AV-FABLE: Audio-Visual Manipulation Forensics in Long-Form Video
The story so far
Hugging Face has released AV-FABLE, a dual timeline benchmark for long-form audio-video tamper detection, indicating that frozen audio-visual large language model perceptual features contain the best forensic evidence by separating time decoders rather than language output for recovery. Local AI tampering in long videos often affects brief events that impact the authenticity of other content, making video-level classification insufficient for forensic analysis.
AI-written from the reports · Updated 22 days ago
Coverage timeline
Follow the coverage to see every side of the story.
- Hugging Face Daily PapersAV-FABLE: Audio-Visual Manipulation Forensics in Long-Form Videos
AV-FABLE introduces an audio-visual benchmark for sparse tampering in long videos, demonstrating that frozen audio-visual large language models' perceptual features contain forensic evidence that the best recovery is achieved by separating time decoders rather than language outputs. Local AI tampering in long videos often affects brief events that impact the authenticity of other content, making video-level classification insufficient for forensic analysis.