Sciweavers

712 search results - page 95 / 143
» Pruning Training Sets for Learning of Object Categories
Sort
View
CVPR
2007
IEEE
14 years 11 months ago
Monocular and Stereo Methods for AAM Learning from Video
The active appearance model (AAM) is a powerful method for modeling deformable visual objects. One of the major drawbacks of the AAM is that it requires a training set of pseudo-d...
Jason Saragih, Roland Göcke
CORR
2010
Springer
155views Education» more  CORR 2010»
13 years 9 months ago
Repairing People Trajectories Based on Point Clustering
This paper presents a method for improving any object tracking algorithm based on machine learning. During the training phase, important trajectory features are extracted which are...
Duc Phu Chau, François Brémond, Etie...
COLING
2008
13 years 10 months ago
Looking for Trouble
This paper presents a method for mining potential troubles or obstacles related to the use of a given object. Some example instances of this relation are medicine, side effect and...
Stijn De Saeger, Kentaro Torisawa, Jun'ichi Kazama
CVPR
2005
IEEE
14 years 11 months ago
Fast Spatial Pattern Discovery Integrating Boosting with Constellations of Contextual Descriptors
We present a novel approach for fast object class recognition incorporating contextual information into boosting. The object is represented as a constellation of generalized corre...
Jaume Amores, Nicu Sebe, Petia Radeva
ATAL
2006
Springer
14 years 28 days ago
Reinforcement learning for declarative optimization-based drama management
A long-standing challenge in interactive entertainment is the creation of story-based games with dynamically responsive story-lines. Such games are populated by multiple objects a...
Mark J. Nelson, David L. Roberts, Charles Lee Isbe...