AI Paper Atlas

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

Inconsistency-aware Multimodal Schrodinger Bridge for Deepfake Localization

Jiayu Xiong, Jing Wang, Qi Zhang, Wanlong Wang, Jun Xue

CVPR 2026 · Vision-language and multimodal › Cross-modal learning · approach: Audio-visual source localization

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 the witness bridge (WSB) for cross-modal filtering and budget allocation (ablation)IaMSB · LAV-DFAP@0.95: 28.16 -> 55.92Improved
add the refinement bridge (RSB) (ablation)IaMSB · LAV-DFAP@0.95: 23.39 -> 55.92Improved
add the coarse bridge (CSB) (ablation)IaMSB · LAV-DFAP@0.5: 83.25 -> 99.33Improved
raise coarse steps from 1 to 2 (ablation)IaMSB CSB · LAV-DFAP@0.95: 52.87 -> 55.92Improved
raise coarse steps from 2 to 3 (ablation)IaMSB CSB · LAV-DFAP@0.95: 55.92 -> 55.98No clear effect
use witness top-k of 16 rather than 2 (ablation)IaMSB WSB · LAV-DFAP@0.95: 50.98 -> 55.92Improved
widen witness top-k from 16 to 64 (ablation)IaMSB WSB · LAV-DFAP@0.95: 55.92 -> 53.97Hurt
IaMSB versus RegQAV on strict IoUIaMSB · AV-Deepfake1MAP@0.95: 12.57 -> 23.01Improved
IaMSB versus MMMS-BA on recall at AR@20IaMSB · LAV-DFAR@20: 95.93 -> 95.41Hurt
IaMSB versus UMMAFormer on visual-only forgery strict IoUIaMSB · TVILAP@0.95: 62.43 -> 65.62Improved

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