Answering Questions about Data Visualizations using Efficient Bimodal Fusion

  title={Answering Questions about Data Visualizations using Efficient Bimodal Fusion},
  author={Kushal Kafle and Robik Shrestha and B. Price and S. Cohen and Christopher Kanan},
  journal={2020 IEEE Winter Conference on Applications of Computer Vision (WACV)},
  • Kushal Kafle, Robik Shrestha, +2 authors Christopher Kanan
  • Published 2020
  • Computer Science
  • 2020 IEEE Winter Conference on Applications of Computer Vision (WACV)
  • Chart question answering (CQA) is a newly proposed visual question answering (VQA) task where an algorithm must answer questions about data visualizations, e.g. bar charts, pie charts, and line graphs. [...] Key Method PReFIL first learns bimodal embeddings by fusing question and image features and then intelligently aggregates these learned embeddings to answer the given question. Despite its simplicity, PReFIL greatly surpasses state-of-the art systems and human baselines on both the FigureQA and DVQA…Expand Abstract
    An Affinity-Driven Relation Network for Figure Question Answering
    Answering Questions about Charts and Generating Visual Explanations
    • 2
    • PDF
    Hierarchical Deep Multi-modal Network for Medical Visual Question Answering
    Advancing Multi-Modal Deep Learning: Towards Language-Grounded Visual Understanding
    DocVQA: A Dataset for VQA on Document Images
    • 1
    • PDF
    Emerging Trends of Multimodal Research in Vision and Language
    Visual Question Answering


    Publications referenced by this paper.
    Answer Them All! Toward Universal Visual Question Answering Models
    • 25
    • PDF
    DVQA: Understanding Data Visualizations via Question Answering
    • 39
    • PDF
    Stacked Attention Networks for Image Question Answering
    • 1,050
    • Highly Influential
    • PDF
    A Question-Answering framework for plots using Deep learning
    • 3
    Visual question answering: Datasets, algorithms, and future challenges
    • 99
    • PDF
    Exploring Models and Data for Image Question Answering
    • 428
    • PDF
    Deep Compositional Question Answering with Neural Module Networks
    • 123
    • PDF
    VQA: Visual Question Answering
    • 1,839
    • PDF