@inbook{4e956adc6f58470da5ec074205ef9f52,
title = "MUST-VQA: MUltilingual Scene-Text VQA",
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.",
keywords = "Multilingual models, Power of language models, Scene text, Translation robustness, Visual question answering, Zero-shot transfer",
author = "Emanuele Vivoli and Biten, {Ali Furkan} and Andres Mafla and Dimosthenis Karatzas and Lluis Gomez",
note = "Publisher Copyright: {\textcopyright} 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.",
year = "2023",
month = feb,
doi = "10.1007/978-3-031-25069-9_23",
language = "English",
isbn = "978-3-031-25068-2",
volume = "13804",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
pages = "345--358",
editor = "Leonid Karlinsky and Tomer Michaeli and Ko Nishino",
booktitle = "Computer Vision – ECCV 2022 Workshops, Proceedings",
}