Publications
-
One Patch to Caption Them All: A Unified Zero-Shot Captioning Framework
Zero-shot captioners are recently proposed models that utilize common-space vision-language representations to caption images without... read more -
CountingDINO 🧮🦕 A Training-free Pipeline for Exemplar-based Class-Agnostic Counting
Class-agnostic counting (CAC) aims to estimate the number of objects in images without being restricted... read more -
Maybe you are looking for CroQS 🐊 Cross-modal Query Suggestion for Text-to-Image Retrieval
Query suggestion, a technique widely adopted in information retrieval, enhances system interactivity and the browsing... read more