ContextBLIP: Doubly Contextual Alignment for Contrastive Image Retrieval from Linguistically Complex Descriptions.
Honglin LinSiyu LiGuoshun NanChaoyue TangXueting WangJingxin XuYankai RongZhouzhili ZhouzhiliYutong GaoQimei CuiXiaofeng TaoPublished in: ACL (Findings) (2024)