Automatic Watermark Detection: What 500 Real Cases Changed

Automated excerpt

A separate 36-image human-mask evaluation still measured only 47.1% precision and 11.0% recall. On a 26-image development set, an early full run reached 31.3% recall but only 6.5% precision. The same sample now supports preset guides for DeeVid AI, Dreamina AI / Jimeng, POLLO AI, Kling AI, Hailuo AI / MiniMax, Vidu AI and DIGEN AI.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.