The authors introduce a nine-reason taxonomy and two labeled datasets explaining why visual questions get different answers, and a multi-label predictor of those reasons.
Bottom-up and top-down attention for image captioning and visual question answering
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Why Does a Visual Question Have Different Answers?
The authors introduce a nine-reason taxonomy and two labeled datasets explaining why visual questions get different answers, and a multi-label predictor of those reasons.