Video Question Answering on CinePile
58.98AccuracyVITED (Temporal Evidence Distillation)
Evaluation Results
| Method | Links | |
|---|---|---|
| VITED (Temporal Evidence Distillation)Params=7B, Base Model=TimeChat Base2025.03 | 58.98 | |
| VITED (Dense Caption Distillation)Params=7B, Base Model=TimeChat Base2025.03 | 57.85 | |
| VITED (Temporal Evidence Distillation)Params=7B, Base Model=LLaVA-Video Base2025.03 | 56.39 | |
| TimeChat (Video Instruction Tuning)Params=7B, Base Model=TimeChat Base2025.03 | 55.86 | |
| LLaVA-Video (Video Instruction Tuning)Params=7B, Base Model=LLaVA-Video Base2025.03 | 54.97 | |
| LLaVA-Video (Chain-of-Thought)Params=7B, Base Model=LLaVA-Video Base2025.03 | 54.82 | |
| VITED (Dense Caption Distillation)Params=7B, Base Model=LLaVA-Video Base2025.03 | 54.79 | |
| LLaVA-VideoParams=7B, Base Model=LLaVA-Video Base2025.03 | 53.77 | |
| LLaVA-OneVisionParams=7B2025.03 | 46.42 | |
| LLaMA-3.2VParams=11B2025.03 | 39.55 | |
| VideoLLaVAParams=7B2025.03 | 22.51 | |
| TimeChat (Chain-of-Thought)Params=7B, Base Model=TimeChat Base2025.03 | 14.27 | |
| TimeChatParams=7B, Base Model=TimeChat Base2025.03 | 13.67 |