SAGA is a multi-granular source attribution system for generative AI videos that identifies the exact generator with state-of-the-art accuracy using only 0.5% labeled data per class.
Getting vit in shape: Scaling laws for compute- optimal model design.Advances in Neural Information Process- ing Systems, 36, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SAGA: Source Attribution of Generative AI Videos
SAGA is a multi-granular source attribution system for generative AI videos that identifies the exact generator with state-of-the-art accuracy using only 0.5% labeled data per class.