"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset."

Sihan Chen et al. (2023)

Details and statistics

DOI: 10.48550/ARXIV.2305.18500

access: open

type: Informal or Other Publication

metadata version: 2023-09-03

a service of  Schloss Dagstuhl - Leibniz Center for Informatics