PT Unknown
AU Emanuele Vivoli
   Ali Furkan Biten
   Andres Mafla
   Dimosthenis Karatzas
   Lluis Gomez
TI MUST-VQA: MUltilingual Scene-text VQA
BT Proceedings European Conference on Computer Vision Workshops
PY 2022
BP 345–358
VL 13804
DI 10.1007/978-3-031-25069-9_23
DE Visual question answering; Scene text; Translation robustness; Multilingual models; Zero-shot transfer; Power of language models
AB 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.
ER