From VQA to Multimodal CQA: Adapting Visual QA Models for Community QA Tasks.

Avikalp Srivastava Hsin Wen Liu Sumio Fujita

Published in: CoRR (2018)

Keyphrases

question answering
question answer
visual tasks
probabilistic model
image database
question answering systems
question classification
open domain
qa clef
machine learning
high level
natural language
information extraction
natural language processing
language model
visual information