3 papers
cs.MM2018
HEVC Inter Coding Using Deep Recurrent Neural Networks and Artificial Reference Pictures
Felix Haub, Thorsten Laude, Jörn Ostermann
The efficiency of motion compensated prediction in modern video codecs highly depends on the available reference pictures. Occlusions and non-linear motion pose challenges for the…
cs.CV2018
Neural Network Compression using Transform Coding and Clustering
Thorsten Laude, Yannick Richter, Jörn Ostermann
With the deployment of neural networks on mobile devices and the necessity of transmitting neural networks over limited or expensive channels, the file size of the trained model wa…
cs.CV2018
Unsupervised Features for Facial Expression Intensity Estimation over Time
Maren Awiszus, Stella Graßhof, Felix Kuhnke +1
The diversity of facial shapes and motions among persons is one of the greatest challenges for automatic analysis of facial expressions. In this paper, we propose a feature describ…