VDQG (Visual Discriminative Question Generation)

Introduced by Li et al. in Learning to Disambiguate by Asking Discriminative Questions

The Visual Discriminative Question Generation (VDQG) dataset contains 11202 ambiguous image pairs collected from Visual Genome. Each image pair is annotated with 4.6 discriminative questions and 5.9 non-discriminative questions on average.

Papers


Paper Code Results Date Stars

Tasks


Similar Datasets


License


  • Unknown

Modalities


Languages