@InProceedings{MohammedAlRawi2019,
author="Mohammed Al Rawi
and Ernest Valveny
and Dimosthenis Karatzas",
title="Can One Deep Learning Model Learn Script-Independent Multilingual Word-Spotting?",
booktitle="15th International Conference on Document Analysis and Recognition",
year="2019",
pages="260--267",
abstract="Word spotting has gained increased attention lately as it can be used to extract textual information from handwritten documents and scene-text images. Current word spotting approaches are designed to work on a single language and/or script. Building intelligent models that learn script-independent multilingual word-spotting is challenging due to the large variability of multilingual alphabets and symbols. We used ResNet-152 and the Pyramidal Histogram of Characters (PHOC) embedding to build a one-model script-independent multilingual word-spotting and we tested it on Latin, Arabic, and Bangla (Indian) languages. The one-model we propose performs on par with the multi-model language-specific word-spotting system, and thus, reduces the number of models needed for each script and/or language.",
optnote="DAG; 600.129; 600.121",
optnote="exported from refbase (http://refbase.cvc.uab.es/show.php?record=3337), last updated on Tue, 25 Jan 2022 16:37:10 +0100",
doi="10.1109/ICDAR.2019.00050",
opturl="https://ieeexplore.ieee.org/abstract/document/8978043",
file=":http://refbase.cvc.uab.es/files/RVK2019.pdf:PDF"
}