Preprint
Aug 2026
Efficient Language-to-Vision Feature Injection for Referring Single-Object Tracking
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...
Han Wang, Yuxuan Liu, Yuhan Sun et al.
· 0 citations