Sciweavers

16 search results - page 2 / 4
» A Comparative Study of Energy Minimization Methods for Marko...
Sort
View
JMLR
2008
230views more  JMLR 2008»
13 years 4 months ago
Exponentiated Gradient Algorithms for Conditional Random Fields and Max-Margin Markov Networks
Log-linear and maximum-margin models are two commonly-used methods in supervised machine learning, and are frequently used in structured prediction problems. Efficient learning of...
Michael Collins, Amir Globerson, Terry Koo, Xavier...
ICIP
2008
IEEE
14 years 6 months ago
Robust snake convergence based on dynamic programming
The extraction of contours using deformable models, such as snakes, is a problem of great interest in computer vision, particular in areas of medical imaging and tracking. Snakes ...
Akshaya Kumar Mishra, Paul W. Fieguth, David A. Cl...
CRV
2008
IEEE
205views Robotics» more  CRV 2008»
13 years 11 months ago
Accurate Boundary Localization using Dynamic Programming on Snakes
The extraction of contours using deformable models, such as snakes, is a problem of great interest in computer vision, particular in areas of medical imaging and tracking. Snakes ...
Akshaya Kumar Mishra, Paul W. Fieguth, David A. Cl...
CVPR
2011
IEEE
13 years 9 hour ago
Illumination Estimation and Cast Shadow Detection through a Higher-order Graphical Model
In this paper, we propose a novel framework to jointly recover the illumination environment and an estimate of the cast shadows in a scene from a single image, given coarse 3D geo...
Alexandros Panagopoulos, Chaohui Wang, Dimitris Sa...
ICASSP
2008
IEEE
13 years 11 months ago
Optical flow robust estimation in a hybrid multi-resolution MRF framework
We propose in this paper a robust multi-resolution technique to estimate dense velocity field from image sequences. It couples a Gaussian pyramidal down-sampling decomposition to...
Cyril Cassisa, Véronique Prinet, Liang Shao...