CMTA detects AI-generated videos by capturing unnatural temporal stability in visual-textual semantic alignment via joint embeddings and multi-grained temporal modeling, outperforming prior methods in cross-generator tests.
Beyond deepfake images: Detecting ai-generated videos
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
-
CMTA: Leveraging Cross-Modal Temporal Artifacts for Generalizable AI-Generated Video Detection
CMTA detects AI-generated videos by capturing unnatural temporal stability in visual-textual semantic alignment via joint embeddings and multi-grained temporal modeling, outperforming prior methods in cross-generator tests.