BTMTrack: Robust RGB-T Tracking via Dual-template Bridging and Temporal-Modal Candidate Elimination

TL;DR

BTMTrack introduces a dual-template and temporal-modal candidate elimination framework for robust RGB-T tracking, effectively integrating temporal information and cross-modal interactions to improve accuracy in challenging conditions.

Contribution

The paper presents a novel RGB-T tracking framework with dual-template backbone, TMCE strategy, and TDTB module, enhancing temporal integration and cross-modal fusion for better tracking performance.

Findings

Achieves 72.3% precision on LasHeR dataset.

Outperforms existing methods on three benchmark datasets.

Demonstrates robustness in low-light and adverse weather conditions.

Abstract

RGB-T tracking leverages the complementary strengths of RGB and thermal infrared (TIR) modalities to address challenging scenarios such as low illumination and adverse weather. However, existing methods often fail to effectively integrate temporal information and perform efficient cross-modal interactions, which constrain their adaptability to dynamic targets. In this paper, we propose BTMTrack, a novel framework for RGB-T tracking. The core of our approach lies in the dual-template backbone network and the Temporal-Modal Candidate Elimination (TMCE) strategy. The dual-template backbone effectively integrates temporal information, while the TMCE strategy focuses the model on target-relevant tokens by evaluating temporal and modal correlations, reducing computational overhead and avoiding irrelevant background noise. Building upon this foundation, we propose the Temporal Dual Template Bridging (TDTB) module, which facilitates precise cross-modal fusion through dynamically filtered tokens. This approach further strengthens the interaction between templates and the search region. Extensive experiments conducted on three benchmark datasets demonstrate the effectiveness of BTMTrack. Our method achieves state-of-the-art performance, with a 72.3% precision rate on the LasHeR test set and competitive results on RGBT210 and RGBT234 datasets.