"Fine-Grained Semantically Aligned Vision-Language Pre-Training."

Juncheng Li et al. (2022)

Details and statistics

DOI: 10.48550/ARXIV.2208.02515

access: open

type: Informal or Other Publication

metadata version: 2022-09-28

a service of  Schloss Dagstuhl - Leibniz Center for Informatics