Visual tracking by dynamic matching-classification network switching

作者：

Highlights：

• A dynamic matching-classification switching framework is proposed to effectively integrate the matching, classification and verification networks.

• A meta classifier is learned to adapt quickly to the current appearance changes through one iteration one training sample, which speeds up the online tracking.

• Extensive experiments on two popular benchmarks show that the proposed tracker achieves good performance compared with recent state-of-the-art methods.

摘要

•A dynamic matching-classification switching framework is proposed to effectively integrate the matching, classification and verification networks.•A meta classifier is learned to adapt quickly to the current appearance changes through one iteration one training sample, which speeds up the online tracking.•Extensive experiments on two popular benchmarks show that the proposed tracker achieves good performance compared with recent state-of-the-art methods.

论文关键词：Visual Tracking,Deep Learning,Ensemble learning

论文评审过程：Received 14 February 2019, Revised 5 January 2020, Accepted 3 May 2020, Available online 1 June 2020, Version of Record 18 June 2020.

论文官网地址：https://doi.org/10.1016/j.patcog.2020.107419