Transformer-based Cross-Modal Recipe Embeddings with Large Batch Training.

Jing Yang Junwen Chen Keiji Yanai

Published in: CoRR (2022)

Keyphrases

cross modal
multi modal
training set
training examples
image retrieval
visual recognition
multimedia retrieval
supervised learning
perceptual information
distance measure
low dimensional
multimedia databases
dimensionality reduction
high dimensional data
text retrieval
visual data