Salient event detection via hypergraph convolutional network with cross-view self-supervised learning

Enchang Zhu, Zhengtao Yu, Yuxin Huang, Shengxiang Gao, Yantuan Xian

Abstract: Highlights•A Hypergraph Learning Model based on Cross-view Self-supervised Learning for Salient Event Detection (SEDGS) is proposed.•We design argument-view hypergraphs and event-view hypergraphs to model event context information and inter-event correlation information, respectively.•We design a novel cross-view self-supervised learning paradigm in model training to enhance hypergraph modeling and improve the salient event detection task.•Experimental results on the publicly available SED dataset demonstrate the superiority of our proposed method.