conference paper


Conference/Proceedings2018 IEEE International Conference on Multimedia Expo Workshops (ICMEW)
Start date23.07.2018
End date27.07.2018
AddressSan Diego, CA, USA
OrganisationIEEE
Author(s)Rolf Jongebloed, Ruben Verhack, Lieven Lange, Thomas Sikora
TitleHierarchical Learning of Sparse Image Representations using Steered Mixture-of-Experts
AbstractPrevious research showed highly efficient compression
results for low bit-rates using Steered Mixture-of-Experts
(SMoE), higher rates still pose a challenge due to the non-
convex optimization problem that becomes more difficult
when increasing the number of components. Therefore, a
novel estimation method based on Hidden Markov Random
Fields is introduced taking spatial dependencies of neighbor-
ing pixels into account combined with a tree-structured split-
ting strategy. Experimental evaluations for images show that
our approach outperforms state-of-the-art techniques using
only one robust parameter set. For video and light field mod-
eling even more gain can be expected.
Key wordsBayes methods, mixture models, Bayesian model, nonstationary random process, piecewise stationary processes, pixel values, space-continuous Gaussian mixture model, statistical representation, steered mixture-of-experts, Analytical models, Estimation, Gaussian mixture model, Image reconstruction, mixture models, mixture-of-experts, Hierarchical Learning
File1536Jongebloed2018.pdf

[BibTeX]