@InProceedings{RubenTito2021,
author="Ruben Tito
and Dimosthenis Karatzas
and Ernest Valveny",
title="Document Collection Visual Question Answering",
booktitle="16th International Conference on Document Analysis and Recognition",
year="2021",
volume="12822",
pages="778--792",
optkeywords="Document collection",
optkeywords="Visual Question Answering",
abstract="Current tasks and methods in Document Understanding aims to process documents as single elements. However, documents are usually organized in collections (historical records, purchase invoices), that provide context useful for their interpretation. To address this problem, we introduce Document Collection Visual Question Answering (DocCVQA) a new dataset and related task, where questions are posed over a whole collection of document images and the goal is not only to provide the answer to the given question, but also to retrieve the set of documents that contain the information needed to infer the answer. Along with the dataset we propose a new evaluation metric and baselines which provide further insights to the new dataset and task.",
optnote="DAG; 600.121",
optnote="exported from refbase (http://refbase.cvc.uab.es/show.php?record=3622), last updated on Fri, 07 Jan 2022 14:01:07 +0100",
opturl="https://link.springer.com/chapter/10.1007/978-3-030-86331-9_50",
file=":http://refbase.cvc.uab.es/files/TKV2021.pdf:PDF"
}