Result Details
Task: Wav2lip Deepfake Video Model Attribution
Analysis Date: 2024-11-01 10:21:00.752761
Information:
Resolution: 576 x 1024 | Codec: h264 | File Size: 1382.69KB | Bitrate: 240 kbps | Duration: 29.97 seconds | FPS: 30.0 |
Resolution: 576 x 1024 | Codec: h264 | File Size: 1382.69KB | Bitrate: 240 kbps | Duration: 29.97 seconds | FPS: 30.0 |
Analytic Name: WAV2LIP-STA
Description: Deep learning based method that can identify wav2lip model generated deepfake videos. This method learns the spatial and temporal artifacts from multi-frames (5) to expose wav2lip deepfakes.
Reference:
https://arxiv.org/pdf/2202.12951.pdf
🧪 Fake Probability: 73.74%
â–²
73.74%
AI-generated Likelihood
Scope: Human face videos
Advanced Result:
Download