SOURCE-LINKED INTELLIGENCE

Efficient Language-to-Vision Feature Injection for Referring Single-Object Tracking

arXiv · AI, language, vision and robotics · article · Aug 29, 2026 · UTC

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

Read original source ↗ Open in workspace

recordType

paper

region

Global