What is it about?

It is a novel real-time video object tracking algorithm based on graph attention network and Siamese network. This method can effectively make the tracker constantly adapt to the change of object appearance and improve the robustness and accuracy of the tracker.

Featured Image

Why is it important?

Because in the traditional video target tracking process, it is difficult to adapt to the appearance change of the target without updating the template. Therefore, a good template updating method is an important condition for video target tracking algorithm.


I hope this article will inspire researchers who need new templates for object tracking.

Xiaopeng Li

Read the Original

This page is a summary of: A Multi‐Template Fusion Object Tracking Algorithm Based on Graph Attention Network, IEEJ Transactions on Electrical and Electronic Engineering, October 2022, Wiley,
DOI: 10.1002/tee.23719.
You can read the full text:



The following have contributed to this page