WoundcareVQA: A multilingual visual question answering benchmark dataset for wound care
We construct and explore the tasks of multimodal, multilingual VQA. We hope the work here can inspire further research in wound care metadata classification, VQA response generation, and open response automatic evaluation.
Authors
- Fei Xia (ORCID: https://orcid.org/0000-0001-6015-6064)
- Meliha Yetişgen (ORCID: https://orcid.org/0000-0001-9919-9811)
- Asma Ben Abacha (ORCID: https://orcid.org/0000-0001-6312-9387)
- M. Kennedy Hall (ORCID: https://orcid.org/0000-0002-0803-1552)
- Wen-wai Yim (ORCID: https://orcid.org/0000-0001-9011-0817)
- Jiaying Xu (ORCID: https://orcid.org/0009-0003-4737-9628)
- Zixuan Yu (ORCID: https://orcid.org/0000-0002-1235-7299)
- A. V. Subbarao
- Chia-Yu Chen
- Robert Doerning
Institutions
- Microsoft (United States) (US)
- University of Washington (US)
- Microsoft Research (United Kingdom) (GB)
- Seattle University (US)
Publication Details
- Journal
- Journal of Biomedical Informatics
- Published
- 2025-08-29
- DOI
- https://doi.org/10.1016/j.jbi.2025.104888
- Primary Topic
- Multimodal Machine Learning Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.00