Separate and Locate: Rethink the Text in Text-based Visual Question Answering.

Chengyang Fang Jiangnan Li Liang Li Can Ma Dayong Hu

Published in: ACM Multimedia (2023)

Keyphrases

question answering
syntactic information
information retrieval
text summarization
visual features
semantic parsing
natural language processing
visual information
named entities
textual entailment recognition

natural language questions
question classification
natural language text
cross language
keywords
information extraction
natural language
relation extraction
passage retrieval

text mining
qa clef
question answering systems
text retrieval
free text
semantic information
text documents
news video
answering questions

answer validation
semantic roles
question answer pairs
image classification
image search
visual data
sentence retrieval
semantic role labeling
artificial intelligence