"DeCap: Decoding CLIP Latents for Zero-Shot Captioning via Text-Only Training."

Wei Li et al. (2023)

Details and statistics

DOI: 10.48550/ARXIV.2303.03032

access: open

type: Informal or Other Publication

metadata version: 2023-11-02

a service of  Schloss Dagstuhl - Leibniz Center for Informatics