{"slug": "inconsistency-aware-multimodal-schr-odinger-bridge-for-deepfake-localization", "title": "Inconsistency-aware Multimodal Schr\\\"odinger Bridge for Deepfake Localization", "summary": "Researchers have developed IaMSB, an inconsistency-aware multimodal Schrödinger Bridge framework that improves deepfake localization by jointly estimating cross-modal consistency and performing interval-level temporal evidence detection. The method addresses the challenge of symmetric fusion under single-sided or asynchronous forgeries, which propagates cross-modal noise and degrades precision. Across benchmarks, IaMSB raises strict-IoU boundary precision by 3% to 10%, particularly improving high-precision localization for single-sided forgeries.", "body_md": "arXiv:2605.23113v1 Announce Type: new\nAbstract: Audio-visual deepfake localization demands interval-level outputs that serve as temporal evidence. Despite recent progress, symmetric fusion under single-sided or asynchronous forgeries propagates cross-modal noise, degrading high-precision localization. We present IaMSB, an inconsistency-aware multimodal Schr\\\"odinger Bridge (SB) that jointly estimates cross-modal consistency and performs interval-level localization. Unlike diffusion models, SB minimizes path-distribution discrepancy and yields consistency scores without explicit noise injection or denoising. With the Schr\\\"odinger Bridge (SB), IaMSB unifies consistency estimation, cross-modal information selection, and bridge-step scheduling in one framework. Specifically, a lightweight coarse bridge first proposes candidate intervals and estimates cross-modal consistency; these statistics select cross-modal witness signals and allocate bridge steps asymmetrically across modalities. A refinement bridge then performs step-tuned fusion and outputs refined, time-aligned intervals. IaMSB anticipates single-sided and asynchronous forgeries and, using bottlenecked cross-modal interaction with step allocation, suppresses noise transfer, avoids unnecessary iterations. Across benchmarks, IaMSB stabilizes strict-IoU boundary precision, raising AP@0.95 by 3%~10%, and yields improved high-precision localization, particularly for single-sided forgeries.", "url": "https://wpnews.pro/news/inconsistency-aware-multimodal-schr-odinger-bridge-for-deepfake-localization", "canonical_source": "https://arxiv.org/abs/2605.23113", "published_at": "2026-05-25 04:00:00+00:00", "updated_at": "2026-05-25 15:20:46.039530+00:00", "lang": "en", "topics": ["computer-vision", "machine-learning", "artificial-intelligence", "neural-networks", "ai-research"], "entities": ["IaMSB", "Schrödinger Bridge"], "alternates": {"html": "https://wpnews.pro/news/inconsistency-aware-multimodal-schr-odinger-bridge-for-deepfake-localization", "markdown": "https://wpnews.pro/news/inconsistency-aware-multimodal-schr-odinger-bridge-for-deepfake-localization.md", "text": "https://wpnews.pro/news/inconsistency-aware-multimodal-schr-odinger-bridge-for-deepfake-localization.txt", "jsonld": "https://wpnews.pro/news/inconsistency-aware-multimodal-schr-odinger-bridge-for-deepfake-localization.jsonld"}}