Sciweavers

14 search results - page 3 / 3
» Learning Full Pairwise Affinities for Spectral Segmentation
Sort
View
CVPR
2006
IEEE
14 years 9 months ago
Unsupervised Learning of Categories from Sets of Partially Matching Image Features
We present a method to automatically learn object categories from unlabeled images. Each image is represented by an unordered set of local features, and all sets are embedded into...
Kristen Grauman, Trevor Darrell
CVPR
2007
IEEE
14 years 9 months ago
Learning and Matching Line Aspects for Articulated Objects
Traditional aspect graphs are topology-based and are impractical for articulated objects. In this work we learn a small number of aspects, or prototypical views, from video data. ...
Xiaofeng Ren
KDD
2007
ACM
181views Data Mining» more  KDD 2007»
14 years 7 months ago
BoostCluster: boosting clustering by pairwise constraints
Data clustering is an important task in many disciplines. A large number of studies have attempted to improve clustering by using the side information that is often encoded as pai...
Yi Liu, Rong Jin, Anil K. Jain
CVPR
2006
IEEE
14 years 9 months ago
Automatic Kinematic Chain Building from Feature Trajectories of Articulated Objects
We investigate the problem of learning the structure of an articulated object, i.e. its kinematic chain, from feature trajectories under affine projections. We demonstrate this po...
Jingyu Yan, Marc Pollefeys