Sciweavers

240 search results - page 11 / 48
» An Evolutionary Approach for Learning Motion Class Patterns
Sort
View
TNN
2010
171views Management» more  TNN 2010»
14 years 4 months ago
Sensitivity versus accuracy in multiclass problems using memetic Pareto evolutionary neural networks
This paper proposes a multiclassification algorithm using multilayer perceptron neural network models. It tries to boost two conflicting main objectives of multiclassifiers: a high...
Juan Carlos Fernández Caballero, Francisco ...
ICIP
2009
IEEE
15 years 10 months ago
Learning Local Models For 2d Human Motion Tracking
We present a novel approach to tracking 2D human motion in uncalibrated monocular videos. Human motion usually exhibits timevarying patterns, and we propose to use locally learnt ...
ACCV
2009
Springer
15 years 4 months ago
Detecting Spatiotemporal Structure Boundaries: Beyond Motion Discontinuities
Abstract. The detection of motion boundaries has been and remains a longstanding challenge in computer vision. In this paper, the recovery of motion boundaries is recast in a broad...
Konstantinos G. Derpanis, Richard P. Wildes
PRL
2007
200views more  PRL 2007»
14 years 9 months ago
Generative learning of visual concepts using multiobjective genetic programming
This paper introduces a novel method of visual learning based on Genetic Programming, which evolves a population of individuals (image analysis programs) that process attributed v...
Krzysztof Krawiec
92
Voted
EUSFLAT
2009
140views Fuzzy Logic» more  EUSFLAT 2009»
14 years 7 months ago
Incremental Possibilistic Approach for Online Clustering and Classification
In this paper, we propose to develop the supervised classification method Fuzzy Pattern Matching to be in addition a non supervised one. The goal is to monitor dynamic systems with...
Moamar Sayed Mouchaweh, Bernard Riera