Localize, Group, and Select: Boosting Text-VQA by Scene Text Modeling.

Xiaopeng Lu Zhen Fan Yansen Wang Jean Oh Carolyn P. Rosé

Published in: CoRR (2021)

Keyphrases

scene text
text detection
image database
natural scene images
text mining
video database
text information
scene images
complex background
text regions
computer vision
multiscale
keywords
visual features