"Semantic Compositions Enhance Vision-Language Contrastive Learning."

Maxwell Mbabilla Aladago, Lorenzo Torresani, Soroush Vosoughi (2024)

Details and statistics

DOI: 10.48550/ARXIV.2407.01408

access: open

type: Informal or Other Publication

metadata version: 2024-08-13

a service of  Schloss Dagstuhl - Leibniz Center for Informatics