Efficient Multilingual Multi-modal Pre-training through Triple Contrastive Loss.

Youhan Lee Kyungtae Lim Woonhyuk Baek Byungseok Roh Saehoon Kim

Published in: COLING (2022)

Keyphrases

multi modal
multi modality
cross modal
audio visual
semantic concepts
video search
image registration
medical images
image classification
single modality