Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language Models

Open Webpage

Archiki Prasad, Elias Stengel-Eskin, Mohit Bansal

Published: 01 Jan 2024, Last Modified: 27 Sept 2024ICLR 2024EveryoneRevisionsBibTeXCC BY-SA 4.0