Overview of deep-learning based methods for salient object detection in videos

作者：

Highlights：

• This paper provides an overview of recent deep-learning based methods for salient object detection in videos.

• A classification of the state-of-the-art methods and their frameworks is provided.

• The performance of state-of-the-art methods is further analysed through experimental comparison on different public datasets and ablation study on the impact of variants.

摘要

•This paper provides an overview of recent deep-learning based methods for salient object detection in videos.•A classification of the state-of-the-art methods and their frameworks is provided.•The performance of state-of-the-art methods is further analysed through experimental comparison on different public datasets and ablation study on the impact of variants.

论文关键词：Deep-learning,Salient object detection,Video

论文评审过程：Received 7 March 2019, Revised 12 February 2020, Accepted 17 March 2020, Available online 19 March 2020, Version of Record 7 April 2020.

论文官网地址：https://doi.org/10.1016/j.patcog.2020.107340