Weakly Supervised Grounding for VQA in Vision-Language Transformers.

Aisha Urooj Khan Hilde Kuehne Chuang Gan Niels da Vitoria Lobo Mubarak Shah

Published in: ECCV (35) (2022)

Keyphrases

weakly supervised
topic models
object class
relation extraction
computer vision
semi supervised
superpixels
image database
natural language
image segmentation
object recognition
viewpoint
domain specific
unsupervised learning
named entities