Video Question Answering on NExT-QA zero-shot
0.845AccuracyVideoLLaMA3
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| VideoLLaMA3LLM=Qwen2.5-7B, Frames=1fps2025.07 | 0.845 | — | |
| InternVL3.5-REGATELLM=Qwen3-14B, Frames=16, Tokens=2.32B (↓ 41.41%)2025.07 | 0.812 | — | |
| InternVL3.5LLM=Qwen3-14B, Frames=16, Tokens=3.96B2025.07 | 0.808 | — | |
| LLaVA-OneVisionLLM=Qwen2-7B, Frames=322025.07 | 0.794 | — | |
| Original (upper bound)protocol=zero-shot, evaluation model=Qwen3-VL-8B2026.06 | 0.7831 | — | |
| FAMSprotocol=zero-shot, evaluation model=Qwen3-VL-8B, category=Face-only, generative2026.06 | 0.7797 | -0.34 | |
| DeepPrivacy2 (face)protocol=zero-shot, evaluation model=Qwen3-VL-8B, category=Face-only, generative2026.06 | 0.778 | -0.51 | |
| EgoBlurprotocol=zero-shot, evaluation model=Qwen3-VL-8B, category=Classical2026.06 | 0.7756 | -0.75 | |
| LLaVA-NeXT-VideoLLM=Qwen2-32B, Frames=322025.07 | 0.773 | — | |
| FADMprotocol=zero-shot, evaluation model=Qwen3-VL-8B, category=Body-only, generative2026.06 | 0.7649 | -1.82 | |
| StructAllprotocol=zero-shot, evaluation model=Qwen3-VL-8B, conditioning=Wan2.1-VACE2026.06 | 0.7585 | -2.46 | |
| VideoChat2-REGATELLM=Mistral-7B, Frames=16, Tokens=2.22B (↓ 43.51%)2025.07 | 0.755 | — | |
| StructHumanprotocol=zero-shot, evaluation model=Qwen3-VL-8B, conditioning=Wan2.1-VACE2026.06 | 0.7537 | -2.94 | |
| VideoChat2LLM=Mistral-7B, Frames=16, Tokens=3.93B2025.07 | 0.752 | — | |
| Pixelationprotocol=zero-shot, evaluation model=Qwen3-VL-8B, category=Classical2026.06 | 0.7376 | -4.55 | |
| DeepPrivacy2 (body)protocol=zero-shot, evaluation model=Qwen3-VL-8B, category=Body-only, generative2026.06 | 0.7339 | -4.92 | |
| Blackoutprotocol=zero-shot, evaluation model=Qwen3-VL-8B, category=Classical2026.06 | 0.73 | -5.31 | |
| Gaussian blurprotocol=zero-shot, evaluation model=Qwen3-VL-8B, category=Classical2026.06 | 0.7293 | -5.38 | |
| VideoLLaMA2LLM=Qwen2-7B, Frames=16, Tokens=83.82M2025.07 | 0.708 | — | |
| VideoLLaMA2-REGATELLM=Qwen2-7B, Frames=16, Tokens=49.27M (↓ 41.22%)2025.07 | 0.7 | — | |
| VILA1.5LLM=Llama-2-40B, Frames=82025.07 | 0.679 | — | |
| SeViLAParams=4.1B, Zero-shot=true2023.04 | 0.636 | — | |
| InternVideoType=Enc-Dec, Params=1.3B, Zero-shot=true2023.04 | 0.491 | — | |
| VicTR (B/16)Params=167M, Zero-shot=true2023.04 | 0.455 | — | |
| X-CLIPType=Enc only, Params=194M, Zero-shot=true2023.04 | 0.438 | — | |
| Just-AskParams=75M, Zero-shot=true2023.04 | 0.384 | — | |
| CaKE-LMParams=2.7B, Zero-shot=true2023.04 | 0.349 | — | |
| RandomZero-shot=true2023.04 | 0.2 | — |