MUST-VQA: MUltilingual Scene-text VQA
This addresses the problem of language diversity in STVQA for applications like multilingual image understanding, but it is incremental as it adapts existing multilingual models to a specific task.
The paper tackles multilingual scene-text visual question answering (STVQA) by introducing MUST-VQA, a framework that handles questions in different languages in a zero-shot manner, and shows models perform comparably in zero-shot settings.
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.