Learning user interest with improved triplet deep ranking and web-image priors for topic-related video summarization

作者：

Highlights：

• A new Flickr images dataset is collected to learn what is of interest to users.

• An improved triplet deep ranking model is proposed to generate video summaries.

• A novel efficient and accurate entropy-based video segmentation method is proposed.

摘要

•A new Flickr images dataset is collected to learn what is of interest to users.•An improved triplet deep ranking model is proposed to generate video summaries.•A novel efficient and accurate entropy-based video segmentation method is proposed.

论文关键词：Video summarization,Web-image priors,Improved triplet deep ranking,Image entropy,Video segmentation

论文评审过程：Received 27 January 2019, Revised 16 September 2020, Accepted 16 September 2020, Available online 29 September 2020, Version of Record 9 October 2020.

论文官网地址：https://doi.org/10.1016/j.eswa.2020.114036