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