RefineRank: Joint Box Refinement and Ranking for Surgical Spatio-Temporal Grounding
Results show that a small box-level module can reconcile question understanding with precise localization without retraining either backbone, and introduce RefineRank, which closes this gap at the candidate-box level.
Linzhe Jiang, Jiayuan Huang, Changhao Zhang et al.
· 0 citations