The 2nd Anti-UAV Workshop \& Challenge aims to encourage research in developing novel and accurate methods for multi-scale object tracking.
Our method has the following two advantages: (1) We are the first to consider neighborhood information of descriptors, while former works mainly focus on neighborhood consistency of feature points; (2) Our method can be applied in any former work of learning descriptors by triplet loss.
We evaluate and analyze more than 30 trackers on LSOTB-TIR to provide a series of baselines, and the results show that deep trackers achieve promising performance.
Moreover, we introduce a classification part that is trained online and optimized with a Conjugate-Gradient-based strategy to guarantee real-time tracking speed.
These two feature models are learned using a multi-task matching framework and are jointly optimized on the TIR tracking task.
These two similarities complement each other and hence enhance the discriminative capacity of the network for handling distractors.
In this paper, we cast the TIR tracking problem as a similarity verification task, which is coupled well to the objective of the tracking task.