A new benchmark and a fine-tuning plus random-forest aggregation pipeline let eleven of twelve image-level deepfake detectors beat the best video-level detector on AI-generated video.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
FakeI2V-Bench: Benchmarking the Applicability of Image-level Deepfake Detectors for Deepfake Video Detection
A new benchmark and a fine-tuning plus random-forest aggregation pipeline let eleven of twelve image-level deepfake detectors beat the best video-level detector on AI-generated video.