Eccv caption: Correcting false negatives by collecting machine-and-human-verified image-caption associations for ms-cocoJan 1, 2022ยทSanghyuk Chun,Wonjae KimSong Park,Minsuk Chang,Seong Joon Ohยท 0 min read PDF Cite CodeTypeConference paperPublicationEuropean Conference on Computer VisionLast updated on Jan 1, 2022 AuthorsSong ParkResearch Scientist ← SeiT: Storage-efficient vision training with tokens using 1% of pixel storage Jan 1, 2023Few-shot font generation with weakly supervised localized representations Jan 1, 2022 →