English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Medical visual question answering (VQA) is a challenging task that requiresanswering clinical questions of a given medical image, by taking consider ofboth visual and language information. However, due to the small scale oftraining data for medical VQA, pre-training fine-tuning paradigms have been acommonly used solution to improve model generalization performance. In thispaper, we present a novel self-supervised approach that learns unimodal andmultimodal feature representations of input images and text using medical imagecaption datasets, by leveraging both unimodal and multimodal contrastivelosses, along with masked language modeling and image text matching aspretraining objectives. The pre-trained model is then transferred to downstreammedical VQA tasks. The proposed approach achieves state-of-the-art (SOTA)performance on three publicly available medical VQA datasets with significantaccuracy improvements of 2.2%, 14.7%, and 1.7% respectively. Besides, weconduct a comprehensive analysis to validate the effectiveness of differentcomponents of the approach and study different pre-training settings. Our codesand models are available at https://github.com/pengfeiliHEU/MUMC.

Masked Vision and Language Pre-training with Unimodal and Multimodal Contrastive Losses for Medical Visual Question Answering