Sciweavers

2295 search results - page 346 / 459
» Learning Overcomplete Representations
Sort
View
ISCIS
2009
Springer
14 years 4 months ago
Using 3D contours and their relations for cognitive vision and robotics
—In this work, we make use of 3D visual contours carrying geometric as well as appearance information. Between these contours, we define 3D relations that encode structural info...
Emre Baseski, Leon Bodenhagen, Nicolas Pugeault, S...
ICMCS
2008
IEEE
330views Multimedia» more  ICMCS 2008»
14 years 4 months ago
Automatic trademark detection and recognition in sport videos
In this paper we describe a system for automatic detection and recognition of trademarks in sports videos. We propose a compact representation of trademarks based on SIFT feature ...
Lamberto Ballan, Marco Bertini, Alberto Del Bimbo,...
ICRA
2008
IEEE
150views Robotics» more  ICRA 2008»
14 years 4 months ago
Rigorously Bayesian range finder sensor model for dynamic environments
— This paper proposes and experimentally validates a Bayesian network model of a range finder adapted to dynamic environments. The modeling rigorously explains all model assumpt...
Tinne De Laet, Joris De Schutter, Herman Bruyninck...
SEMCO
2007
IEEE
14 years 4 months ago
Modeling Discriminative Global Inference
Many recent advances in complex domains such as Natural Language Processing (NLP) have taken a discriminative approach in conjunction with the global application of structural and...
Nicholas Rizzolo, Dan Roth
CVPR
2010
IEEE
14 years 4 months ago
One-Shot Multi-Set Non-rigid Feature-Spatial Matching
We introduce a novel framework for nonrigid feature matching among multiple sets in a way that takes into consideration both the feature descriptor and the features spatial arra...
Marwan Torki and Ahmed Elgammal