@InProceedings{JordyVanLandeghem2023,
author="Jordy Van Landeghem
and Ruben Tito
and Lukasz Borchmann
and Michal Pietruszka
and Pawel Joziak
and Rafal Powalski
and Dawid Jurkiewicz
and Mickael Coustaty
and Bertrand Anckaert
and Ernest Valveny
and Matthew Blaschko
and Sien Moens
and Tomasz Stanislawek",
title="Document Understanding Dataset and Evaluation (DUDE)",
booktitle="20th IEEE International Conference on Computer Vision",
year="2023",
pages="19528--19540",
abstract="We call on the Document AI (DocAI) community to re-evaluate current methodologies and embrace the challenge of creating more practically-oriented benchmarks. Document Understanding Dataset and Evaluation (DUDE) seeks to remediate the halted research progress in understanding visually-rich documents (VRDs). We present a new dataset with novelties related to types of questions, answers, and document layouts based on multi-industry, multi-domain, and multi-page VRDs of various origins and dates. Moreover, we are pushing the boundaries of current methods by creating multi-task and multi-domain evaluation setups that more accurately simulate real-world situations where powerful generalization and adaptation under low-resource settings are desired. DUDE aims to set a new standard as a more practical, long-standing benchmark for the community, and we hope that it will lead to future extensions and contributions that address real-world challenges. Finally, our work illustrates the importance of finding more efficient ways to model language, images, and layout in DocAI.",
optnote="DAG",
optnote="exported from refbase (http://refbase.cvc.uab.es/show.php?record=3948), last updated on Fri, 26 Jan 2024 09:23:47 +0100",
opturl="https://openaccess.thecvf.com/content/ICCV2023/html/Van_Landeghem_Document_Understanding_Dataset_and_Evaluation_DUDE_ICCV_2023_paper.html",
file=":http://refbase.cvc.uab.es/files/LTB2023.pdf:PDF"
}