Visual Discriminative Question Generation (VDQG) dataset

by No License

Visual Discriminative Question Generation (VDQG) dataset

The 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. The dataset is used in our ICCV 2017 paper "Learning to Disambiguate by Asking Discriminative Questions". (http://personal.ie.cuhk.edu.hk/~ccloy/files/iccv_2017_learning.pdf)

Dataset Attributes

Label SVG
CategoriesVision, Language, Vqa, Question, Genome, Biology