Dynamic graph convolutional network for multi-video summarization

作者：

Highlights：

• The first work on dynamic graph convolutional network for multi-video summarization.

• Two strategies are proposed to solve the class imbalance problem of the task.

• A diversity regularization is designed to encourage a diverse summarization.

• The proposed model can generate diverse summaries and achieve state-of-the-art performances.

摘要

•The first work on dynamic graph convolutional network for multi-video summarization.•Two strategies are proposed to solve the class imbalance problem of the task.•A diversity regularization is designed to encourage a diverse summarization.•The proposed model can generate diverse summaries and achieve state-of-the-art performances.

论文关键词：Multi-video summarization,Graph convolutional network,Class imbalance problem

论文评审过程：Received 28 May 2019, Revised 3 April 2020, Accepted 15 April 2020, Available online 20 June 2020, Version of Record 1 July 2020.

论文官网地址：https://doi.org/10.1016/j.patcog.2020.107382