AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Detecting and Grounding Multi-Modal Media Manipulation and Beyond

Rui Shao, Tianxing Wu, Jianlong Wu, Liqiang Nie, Ziwei Liu

TPAMI 2024 · Vision-language and multimodal › Cross-modal learning · approach: Multimodal sentiment analysis · 69 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 global manipulation-aware contrastive loss (MAC-G) (ablation)HAMMER · DGM4binary AUC: 92.77 -> 93.19Improved
add multi-label classification loss (ablation)HAMMER · DGM4multi-label mAP: 27.22 -> 86.22Improved
add image manipulation grounding loss (ablation)HAMMER · DGM4image grounding IoUmean: 4.69 -> 76.45Improved
add text manipulation grounding loss (ablation)HAMMER · DGM4text grounding F1: 22.53 -> 71.35Improved
add grounding and contrastive losses to binary-classification-only training (ablation)HAMMER · DGM4binary ACC: 83.81 -> 86.39Improved
add local-view manipulation-aware contrastive loss (MAC-L) (ablation)HAMMER · DGM4text grounding F1: 71.35 -> 72.59Improved
use manipulation-aware contrastive learning instead of normal contrastive learning (ablation)HAMMER · DGM4binary AUC: 92.95 -> 93.19Improved
add momentum models (ablation)HAMMER · DGM4binary AUC: 92.96 -> 93.19Improved
add momentum models (ablation)HAMMER · DGM4text grounding precision: 76.13 -> 75.01Hurt
add text modality to image-only model (ablation)HAMMER · DGM4 text-forgery splittext grounding F1: 37.77 -> 72.08Improved
add text modality to image-only model (ablation)HAMMER · DGM4 image-forgery splitbinary AUC: 93.96 -> 94.40Improved
replace [CLS] token with local patch attentional aggregation (LPAA) for bbox grounding (ablation)HAMMER · DGM4image groundingImproved

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