Video object tracking and segmentation with box annotation

作者：

Highlights：

• A two-stage framework with the box annotation reduces the runtime by a large margin.

• The box annotation automatically segments the object in the remaining frames.

• The segmentation cues are used to perform reverse optimization to locate the objects.

• The framework outperforms state-of-the-art methods in terms of mean IoU scores.

摘要

•A two-stage framework with the box annotation reduces the runtime by a large margin.•The box annotation automatically segments the object in the remaining frames.•The segmentation cues are used to perform reverse optimization to locate the objects.•The framework outperforms state-of-the-art methods in terms of mean IoU scores.

论文关键词：Video object tracking,Video object segmentation,Reverse optimization,Bounding box annotation

论文评审过程：Received 15 August 2019, Revised 12 March 2020, Accepted 12 April 2020, Available online 20 April 2020, Version of Record 29 April 2020.

论文官网地址：https://doi.org/10.1016/j.image.2020.115858