210 citations · 633 across the 54 of their papers we have counts for
1 paper · 2 filters
Virginie Do, Oana-Maria Camburu, Zeynep Akata +1
The recently proposed SNLI-VE corpus for recognising visual-textual entailment is a large, real-world dataset for fine-grained multimodal reasoning. However, the automatic way in w…