@InProceedings{EmanueleVivoli2022,
author="Emanuele Vivoli
and Ali Furkan Biten
and Andres Mafla
and Dimosthenis Karatzas
and Lluis Gomez",
title="MUST-VQA: MUltilingual Scene-text VQA",
booktitle="Proceedings European Conference on Computer Vision Workshops",
year="2022",
volume="13804",
pages="345--358",
optkeywords="Visual question answering",
optkeywords="Scene text",
optkeywords="Translation robustness",
optkeywords="Multilingual models",
optkeywords="Zero-shot transfer",
optkeywords="Power of language models",
abstract="In this paper, we present a framework for Multilingual Scene Text Visual Question Answering that deals with new languages in a zero-shot fashion. Specifically, we consider the task of Scene Text Visual Question Answering (STVQA) in which the question can be asked in different languages and it is not necessarily aligned to the scene text language. Thus, we first introduce a natural step towards a more generalized version of STVQA: MUST-VQA. Accounting for this, we discuss two evaluation scenarios in the constrained setting, namely IID and zero-shot and we demonstrate that the models can perform on a par on a zero-shot setting. We further provide extensive experimentation and show the effectiveness of adapting multilingual language models into STVQA tasks.",
optnote="DAG; 302.105; 600.155; 611.002",
optnote="exported from refbase (http://refbase.cvc.uab.es/show.php?record=3770), last updated on Wed, 12 Jul 2023 10:44:23 +0200",
doi="10.1007/978-3-031-25069-9_23",
opturl="https://link.springer.com/chapter/10.1007/978-3-031-25069-9_23",
file=":http://refbase.cvc.uab.es/files/VBM2022.pdf:PDF"
}