"If CLIP Could Talk: Understanding Vision-Language Model Representations ..."

Reza Esfandiarpoor, Cristina Menghini, Stephen H. Bach (2024)

Details and statistics

DOI: 10.48550/ARXIV.2403.16442

access: open

type: Informal or Other Publication

metadata version: 2024-04-09

a service of  Schloss Dagstuhl - Leibniz Center for Informatics