"Text encoders are performance bottlenecks in contrastive vision-language ..."

Amita Kamath, Jack Hessel, Kai-Wei Chang (2023)

Details and statistics

DOI: 10.48550/ARXIV.2305.14897

access: open

type: Informal or Other Publication

metadata version: 2023-06-06

a service of  Schloss Dagstuhl - Leibniz Center for Informatics