Sciweavers

455 search results - page 22 / 91
» Learning Shape from Defocus
Sort
View
MICCAI
2005
Springer
15 years 10 months ago
Multiscale 3D Shape Analysis Using Spherical Wavelets
Shape priors attempt to represent biological variations within a population. When variations are global, Principal Component Analysis (PCA) can be used to learn major modes of vari...
Delphine Nain, Steven Haker, Aaron F. Bobick, Alle...
CVPR
2009
IEEE
1216views Computer Vision» more  CVPR 2009»
16 years 4 months ago
Marked Point Processes for Crowd Counting
A Bayesian marked point process (MPP) model is developed to detect and count people in crowded scenes. The model couples a spatial stochastic process governing number and placem...
Robert T. Collins, Weina Ge
PAMI
2008
231views more  PAMI 2008»
14 years 9 months ago
Nonrigid Structure-from-Motion: Estimating Shape and Motion with Hierarchical Priors
This paper describes methods for recovering time-varying shape and motion of nonrigid 3D objects from uncalibrated 2D point tracks. For example, given a video recording of a talkin...
Lorenzo Torresani, Aaron Hertzmann, Christoph Breg...
72
Voted
CVIU
2004
115views more  CVIU 2004»
14 years 9 months ago
Dynamic learning from multiple examples for semantic object segmentation and search
We present a novel ``dynamic learning'' approach for an intelligent image database system to automatically improve object segmentation and labeling without user interven...
Yaowu Xu, Eli Saber, A. Murat Tekalp
GECCO
2010
Springer
153views Optimization» more  GECCO 2010»
15 years 29 days ago
Multi-task evolutionary shaping without pre-specified representations
Shaping functions can be used in multi-task reinforcement learning (RL) to incorporate knowledge from previously experienced tasks to speed up learning on a new task. So far, rese...
Matthijs Snel, Shimon Whiteson