@inbook{20a1b1477c304b1bb48078a3d045a29b,
title = "ICDAR 2021 Competition on Document Visual Question Answering",
abstract = "In this report we present results of the ICDAR 2021 edition of the Document Visual Question Challenges. This edition complements the previous tasks on Single Document VQA and Document Collection VQA with a newly introduced on Infographics VQA. Infographics VQA is based on a new dataset of more than 5, 000 infographics images and 30, 000 question-answer pairs. The winner methods have scored 0.6120 ANLS in Infographics VQA task, 0.7743 ANLSL in Document Collection VQA task and 0.8705 ANLS in Single Document VQA. We present a summary of the datasets used for each task, description of each of the submitted methods and the results and analysis of their performance. A summary of the progress made on Single Document VQA since the first edition of the DocVQA 2020 challenge is also presented.",
keywords = "Document understanding, Infographics, Visual Question Answering",
author = "Rub{\`e}n Tito and Minesh Mathew and Jawahar, {C. V.} and Ernest Valveny and Dimosthenis Karatzas",
note = "Funding Information: Acknowledgments. This work was supported by an AWS Machine Learning Research Award, the CERCA Programme/Generalitat de Catalunya, and UAB PhD scholarship No B18P0070. We thank especially Dr. R. Manmatha for many useful inputs and discussions. Publisher Copyright: {\textcopyright} 2021, Springer Nature Switzerland AG.",
year = "2021",
doi = "10.1007/978-3-030-86337-1_42",
language = "English",
isbn = "9783030863364",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Science and Business Media Deutschland GmbH",
pages = "635--649",
editor = "Josep Llad{\'o}s and Daniel Lopresti and Seiichi Uchida",
booktitle = "Document Analysis and Recognition - ICDAR 2021 - 16th International Conference, Proceedings",
}