# Target-Aware Tracking with Long-term Context Attention

## TL;DR

This paper introduces TATrack, a novel long-term context attention module embedded in a Transformer-based tracker, significantly improving robustness and accuracy in visual tracking by utilizing extensive contextual information.

## Contribution

The paper proposes the LCA module for long-term context fusion and a dynamic online update algorithm, advancing tracker robustness and accuracy over existing methods.

## Key findings

- Achieves state-of-the-art performance on multiple benchmarks.
- Improves robustness against appearance changes and similar objects.
- Enhances target localization accuracy.

## Abstract

Most deep trackers still follow the guidance of the siamese paradigms and use a template that contains only the target without any contextual information, which makes it difficult for the tracker to cope with large appearance changes, rapid target movement, and attraction from similar objects. To alleviate the above problem, we propose a long-term context attention (LCA) module that can perform extensive information fusion on the target and its context from long-term frames, and calculate the target correlation while enhancing target features. The complete contextual information contains the location of the target as well as the state around the target. LCA uses the target state from the previous frame to exclude the interference of similar objects and complex backgrounds, thus accurately locating the target and enabling the tracker to obtain higher robustness and regression accuracy. By embedding the LCA module in Transformer, we build a powerful online tracker with a target-aware backbone, termed as TATrack. In addition, we propose a dynamic online update algorithm based on the classification confidence of historical information without additional calculation burden. Our tracker achieves state-of-the-art performance on multiple benchmarks, with 71.1\% AUC, 89.3\% NP, and 73.0\% AO on LaSOT, TrackingNet, and GOT-10k. The code and trained models are available on https://github.com/hekaijie123/TATrack.