Progressive reinforcement learning for video summarization

Guolong Wang, Xun Wu, Junchi Yan

Abstract: Highlights•We design a progressive reinforcement learning structure for video summarization (PRLVS).•Our PRLVS simulates a “T”-type thinking paradigm by optimizing a horizontal and vertical policy alternatively.•Our PRLVS incorporates an unsupervised reward measuring the amount of information carried by the summaries.