Sciweavers

683 search results - page 120 / 137
» Learning Shape Prior Models for Object Matching
Sort
View
126
Voted
KDD
2012
ACM
205views Data Mining» more  KDD 2012»
13 years 3 days ago
Rank-loss support instance machines for MIML instance annotation
Multi-instance multi-label learning (MIML) is a framework for supervised classification where the objects to be classified are bags of instances associated with multiple labels....
Forrest Briggs, Xiaoli Z. Fern, Raviv Raich
CVPR
2009
IEEE
16 years 4 months ago
Regularized Multi-Class Semi-Supervised Boosting
Many semi-supervised learning algorithms only deal with binary classification. Their extension to the multi-class problem is usually obtained by repeatedly solving a set of bina...
Amir Saffari, Christian Leistner, Horst Bischof
68
Voted
CVPR
2008
IEEE
15 years 11 months ago
Graph cut with ordering constraints on labels and its applications
In the last decade, graph-cut optimization has been popular for a variety of pixel labeling problems. Typically graph-cut methods are used to incorporate a smoothness prior on a l...
Xiaoqing Liu, Olga Veksler, Jagath Samarabandu
ICCV
2009
IEEE
16 years 2 months ago
Subspace Constrained Mean-Shift
Deformable model fitting has been actively pursued in the computer vision community for over a decade. As a result, numerous approaches have been proposed with varying degrees of...
Jason M. Saragih, Simon Lucey, Jeffrey F. Cohn
93
Voted
ICCV
2009
IEEE
14 years 7 months ago
Face alignment through subspace constrained mean-shifts
Deformable model fitting has been actively pursued in the computer vision community for over a decade. As a result, numerous approaches have been proposed with varying degrees of ...
Jason M. Saragih, Simon Lucey, Jeffrey F. Cohn