Video Question Answering on IntentQA (val)
86.6AccuracyMM1.5-Video-7B
Evaluation Results
| Method | Links | |
|---|---|---|
| MM1.5-Video-7BTraining Mode=SFT, Video Data=true, Model Size=7B2024.09 | 86.6 | |
| VideoChat2-7BTraining Mode=SFT, Video Data=true, Model Size=7B2024.09 | 81.9 | |
| MM1.5-Video-3BTraining Mode=SFT, Video Data=true, Model Size=3B2024.09 | 81.2 | |
| MM1.5-Video-7BTraining Mode=Training-free, Video Data=false, Model Size=7B2024.09 | 76.7 | |
| MM1.5-Video-1BTraining Mode=SFT, Video Data=true, Model Size=1B2024.09 | 74.2 | |
| MM1.5-Video-3BTraining Mode=Training-free, Video Data=false, Model Size=3B2024.09 | 72.7 | |
| MM1.5-Video-1BTraining Mode=Training-free, Video Data=false, Model Size=1B2024.09 | 67.8 | |
| IG-VLM-7B (LLaVA-v1.6)Training Mode=Training-free, Video Data=false, Model Size=7B2024.09 | 60.3 | |
| SlowFast-LLaVA-7BTraining Mode=Training-free, Video Data=false, Model Size=7B2024.09 | 60.1 |