Efficient Language-to-Vision Feature Injection for Referring Single-Object Tracking
TL;DR
LVTrack is presented, a pure transformer framework that introduces a mode-conditioned Gated Feature Injector to adaptively regulate textual guidance and alleviate semantic drift, and directly harnesses a frozen vision-language pretrained model, greatly reducing training cost and preserving strong language understanding.
Abstract
Referring single-object tracking enables language-grounded target initialization and subsequent tracking by jointly leveraging semantic cues and visual templates. The core difficulty is to use language differently across stages: it is indispensable for grounding but can induce semantic drift during tracking when overemphasized. Meanwhile, current methods often require costly vision-language alignment training. We present LVTrack, a pure transformer framework that introduces a mode-conditioned Gated Feature Injector to adaptively regulate textual guidance and alleviate semantic drift. Together with targeted adaptations, it directly harnesses a frozen vision-language pretrained model, greatly reducing training cost and preserving strong language understanding. To further improve temporal localization, LVTrack integrates hybrid relative-absolute positional encodings with a lightweight memory mechanism and optimizes autoregressive box prediction using a Gaussian-smoothed KL loss. Extensive experiments on standard benchmarks demonstrate that LVTrack achieves strong performance.