LEAF-QA: Locate, Encode & Attend for Figure Question Answering

@article{Chaudhry2020LEAFQALE,
  title={LEAF-QA: Locate, Encode & Attend for Figure Question Answering},
  author={Ritwick Chaudhry and Sumit Shekhar and Utkarsh Gupta and Pranav Maneriker and Prann Bansal and A. Joshi},
  journal={2020 IEEE Winter Conference on Applications of Computer Vision (WACV)},
  year={2020},
  pages={3501-3510}
}
  • Ritwick Chaudhry, Sumit Shekhar, +3 authors A. Joshi
  • Published 2020
  • Computer Science
  • 2020 IEEE Winter Conference on Applications of Computer Vision (WACV)
  • We introduce LEAF-QA, a comprehensive dataset of $250,000$ densely annotated figures/charts, constructed from real-world open data sources, along with ~2 million question-answer (QA) pairs querying the structure and semantics of these charts. [...] Key Method To this end, LEAF-Net, a deep architecture involving chart element localization, question and answer encoding in terms of chart elements, and an attention network is proposed. Different experiments are conducted to demonstrate the challenges of QA on LEAF…Expand Abstract

    Figures, Tables, and Topics from this paper.

    An Affinity-Driven Relation Network for Figure Question Answering
    Answering Questions about Charts and Generating Visual Explanations
    1
    A Formative Study on Designing Accurate and Natural Figure Captioning Systems

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 32 REFERENCES
    Visual7W: Grounded Question Answering in Images
    413
    FigureQA: An Annotated Figure Dataset for Visual Reasoning
    48
    Exploring Models and Data for Image Question Answering
    423
    Show, Ask, Attend, and Answer: A Strong Baseline For Visual Question Answering
    92
    Towards VQA Models That Can Read
    51
    Stacked Attention Networks for Image Question Answering
    1028
    VQA: Visual Question Answering
    1776
    ICDAR 2019 Competition on Scene Text Visual Question Answering
    10
    Neural Module Networks
    474
    FigureSeer: Parsing Result-Figures in Research Papers
    48