A Transformer sequence-to-sequence model translates scene graphs into semantic layouts via new token codes, and a new metric SLEU measures layout similarity.
Spice: Semantic propositional image cap- tion evaluation
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
-
Seq-SG2SL: Inferring Semantic Layout from Scene Graph Through Sequence to Sequence Learning
A Transformer sequence-to-sequence model translates scene graphs into semantic layouts via new token codes, and a new metric SLEU measures layout similarity.