IEEE
14 years 9 months ago
1998
IEEE
We describe how to teach deformable models to maximize image segmentation correctness based on user-specified criteria, and we present a method for evaluating which criteria work ...
CVPR
2010
IEEE
13 years 10 months ago
2010
IEEE
The 3D reconstruction of a face from a single frontal image is an ill-posed problem. This is further accentuated when the face image is captured under different poses and/or compl...