MUST-VQA: MUltilingual Scene-text VQA.

Emanuele Vivoli Ali Furkan Biten Andrés Mafla Dimosthenis Karatzas Lluís Gómez

Published in: CoRR (2022)

Keyphrases

video quality assessment
image database
video database
text detection
scene text
image data
computer vision
human visual system
natural scene images
video data
image content
video retrieval
color images
binary images
temporal information
video clips