BOK-VQA: Bilingual outside Knowledge-Based Visual Question Answering via Graph Representation Pretraining

Min Jun Kim, Seung Woo Song, You Han Lee, Haneol Jang, Kyung Tae Lim

Research output: Contribution to journalConference articlepeer-review

4 Scopus citations

Abstract

The current research direction in generative models, such as the recently developed GPT4, aims to find relevant knowledge information for multimodal and multilingual inputs to provide answers. Under these research circumstances, the demand for multilingual evaluation of visual question answering (VQA) tasks, a representative task of multimodal systems, has increased. Accordingly, we propose a bilingual outside-knowledge VQA (BOK-VQA) dataset in this study that can be extended to multilingualism. The proposed data include 17K images, 17K question-answer pairs for both Korean and English and 280K instances of knowledge information related to question-answer content. We also present a framework that can effectively inject knowledge information into a VQA system by pretraining the knowledge information of BOK-VQA data in the form of graph embeddings. Finally, through in-depth analysis, we demonstrated the actual effect of the knowledge information contained in the constructed training data on VQA.

Original languageEnglish
Pages (from-to)18381-18389
Number of pages9
JournalProceedings of the AAAI Conference on Artificial Intelligence
Volume38
Issue number16
DOIs
StatePublished - 25 Mar 2024
Event38th AAAI Conference on Artificial Intelligence, AAAI 2024 - Vancouver, Canada
Duration: 20 Feb 202427 Feb 2024

Fingerprint

Dive into the research topics of 'BOK-VQA: Bilingual outside Knowledge-Based Visual Question Answering via Graph Representation Pretraining'. Together they form a unique fingerprint.

Cite this