DVQA: Understanding Data Visualizations via Question Answering

Bar charts are an effective way to convey numeric information, but today's algorithms cannot parse them. Existing methods fail when faced with even minor variations in appearance. Here, we present DVQA, a dataset that tests many aspects of bar chart understanding in a question answering framewo...

Full description

Saved in:
Bibliographic Details
Published in2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition pp. 5648 - 5656
Main Authors Kafle, Kushal, Price, Brian, Cohen, Scott, Kanan, Christopher
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2018
Subjects
Bars
Cognition
Data mining
Data visualization
Image color analysis
Knowledge discovery
Visualization
Online AccessGet full text

Cover

More Information
Summary:Bar charts are an effective way to convey numeric information, but today's algorithms cannot parse them. Existing methods fail when faced with even minor variations in appearance. Here, we present DVQA, a dataset that tests many aspects of bar chart understanding in a question answering framework. Unlike visual question answering (VQA), DVQA requires processing words and answers that are unique to a particular bar chart. State-of-the-art VQA algorithms perform poorly on DVQA, and we propose two strong baselines that perform considerably better. Our work will enable algorithms to automatically extract numeric and semantic information from vast quantities of bar charts found in scientific publications, Internet articles, business reports, and many other areas.
ISSN:1063-6919
DOI:10.1109/CVPR.2018.00592