A Diagram is Worth a Dozen Images

@inproceedings{Kembhavi2016ADI,
  title={A Diagram is Worth a Dozen Images},
  author={Aniruddha Kembhavi and M. Salvato and Eric Kolve and Minjoon Seo and Hannaneh Hajishirzi and Ali Farhadi},
  booktitle={ECCV},
  year={2016}
}
  • Aniruddha Kembhavi, M. Salvato, +3 authors Ali Farhadi
  • Published in ECCV 2016
  • Computer Science
  • Diagrams are common tools for representing complex concepts, relationships and events, often when it would be difficult to portray the same information with natural images. [...] Key Method We define syntactic parsing of diagrams as learning to infer DPGs for diagrams and study semantic interpretation and reasoning of diagrams in the context of diagram question answering. We devise an LSTM-based method for syntactic parsing of diagrams and introduce a DPG-based attention model for diagram question answering.Expand Abstract
    58 Citations
    Dynamic Graph Generation Network: Generating Relational Knowledge from Diagrams
    • 8
    • Highly Influenced
    • PDF
    Look, Read and Enrich - Learning from Scientific Figures and their Captions
    • 2
    • PDF
    Enhancing the AI2 Diagrams Dataset Using Rhetorical Structure Theory
    • 4
    • Highly Influenced
    • PDF
    MoQA - A Multi-modal Question Answering Architecture
    Visual question answering: A survey of methods and datasets
    • 154
    • PDF
    Data Interpretation over Plots
    • 1
    Structured Set Matching Networks for One-Shot Part Labeling
    • 8
    • PDF
    Answering Questions about Data Visualizations using Efficient Bimodal Fusion
    • 10
    • PDF
    Computational perception for multi-modal document understanding

    References

    SHOWING 1-10 OF 61 REFERENCES
    Diagram Understanding in Geometry Questions
    • 60
    • PDF
    Bringing Semantics into Focus Using Visual Abstraction
    • 156
    • PDF
    Yin and Yang: Balancing and Answering Binary Visual Questions
    • 169
    • PDF
    Learning Common Sense through Visual Abstraction
    • 66
    • PDF
    Extraction,layout analysis and classification of diagrams in PDF documents
    • 66
    • PDF
    VQA: Visual Question Answering
    • 1,905
    • PDF
    Visual7W: Grounded Question Answering in Images
    • 431
    • PDF