566 search results - page 91 / 114 » OCR with No Shape Training |
101
click to vote
ECCV
2008
Springer
15 years 11 months ago
2008
Springer
We propose a graph-based semi-supervised symmetric matching framework that performs dense matching between two uncalibrated wide-baseline images by exploiting the results of sparse...
101
click to vote
ECCV
2004
Springer
15 years 11 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...
101
click to vote
ECCV
2006
Springer
15 years 11 months ago
2006
Springer
Abstract. This contribution proposes a compositional approach to visual object categorization of scenes. Compositions are learned from the Caltech 101 database1 intermediate abstra...
ICPR
2006
IEEE
15 years 10 months ago
2006
IEEE
Coarticulation is one of the important factors that makes automatic sign language recognition a hard problem. Unlike in speech recognition, coarticulation effects in sign language...
ICPR
2006
IEEE
15 years 10 months ago
2006
IEEE
One possible solution for pose- and illuminationinvariant face recognition is to employ appearancebased approaches, which rely greatly on correct facial textures. However, existin...