Video Question Answering on HOIGen zero-shot
86.9AccuracyEgoBlur
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| EgoBlurprotocol=zero-shot, evaluation model=Qwen3-VL-8B, category=Classical2026.06 | 86.9 | 0.5 | |
| Original (upper bound)protocol=zero-shot, evaluation model=Qwen3-VL-8B2026.06 | 86.4 | — | |
| FAMSprotocol=zero-shot, evaluation model=Qwen3-VL-8B, category=Face-only, generative2026.06 | 86.13 | -0.27 | |
| DeepPrivacy2 (face)protocol=zero-shot, evaluation model=Qwen3-VL-8B, category=Face-only, generative2026.06 | 85.6 | -0.8 | |
| FADMprotocol=zero-shot, evaluation model=Qwen3-VL-8B, category=Body-only, generative2026.06 | 83.33 | -3.07 | |
| StructHumanprotocol=zero-shot, evaluation model=Qwen3-VL-8B, conditioning=Wan2.1-VACE2026.06 | 82.37 | -4.03 | |
| StructAllprotocol=zero-shot, evaluation model=Qwen3-VL-8B, conditioning=Wan2.1-VACE2026.06 | 81.8 | -4.6 | |
| Gaussian blurprotocol=zero-shot, evaluation model=Qwen3-VL-8B, category=Classical2026.06 | 81.33 | -5.07 | |
| Pixelationprotocol=zero-shot, evaluation model=Qwen3-VL-8B, category=Classical2026.06 | 78.2 | -8.2 | |
| Blackoutprotocol=zero-shot, evaluation model=Qwen3-VL-8B, category=Classical2026.06 | 73.47 | -12.93 | |
| DeepPrivacy2 (body)protocol=zero-shot, evaluation model=Qwen3-VL-8B, category=Body-only, generative2026.06 | 73.1 | -13.3 |