Synthesize then align: Modality alignment augmentation for zero-shot image captioning with synthetic data

Open Webpage

Zhiyue Liu, Jinyuan Liu, Xin Ling, Qingbao Huang, Jiahai Wang

Published: 2025, Last Modified: 15 Dec 2025Knowl. Based Syst. 2025EveryoneRevisionsBibTeXCC BY-SA 4.0