A tree-structured memory network that uses parse trees and distinguishes visual from verbal words improves video question answering accuracy over flat sequence attention baselines.
Title resolution pending
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
-
A Better Way to Attend: Attention with Trees for Video Question Answering
A tree-structured memory network that uses parse trees and distinguishes visual from verbal words improves video question answering accuracy over flat sequence attention baselines.