Contrastive training of a multimodal encoder for medical visual question answering

Contrastive training of a multimodal encoder for medical visual question answering

Models for Visual Question Answering (VQA) on medical images aim to answer diagnostically relevant natural language questions with basis on visual contents. In this article, we propose a novel approach to address this problem, which combines a strong image encoder based on EfficientNetV2 with a mult...

Full description

Bibliographic Details
Main Authors: João Daniel Silva, Bruno Martins, João Magalhães
Format: Article
Language:English
Published: Elsevier 2023-05-01
Series:Intelligent Systems with Applications
Subjects:
Medical visual question answering
Transformer encoders
Vision and language
Computer vision
Natural language processing
Online Access:http://www.sciencedirect.com/science/article/pii/S2667305323000467

Internet

http://www.sciencedirect.com/science/article/pii/S2667305323000467

Similar Items