Weakly-Supervised Learning of Visual Relations in Multimodal Pretraining.

Emanuele Bugliarello Aida Nematzadeh Lisa Anne Hendricks

Published in: CoRR (2023)

Keyphrases

weakly supervised learning
object detection
weakly supervised
multi modal
object class
multiple instance learning
computer vision
visual features
visual information
semantic relations
low level
multiscale
spatial relations
pairwise
image features