ReConFuse detects AI-generated videos by fusing WF-VAE reconstruction error patterns with multi-frame semantic features via a Mamba-based temporal model.
arXiv preprint arXiv:2402.13126 (2024) 14 X
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
ReConFuse: Reconstruction-Error Guided Semantic Fusion for AI-Generated Video Detection
ReConFuse detects AI-generated videos by fusing WF-VAE reconstruction error patterns with multi-frame semantic features via a Mamba-based temporal model.