Siamese network for object tracking with multi-granularity appearance representations
作者：
Highlights：
• Enhance semantic feature representations for targets in tracking by a improved Siamese network and a convolutional block attention module.
• Capture multi-granularity appearance features of objects at pixel, local and global level accurately.
• Combine two models dynamically with the Hedge algorithm in a selective traverse fashion efficiently to track objects.
• Design an updatable tracker which performs better that most state-of-the-art trackers and operates at speeds that exceed the real-time requirement.
摘要
•Enhance semantic feature representations for targets in tracking by a improved Siamese network and a convolutional block attention module.•Capture multi-granularity appearance features of objects at pixel, local and global level accurately.•Combine two models dynamically with the Hedge algorithm in a selective traverse fashion efficiently to track objects.•Design an updatable tracker which performs better that most state-of-the-art trackers and operates at speeds that exceed the real-time requirement.
论文关键词：Object tracking,Siamese network,Appearance adaption
论文评审过程：Received 8 September 2019, Revised 22 March 2021, Accepted 26 April 2021, Available online 2 May 2021, Version of Record 16 May 2021.
论文官网地址：https://doi.org/10.1016/j.patcog.2021.108003
