BSTrack: Bridging Cross-Modal Spatio-Temporal Differences in Vision-Language Tracking
Yihao Zhen, Qiang Wang, Liangqiong Qu, Huijie Fan
IEEE Transactions on Circuits and Systems for Video Technology
official publication
A vision-language tracker that bridges cross-modal spatio-temporal differences through fine-grained input decoupling and efficient semantic information updating.
|