Improving visual question answering by combining scene-text information.

Himanshu Sharma Anand Singh Jalal

Published in: Multim. Tools Appl. (2022)

Keyphrases

question answering
text information
web images
textual information
visual information
natural language processing
information retrieval
complex background
visual features
video sequences
image search
information extraction
high level
complex scenes
low level
natural language
keywords
named entities
term frequency