IaMSB applies a Schrödinger Bridge in two stages to estimate cross-modal consistency and localize deepfake intervals, reporting 3-10% gains in AP@0.95 especially on single-sided forgeries.
Dimodif: Discourse modality-information differentiation for audio- visual deepfake detection and localization
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
AVPF generates self-created audio-visual pseudo-fakes from real samples to train deepfake detectors that generalize better, with reported average gains up to 7.4%.
citing papers explorer
-
Inconsistency-aware Multimodal Schr\"odinger Bridge for Deepfake Localization
IaMSB applies a Schrödinger Bridge in two stages to estimate cross-modal consistency and localize deepfake intervals, reporting 3-10% gains in AP@0.95 especially on single-sided forgeries.
-
Generalizing Video DeepFake Detection by Self-generated Audio-Visual Pseudo-Fakes
AVPF generates self-created audio-visual pseudo-fakes from real samples to train deepfake detectors that generalize better, with reported average gains up to 7.4%.