ML Anthology

MUST-VQA: MUltilingual Scene-Text VQA

Emanuele Vivoli, Ali Furkan Biten, Andrés Mafla, Dimosthenis Karatzas, Lluís Gómez
ECCVW 2022 pp. 345-358
doi:10.1007/978-3-031-25069-9_23 /eccvw/2022/vivoli2022eccvw-mustvqa/

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.

PDF ECCVW Semantic Scholar

Cite

Text

Vivoli et al. "MUST-VQA: MUltilingual Scene-Text VQA." European Conference on Computer Vision Workshops, 2022. doi:10.1007/978-3-031-25069-9_23

Markdown

[Vivoli et al. "MUST-VQA: MUltilingual Scene-Text VQA." European Conference on Computer Vision Workshops, 2022.](https://mlanthology.org/eccvw/2022/vivoli2022eccvw-mustvqa/) doi:10.1007/978-3-031-25069-9_23

BibTeX

@inproceedings{vivoli2022eccvw-mustvqa,
  title     = {{MUST-VQA: MUltilingual Scene-Text VQA}},
  author    = {Vivoli, Emanuele and Biten, Ali Furkan and Mafla, Andrés and Karatzas, Dimosthenis and Gómez, Lluís},
  booktitle = {European Conference on Computer Vision Workshops},
  year      = {2022},
  pages     = {345-358},
  doi       = {10.1007/978-3-031-25069-9_23},
  url       = {https://mlanthology.org/eccvw/2022/vivoli2022eccvw-mustvqa/}
}