Sciweavers

235 search results - page 19 / 47
» Tracking Large Variable Numbers of Objects in Clutter
Sort
View
ECCV
2008
Springer
14 years 9 months ago
Finding Actions Using Shape Flows
Abstract. We propose a novel method for action detection based on a new action descriptor called a shape flow that represents both the shape and movement of an object in a holistic...
Hao Jiang, David R. Martin
ICRA
2010
IEEE
133views Robotics» more  ICRA 2010»
13 years 6 months ago
Variable resolution decomposition for robotic navigation under a POMDP framework
— Partially Observable Markov Decision Processes (POMDPs) offer a powerful mathematical framework for making optimal action choices in noisy and/or uncertain environments, in par...
Robert Kaplow, Amin Atrash, Joelle Pineau
CVPR
2009
IEEE
15 years 2 months ago
Learning to Track with Multiple Observers
We propose a novel approach to designing algorithms for object tracking based on fusing multiple observation models. As the space of possible observation models is too large for...
Björn Stenger, Roberto Cipolla, Thomas Woodle...
CAIP
2003
Springer
222views Image Analysis» more  CAIP 2003»
14 years 29 days ago
Learning Statistical Structure for Object Detection
Abstract. Many classes of images exhibit sparse structuring of statistical dependency. Each variable has strong statistical dependency with a small number of other variables and ne...
Henry Schneiderman
BMCBI
2007
120views more  BMCBI 2007»
13 years 7 months ago
Re-sampling strategy to improve the estimation of number of null hypotheses in FDR control under strong correlation structures
Background: When conducting multiple hypothesis tests, it is important to control the number of false positives, or the False Discovery Rate (FDR). However, there is a tradeoff be...
Xin Lu, David L. Perkins