Sciweavers

12 search results - page 1 / 3
» Learning from One Example through Shared Densities on Transf...
Sort
View
CVPR
2000
IEEE
14 years 6 months ago
Learning from One Example through Shared Densities on Transforms
We define a process called congealing in which elements of a dataset (images) are brought into correspondence with each other jointly, producing a data-defined model. It is based ...
Erik G. Miller, Nicholas E. Matsakis, Paul A. Viol...
IVC
2010
128views more  IVC 2010»
13 years 2 months ago
Online kernel density estimation for interactive learning
In this paper we propose a Gaussian-kernel-based online kernel density estimation which can be used for applications of online probability density estimation and online learning. ...
Matej Kristan, Danijel Skocaj, Ales Leonardis
PAMI
2006
136views more  PAMI 2006»
13 years 4 months ago
Data Driven Image Models through Continuous Joint Alignment
This paper presents a family of techniques that we call congealing for modeling image classes from data. The idea is to start with a set of images and make them appear as similar a...
Erik G. Learned-Miller
GECCO
2010
Springer
184views Optimization» more  GECCO 2010»
13 years 9 months ago
Transfer learning through indirect encoding
An important goal for the generative and developmental systems (GDS) community is to show that GDS approaches can compete with more mainstream approaches in machine learning (ML)....
Phillip Verbancsics, Kenneth O. Stanley
CVPR
2006
IEEE
14 years 6 months ago
Escaping local minima through hierarchical model selection: Automatic object discovery, segmentation, and tracking in video
Recently, the generative modeling approach to video segmentation has been gaining popularity in the computer vision community. For example, the flexible sprites framework has been...
Nebojsa Jojic, John M. Winn, Larry Zitnick