2 datasets found

Tags: Compositional Language

Filter Results
  • CLEVR-CoGenT

    The CLEVR-CoGenT dataset is a dataset for visual question answering, where the questions consist on comparing the position of two objects.
  • CLEVR

    CLEVR images contain objects characterized by a set of attributes (shape, color, size and material). The questions are grouped into 5 categories: Exist, Count, CompareInteger,...