“…Temporal nature of video Many video quality metrics account for the temporal nature of video by using pooling approaches as the Minkowski summation [21,58,183,343,349,353,354] or percentile pooling [27,116,190], while others include frames in a small interval around the current frame into the prediction [21,183,282] or use the differences to the preceding frame in the prediction [78,212,224,227,228,232,277,341,370,373]. Only a small subset of all metrics consider the temporal dimension of video without any significant temporal pooling or at least consider a relatively large interval of a few seconds [11,135,172,203,220,332].…”