ViConsFormer: Constituting Meaningful Phrases of Scene Texts using Transformer-based Method in Vietnamese Text-based Visual Question Answering
This work addresses the problem of improving text-based VQA for Vietnamese language users, representing an incremental advancement in a domain-specific area.
The paper tackles the challenge of exploiting meaning from scene texts in Vietnamese text-based visual question answering by introducing a novel method based on linguistic definitions of meaning, achieving state-of-the-art results on two large-scale Vietnamese datasets.
Text-based VQA is a challenging task that requires machines to use scene texts in given images to yield the most appropriate answer for the given question. The main challenge of text-based VQA is exploiting the meaning and information from scene texts. Recent studies tackled this challenge by considering the spatial information of scene texts in images via embedding 2D coordinates of their bounding boxes. In this study, we follow the definition of meaning from linguistics to introduce a novel method that effectively exploits the information from scene texts written in Vietnamese. Experimental results show that our proposed method obtains state-of-the-art results on two large-scale Vietnamese Text-based VQA datasets. The implementation can be found at this link.