TU Berlin

Fachgebiet NachrichtenübertragungWiss. Veröffentlichungen

Inhalt des Dokuments

zur Navigation

Wissenschaftliche Veröffentlichungen

Hierarchical Learning of Sparse Image Representations using Steered Mixture-of-Experts
Zitatschlüssel 1536Jongebloed2018
Autor Rolf Jongebloed and Ruben Verhack and Lieven Lange and Thomas Sikora
Buchtitel 2018 IEEE International Conference on Multimedia Expo Workshops (ICMEW)
Jahr 2018
Adresse San Diego, CA, USA
Organisation IEEE
Zusammenfassung 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 zur Publikation Download Bibtex Eintrag



Schnellnavigation zur Seite über Nummerneingabe