Overview

Document Visual Question Answering (DocVQA) seeks to inspire a “purpose-driven” point of view in Document Analysis and Recognition research, where the document content is extracted and used to respond to high-level tasks defined by the human consumers of this information. To this end we organize a series of challenges and release datasets to enable machines "understand" document images and thereby answer questions asked on them.

Citation

If you use the DocVQA dataset ( the one used for task 1 of the first edition of the challenge) please cite

@misc{docvqa,
    title={DocVQA: A Dataset for VQA on Document Images},
    author={Minesh Mathew and Dimosthenis Karatzas and R. Manmatha and C. V. Jawahar},
    year={2020},
    eprint={2007.00398},
    archivePrefix={arXiv},
    primaryClass={cs.CV}
}

We presented a short technical report on the 2020 challenge at the IAPR Workshop on Document Analysis Systems (DAS) 2020. The report can be cited using the below

@misc{docvqa_challenge_report,
    title={Document Visual Question Answering Challenge 2020},
    author={Minesh Mathew and Ruben Tito and Dimosthenis Karatzas and R. Manmatha and
    C. V. Jawahar},
    year={2020},
    eprint={2008.08899},
    archivePrefix={arXiv},
    primaryClass={cs.CV}
}

News

  • [August 2020] DocVQA 2021 Challenge Announced. The challenge will be hosted as part of ICDAR 2021
  • [June 2020] Presentation of competition summary and overview of DocVQA 2020 challenge and announcement of prizes at the CVPR 2020 workshop
  • [May 2020] - DocVQA 2020 Challenge ends and results are published
  • [April 2020] - Release of final version of Datasets for Task 1 and Task 2 of the 2020 Challenge.
  • [ March 2020] - Challenge begins with intial data release.

Acknolwedgement

  • Annotation efforts towards dataset for the Task1 and prizes for the 2020 challenge are sponsored by Amazon AWS.
  • We would like to thank Kerala Women in Nano Startups (KWINS) team of Kerala Startup Mission for helping us connect with an amazing group of women freelancers who helped us with the annotation for Task1 dataset of the 2020 challenge.

People

 

IMG

Minesh Mathew
IIIT Hyderabad
 

IMG

Rubèn Pérez Tito
CVC, University of Barcelona

IMG

Dimosthenis Karatzas
CVC, University of Barcelona

IMG

R. Manmatha
Amazon
 

IMG

C.V. Jawahar
IIIT Hyderabad
 

Contact

Please feel free to contact us for any queries, suggestions or feedback.
Email ID: minesh[dot]mathew@research[dot]iiit[dot]ac[dot]in


IMG
IMG
IMG