A binary-search style reward that halves candidate objects each round improves goal-oriented visual dialogue accuracy and reduces question repetition.
In Proceedings of COMPSTAT’2010: 19th International Conference on Computational Statistic- sParis France, August 22-27, 2010 Keynote, Invited and Contributed Papers, 177–186
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Divide-and-Conquer: Tree-structured Strategy with Answer Distribution Estimator for Goal-Oriented Visual Dialogue
A binary-search style reward that halves candidate objects each round improves goal-oriented visual dialogue accuracy and reduces question repetition.