Motion-aware video quality assessment

This work focuses on considering motion towards improving video quality assessment algorithms. The improvement refers to improving computational video quality assessment algorithms in order to be in closer agreement with the subjective evaluation of video quality. We propose a motion saliency model that exploits motion features on spatial level and also an approach for consideration of global motion in the temporal dimension, leading to further improvements in the accuracy of video quality assessment. We perform evaluation by integrating our approaches in existing objective quality models and also by comparing them to existing related state-of-the-art video quality assessment methods.