Sciweavers

Share
IJCV
2008

Describing Visual Scenes Using Transformed Objects and Parts

9 years 10 months ago
Describing Visual Scenes Using Transformed Objects and Parts
We develop hierarchical, probabilistic models for objects, the parts composing them, and the visual scenes surrounding them. Our approach couples topic models originally developed for text analysis with spatial transformations, and thus consistently accounts for geometric constraints. By building integrated scene models, we may discover contextual relationships, and better exploit partially labeled training images. We first consider images of isolated objects, and show that sharing parts among object categories improves detection accuracy when learning from few examples. Turning to multiple object scenes, we propose nonparametric models which use Dirichlet processes to automatically learn the number of parts underlying each object category, and objects composing each scene. The resulting transformed Dirichlet process (TDP) leads to Monte Carlo algorithms which simultaneously segment and recognize objects in street and office scenes.
Erik B. Sudderth, Antonio Torralba, William T. Fre
Added 12 Dec 2010
Updated 12 Dec 2010
Type Journal
Year 2008
Where IJCV
Authors Erik B. Sudderth, Antonio Torralba, William T. Freeman, Alan S. Willsky
Comments (0)
books