Parallel multi-head attention and term-weighted question embedding for medical visual question answering

The goal of medical visual question answering (Med-VQA) is to correctly answer a clinical question posed by a medical image. Medical images are fundamentally different from images in the general domain. As a result, using general domain Visual Question Answering (VQA) models to the medical domain is...

Descripción completa

Detalles Bibliográficos
Autores principales: Manmadhan, Sruthy, Kovoor, Binsu C
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Springer US 2023
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10006552/
https://www.ncbi.nlm.nih.gov/pubmed/37362667
http://dx.doi.org/10.1007/s11042-023-14981-2

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10006552/
https://www.ncbi.nlm.nih.gov/pubmed/37362667
http://dx.doi.org/10.1007/s11042-023-14981-2

Ejemplares similares