FreqTrack: Frequency Learning based Vision Transformer for RGB-Event Object Tracking

TL;DR

FreqTrack introduces a frequency-aware transformer framework for RGB-event object tracking, leveraging frequency-domain transformations and wavelet-based edge refinement to improve robustness in complex scenes.

Contribution

The paper proposes a novel frequency-domain fusion method with a spectral enhancement transformer and wavelet edge refinement for improved RGB-event tracking.

Findings

Achieves 76.6% precision on COESOT benchmark.

Outperforms existing RGB-event tracking methods.

Effectively models high-frequency event data in challenging scenarios.

Abstract

Existing single-modal RGB trackers often face performance bottlenecks in complex dynamic scenes, while the introduction of event sensors offers new potential for enhancing tracking capabilities. However, most current RGB-event fusion methods, primarily designed in the spatial domain using convolutional, Transformer, or Mamba architectures, fail to fully exploit the unique temporal response and high-frequency characteristics of event data. To address this, we1 propose FreqTrack, a frequency-aware RGBE tracking framework that establishes complementary inter-modal correlations through frequency-domain transformations for more robust feature fusion. We design a Spectral Enhancement Transformer (SET) layer that incorporates multi-head dynamic Fourier filtering to adaptively enhance and select frequency-domain features. Additionally, we develop a Wavelet Edge Refinement (WER) module, which leverages learnable wavelet transforms to explicitly extract multi-scale edge structures from event data, effectively improving modeling capability in high-speed and low-light scenarios. Extensive experiments on the COESOT and FE108 datasets demonstrate that FreqTrack achieves highly competitive performance, particularly attaining leading precision of 76.6\% on the COESOT benchmark, validating the effectiveness of frequency-domain modeling for RGBE tracking.