AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

Enhancing Multimodal Misinformation Detection by Replaying the Whole Story from Image Modality Perspective

Bing Wang, Ximing Li, Yanjun Wang, Changchun Li, Lin Yuanbo Wu, Buyu Wang, Shengsheng Wang

AAAI 2026 · Image generation › Text-to-image diffusion · approach: Text-driven synthesis and semantic guidance · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add generated augmented image sequence (RETSIMD) to BMRR&B + BMR · Twitteraccuracy: 66.71 -> 69.57Improved
add RETSIMD to GAMEDR&B + GAMED · Weiboaccuracy: 90.24 -> 92.08Improved
add RETSIMD to ResNet + BERTResNet + BERT · GossipCopaccuracy: 87.17 -> 88.13Improved
add augmented images (ablation)RETSIMD (BMR) · Twitteraccuracy: 66.71 -> 69.57Improved
add augmented images (ablation)RETSIMD (BMR) · GossipCopaccuracy: 87.32 -> 88.42Improved
add mutual information regularizers to generator (ablation)RETSIMD (BMR) · Twitteraccuracy: 67.18 -> 69.57Improved
add mutual information regularizers to generator (ablation)RETSIMD (BMR) · Weiboaccuracy: 91.06 -> 92.01Improved
add graph fusion over images instead of concatenation (ablation)RETSIMD (BMR) · Twitteraccuracy: 67.86 -> 69.57Improved
add graph fusion over images instead of concatenation (ablation)RETSIMD (BMR) · GossipCopaccuracy: 87.67 -> 88.42Improved
add RETSIMD to improve image information gainResNet + BERT · GossipCopG(y, xv): .0349 -> .0301Mixed
remove text modality (text-only vs full MMD models) (ablation)SOTA MMD methods · GossipCop, Weibo, Twitteraccuracy gapNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy