Global coordination based on matrix neural gas for dynamic texture synthesis

Authors:
Banchar Arnonkijpanich;Barbara Hammer
Affiliations:
Department of Mathematics, Faculty of Science, Khon Kaen University, Thailand;CITEC, University of Bielefeld, Bielefeld, Germany
Venue:
ANNPR'10 Proceedings of the 4th IAPR TC3 conference on Artificial Neural Networks in Pattern Recognition
Year:
2010

Citing 9
Cited 0

Topology representing networks

Neural Networks
Self-organizing maps

Self-organizing maps
Mixtures of probabilistic principal component analyzers

Neural Computation
Fast texture synthesis using tree-structured vector quantization

Proceedings of the 27th annual conference on Computer graphics and interactive techniques
Dynamic Textures

International Journal of Computer Vision
Keyframe control of smoke simulations

ACM SIGGRAPH 2003 Papers
Animating pictures with stochastic motion textures

ACM SIGGRAPH 2005 Papers
Batch and median neural gas

Neural Networks - 2006 Special issue: Advances in self-organizing maps--WSOM'05
2010 Special Issue: Local matrix learning in clustering and applications for manifold visualization

Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

Matrix neural gas has been proposed as a mathematically well-founded extension of neural gas networks to represent data in terms of prototypes and local principal components in a smooth way. The additional information provided by local principal directions can directly be combined with charting techniques such that a nonlinear embedding of a data manifold into low dimensions results for which an explicit function as well as an approximate inverse exists. In this paper, we show that these ingredients can be used to embed dynamic textures in low dimensional spaces such that, together with a traversing technique in the low dimensional representation, efficient dynamic texture synthesis can be obtained.