Sciweavers

130 search results - page 21 / 26
» Virtual Training for Multi-View Object Class Recognition
Sort
View
UIST
1993
ACM
13 years 11 months ago
VB2: An Architecture for Interaction in Synthetic Worlds
This paper describes the VB2 architecture for the construction of three-dimensional interactive applications. The system's state and behavior are uniformly represented as a n...
Enrico Gobbetti, Jean-Francis Balaguer, Daniel Tha...
SLSFS
2005
Springer
14 years 1 months ago
Constructing Visual Models with a Latent Space Approach
We propose the use of latent space models applied to local invariant features for object classification. We investigate whether using latent space models enables to learn patterns...
Florent Monay, Pedro Quelhas, Daniel Gatica-Perez,...
ICPR
2004
IEEE
14 years 8 months ago
Relaxation Labeling Processes for Protein Secondary Structure Prediction
The prediction of protein secondary structure is a classical problem in bioinformatics, and in the past few years several machine learning techniques have been proposed to t. From...
Giacomo Colle, Marcello Pelillo
ESANN
2003
13 years 9 months ago
Semi-automatic acquisition and labelling of image data using SOMs
Abstract. Application of neural networks for real world object recognition suffers from the need to acquire large quantities of labelled image data. We propose a solution that acq...
Gunther Heidemann, Axel Saalbach, Helge Ritter
CVPR
2010
IEEE
14 years 4 months ago
What Helps Where - And Why? Semantic Relatedness for Knowledge Transfer
Remarkable performance has been reported to recognize single object classes. Scalability to large numbers of classes however remains an important challenge for today's recogn...
Marcus Rohrbach, Michael Stark, Gyö Szarvas, Bern...