FigureQA: An Annotated Figure Dataset for Visual Reasoning

    Adam Atkinson
    Adam Atkinson
    Ákos Kádár
    Ákos Kádár
    Adam Trischler
    Adam Trischler

    international conference on learning representations, 2018.

    Cited by: 3|Bibtex|Views94|Links
    EI

    Abstract:

    We introduce FigureQA, a visual reasoning corpus of over one million question-answer pairs grounded in over 100,000 images. The images are synthetic, scientific-style figures from five classes: line plots, dot-line plots, vertical and horizontal bar graphs, and pie charts. We formulate our reasoning task by generating questions from 15 te...More

    Code:

    Data:

    Your rating :
    0

     

    Tags
    Comments