@InProceedings{AliFurkanBiten2022,
author="Ali Furkan Biten
and Ruben Tito
and Lluis Gomez
and Ernest Valveny
and Dimosthenis Karatzas",
title="OCR-IDL: OCR Annotations for Industry Document Library Dataset",
booktitle="ECCV Workshop on Text in Everything",
year="2022",
abstract="Pretraining has proven successful in Document Intelligence tasks where deluge of documents are used to pretrain the models only later to be finetuned on downstream tasks. One of the problems of the pretraining approaches is the inconsistent usage of pretraining data with different OCR engines leading to incomparable results between models. In other words, it is not obvious whether the performance gain is coming from diverse usage of amount of data and distinct OCR engines or from the proposed models. To remedy the problem, we make public the OCR annotations for IDL documents using commercial OCR engine given their superior performance over open source OCR models. The contributed dataset (OCR-IDL) has an estimated monetary value over 20K US\$. It is our hope that OCR-IDL can be a starting point for future works on Document Intelligence. All of our data and its collection process with the annotations can be found in this https URL.",
optnote="DAG; no proj",
optnote="exported from refbase (http://refbase.cvc.uab.es/show.php?record=3817), last updated on Fri, 26 Jan 2024 09:58:57 +0100",
opturl="https://sites.google.com/view/tie-eccv2022/accepted-papers",
file=":http://refbase.cvc.uab.es/files/BTG2022.pdf:PDF"
}