458 search results - page 20 / 92 » Discriminative Training for Object Recognition Using Image P... |
132
Voted
WACV
2005
IEEE
15 years 7 months ago
2005
IEEE
Current feature-based object recognition methods use information derived from local image patches. For robustness, features are engineered for invariance to various transformation...
130
Voted
CVPR
1997
IEEE
16 years 3 months ago
1997
IEEE
This paper describes an efficient approach to pose invariant object recognition employing pictorial recognition of image patches. A complete affine invariance is achieved by a rep...
125
Voted
ECCV
2008
Springer
16 years 3 months ago
2008
Springer
Multiple Instance Learning (MIL) provides a framework for training a discriminative classifier from data with ambiguous labels. This framework is well suited for the task of learni...
122
Voted
DAGM
2003
Springer
15 years 7 months ago
2003
Springer
We present a holistic statistical model for the automatic analysis of complex scenes. Here, holistic refers to an integrated approach that does not take local decisions about segme...
112
click to vote
NIPS
2001
15 years 3 months ago
2001
We describe an algorithm for automatically learning discriminative components of objects with SVM classifiers. It is based on growing image parts by minimizing theoretical bounds ...