"BUS: Efficient and Effective Vision-language Pre-training with Bottom-Up ..."

Chaoya Jiang et al. (2023)

Details and statistics

DOI: 10.48550/ARXIV.2307.08504

access: open

type: Informal or Other Publication

metadata version: 2023-09-11

a service of  Schloss Dagstuhl - Leibniz Center for Informatics