<<
| Conference/Proceedings | Picture Coding Symposium |
| Start date | 04.12.2016 |
| End date | 07.12.2016 |
| Address | Nuremberg, Germany |
| Publisher | IEEE |
| Pages | 1-5 |
| Author(s) | Lieven Lange, Ruben Verhack, Thomas Sikora |
| Title | Video Representation and Coding Using a Sparse Steered Mixture-of-Experts Network |
| Abstract | In this paper, we introduce a novel approach for video compression that explores spatial as well as temporal redundancies over sequences of many frames in a unified framework. Our approach supports “compressed domain vision” capabilities. To this end, we developed a sparse Steered Mixture of- Experts (SMoE) regression network for coding video in the pixel domain. This approach drastically departs from the established DPCM/Transform coding philosophy. Each kernel in the Mixture-of-Experts network steers along the direction of highest correlation, both in spatial and temporal domain, with local and global support. Our coding and modeling philosophy is embedded in a Bayesian framework and shows strong resemblance to Mixture-of-Experts neural networks. Initial experiments show that at very low bit rates the SMoE approach can provide competitive performance to H.264. |
| Key words | compression, video coding, steered mixture of experts, video representation, video descriptor |
| Note | In IEEE-Explore zugefügt am 24 April 2017! Electronic ISSN: 2472-7822 DOI: 10.1109/PCS.2016.7906369 |
| File | 1502Lange2016.pdf |
BibTeX