AEGIS is a large-scale benchmark for detecting AI-generated videos, with a hard test set of Sora and KLing clips that current vision-language models detect at near-chance accuracy.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
AEGIS: Authenticity Evaluation Benchmark for AI-Generated Video Sequences
AEGIS is a large-scale benchmark for detecting AI-generated videos, with a hard test set of Sora and KLing clips that current vision-language models detect at near-chance accuracy.