486 search results - page 29 / 98 » Learning bilinear models for two-factor problems in vision |
IJCV
2010
13 years 8 months ago
2010
Abstract Image alignment has been a long standing problem in computer vision. Parameterized Appearance Models (PAMs) such as the Lucas-Kanade method, Eigentracking, and Active Appe...
CVPR
2010
IEEE
14 years 6 months ago
2010
IEEE
The dynamic texture (DT) is a probabilistic generative model, defined over space and time, that represents a video as the output of a linear dynamical system (LDS). The DT model ...
NIPS
2004
13 years 11 months ago
2004
We present an algorithm to overcome the local maxima problem in estimating the parameters of mixture models. It combines existing approaches from both EM and a robust fitting algo...
AUSAI
2008
Springer
14 years 5 days ago
2008
Springer
Abstract. Graph-based representations have been used with considercess in computer vision in the abstraction and recognition of object shape and scene structure. Despite this, the ...
ECCV
2008
Springer
15 years 2 days ago
2008
Springer
Learning visual classifiers for object recognition from weakly labeled data requires determining correspondence between image regions and semantic object classes. Most approaches u...