TU Berlin

Communication Systems GroupScientific Publications

Page Content

to Navigation

Scientific Publications

Hierarchical Learning of Sparse Image Representations using Steered Mixture-of-Experts
Citation key 1536Jongebloed2018
Author Rolf Jongebloed and Ruben Verhack and Lieven Lange and Thomas Sikora
Title of Book 2018 IEEE International Conference on Multimedia Expo Workshops (ICMEW)
Year 2018
Address San Diego, CA, USA
Organization IEEE
Abstract Previous 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.
Link to publication Download Bibtex entry

Navigation

Quick Access

Schnellnavigation zur Seite über Nummerneingabe