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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Fake news often involves multimedia information such as text and image tomislead readers, proliferating and expanding its influence. Most existing fakenews detection methods apply the co-attention mechanism to fuse multimodalfeatures while ignoring the consistency of image and text in co-attention. Inthis paper, we propose multimodal matching-aware co-attention networks withmutual knowledge distillation for improving fake news detection. Specifically,we design an image-text matching-aware co-attention mechanism which capturesthe alignment of image and text for better multimodal fusion. The image-textmatching representation can be obtained via a vision-language pre-trainedmodel. Additionally, based on the designed image-text matching-awareco-attention mechanism, we propose to build two co-attention networksrespectively centered on text and image for mutual knowledge distillation toimprove fake news detection. Extensive experiments on three benchmark datasetsdemonstrate that our proposed model achieves state-of-the-art performance onmultimodal fake news detection.

Multimodal Matching-aware Co-attention Networks with Mutual Knowledge Distillation for Fake News Detection