Binary Video Classification on PHTV (test)
94.29AccuracyQwen3-VL-8B-Instruct (LoRA)
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Qwen3-VL-8B-Instruct (LoRA)Learning Paradigm=Final Deployed Model, Fine-tuning Method=LoRA, Base Model=Qwen3-VL-8B-Instruct2026.05 | 94.29 | 96.41 | 92 | 94.15 | 3.43 | |
| Early Fusion (Text+Video)Modality=Text+Video, Learning Paradigm=Multimodal Fusion Models2026.05 | 92.57 | 94.08 | 90.86 | 92.44 | 5.71 | |
| Qwen-VL-MAX (128-shot)Learning Paradigm=In-Context Learning Experiments, Few-shot examples=128-shot2026.05 | 79.66 | 82.1 | 76 | 78.93 | 16.67 | |
| BERT (Text-only)Modality=Text-only, Learning Paradigm=Multimodal Fusion Models2026.05 | 78.57 | 76.88 | 81.71 | 79.22 | 24.57 | |
| Late Fusion (Text+Video)Modality=Text+Video, Learning Paradigm=Multimodal Fusion Models2026.05 | 77.43 | 86.92 | 64.57 | 74.1 | 9.71 | |
| VideoMAE (Video-only)Modality=Video-only, Learning Paradigm=Multimodal Fusion Models2026.05 | 72.29 | 71.91 | 73.14 | 72.52 | 28.57 | |
| Qwen2.5-VL-7B-InstructLearning Paradigm=In-Context Learning Experiments2026.05 | 68.86 | 81.73 | 48.57 | 60.93 | 10.86 | |
| Qwen-VL-MAX + CoT-CNLearning Paradigm=In-Context Learning Experiments, Chain-of-Thought (CoT) Prompting=CN2026.05 | 63.87 | 94.12 | 30.57 | 46.15 | 1.96 | |
| Claude-Opus-4-1 + CoT-ENLearning Paradigm=In-Context Learning Experiments, Chain-of-Thought (CoT) Prompting=EN2026.05 | 63.87 | 89.83 | 30.81 | 45.89 | 3.45 | |
| Qwen-VL-MAX + CoT-ENLearning Paradigm=In-Context Learning Experiments, Chain-of-Thought (CoT) Prompting=EN2026.05 | 58.6 | 93.55 | 17.16 | 29 | 1.15 | |
| Qwen3-VL-Plus + CoT-CNLearning Paradigm=In-Context Learning Experiments, Chain-of-Thought (CoT) Prompting=CN2026.05 | 58 | 96.67 | 16.57 | 28.29 | 0.57 | |
| Gemma3-4BLearning Paradigm=In-Context Learning Experiments2026.05 | 57.14 | 59.54 | 44.57 | 50.98 | 30.29 | |
| GPT-4-Turbo + CoT-ENLearning Paradigm=In-Context Learning Experiments, Chain-of-Thought (CoT) Prompting=EN2026.05 | 54.29 | 66.67 | 17.14 | 27.27 | 8.57 | |
| Gemma3-12BLearning Paradigm=In-Context Learning Experiments2026.05 | 53.43 | 87.5 | 8 | 14.66 | 1.14 | |
| Qwen2.5-VL-3B-InstructLearning Paradigm=In-Context Learning Experiments2026.05 | 46.86 | 41.79 | 16 | 23.14 | 22.29 |