Deep visual tracking: Review and experimental comparison

作者：

Highlights：

• The first comprehensive survey on deep-learning-based trackers.

• Review existing deep visual trackers from three different perspectives.

• Large-scale benchmark evaluations of deep visual trackers.

• Summarize cutting-edge research works and discuss future directions

• Provide useful insights and conclusions for deep visual trackers.

摘要

•The first comprehensive survey on deep-learning-based trackers.•Review existing deep visual trackers from three different perspectives.•Large-scale benchmark evaluations of deep visual trackers.•Summarize cutting-edge research works and discuss future directions•Provide useful insights and conclusions for deep visual trackers.

论文关键词：Visual tracking,Deep learning,CNN,RNN,Pre-training,Online learning

论文评审过程：Received 3 May 2017, Revised 19 October 2017, Accepted 5 November 2017, Available online 6 November 2017, Version of Record 21 December 2017.

论文官网地址：https://doi.org/10.1016/j.patcog.2017.11.007