Preprint
Sep 2026
Concepts Complement Dense Semantics: Learning Compact Sparse Spaces for Text-Image Retrieval
Cross-modal retrieval has been advanced by vision-language pre-trained models that encode images and texts into a shared dense embedding space. While dense representations effectively capture overall semantic similarity, they often obscure fine-grained visual-textual information needed for precise cross-modal matching....
Yoonseo Kim, Jung A. Choi, Cheonyoung Park et al.
· 0 citations