3 search results - page 1 / 1 » Learning a dense multi-view representation for detection, vi... |
ICCV
2009
IEEE
14 years 9 months ago
2009
IEEE
Recognizing object classes and their 3D viewpoints is an
important problem in computer vision. Based on a partbased
probabilistic representation [31], we propose a new
3D object...
CVPR
2009
IEEE
14 years 11 months ago
2009
IEEE
We propose a novel probabilistic framework for learning
visual models of 3D object categories by combining appearance
information and geometric constraints. Objects are
represen...
CVPR
2010
IEEE
13 years 12 months ago
2010
IEEE
This paper presents a new approach for multi-view object class detection. Appearance and geometry are treated as separate learning tasks with different training data. Our approach...