"VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending."

Xingjian He et al. (2023)

Details and statistics

DOI: 10.48550/ARXIV.2305.13167

access: open

type: Informal or Other Publication

metadata version: 2024-02-07

a service of  Schloss Dagstuhl - Leibniz Center for Informatics