Unsupervised Video Summarization Based on An Encoder-Decoder Architecture

Abstract

Abstract The purpose of video summarization is to facilitate large-scale video browsing. Video summarization is a short and concise synopsis of original video. It usually composed of a set of representative video frames from the original video. This paper solves the problem of unsupervised video summarization by developing a Video Summarization Network (VSN) to summarize videos, which is formulated as selecting a sparse subset of video frames that best represents the input video. VSN predicts a probability for each video frame, which indicates the possibility of a frame being selected, and then takes actions to select frames according to the probability distribution to form a video summary. We designed a novel loss function which takes into account the diversity and representativeness of the generated summarization without labels or user interaction.