Dmytro Mishkin ๐บ๐ฆ (@ducha_aiki)
2025-02-24 | โค๏ธ 112 | ๐ 19
ELIP: Enhanced Visual-Language Foundation Models for Image Retrieval
@zgq1879, Yuanpei Liu, @hankaixyz , @WeidiXie Andrew Zisserman
tl;dr: condition the visual encoder on text query for better retrieval. https://arxiv.org/abs/2502.15682 https://x.com/ducha_aiki/status/1893976365805752790/photo/1
๐ ์๋ณธ ๋งํฌ
๋ฏธ๋์ด




๐ Related
Auto-generated - needs manual review