Sciweavers

928 search results - page 92 / 186
» Unsupervised Segmentation of Objects using Efficient Learnin...
Sort
View
ICML
2008
IEEE
16 years 2 months ago
The asymptotics of semi-supervised learning in discriminative probabilistic models
Semi-supervised learning aims at taking advantage of unlabeled data to improve the efficiency of supervised learning procedures. For discriminative models however, this is a chall...
François Yvon, Nataliya Sokolovska, Olivier...
ICPR
2010
IEEE
15 years 5 months ago
Initialisation-Free Active Contour Segmentation
We present a region based active contour model which does not require any initialisation and is capable of modelling multi-modal image regions. Its external force is based on stat...
Xianghua Xie, Majid Mirmehdi
IJCV
2000
180views more  IJCV 2000»
15 years 1 months ago
Probabilistic Models of Appearance for 3-D Object Recognition
We describe how to model the appearance of a 3-D object using multiple views, learn such a model from training images, and use the model for object recognition. The model uses pro...
Arthur R. Pope, David G. Lowe
ASSETS
2006
ACM
15 years 8 months ago
Interactive tracking of movable objects for the blind on the basis of environment models and perception-oriented object recognit
In previous work we have presented a prototype of an assistant system for the blind that can be used for self-localization and interactive object identification of static objects ...
Andreas Hub, Tim Hartter, Thomas Ertl
CIDM
2007
IEEE
15 years 6 months ago
Efficient Kernel-based Learning for Trees
Kernel methods are effective approaches to the modeling of structured objects in learning algorithms. Their major drawback is the typically high computational complexity of kernel ...
Fabio Aiolli, Giovanni Da San Martino, Alessandro ...