Preprint
Aug 2026
Entity-Faithful Repair of Synthetic Supervision for Zero-Shot Image Captioning
ReCap is a plug-and-play framework that shifts synthetic data refinement from implicit global matching to explicit fine-grained realignment, and enforces entity-level correspondence by using detected image-supported entities to guide caption rewriting, yielding more faithful synthetic supervision.
Zhiyue Liu, Wenkai Zhou, Jian Qin et al.
· 0 citations