Visual Question Answering on This-Is-My-Video
61.3Accuracy (VQA)PeKit
Evaluation Results
| Method | Links | |
|---|---|---|
| PeKitBase Model=InternVideoChat2.52025.02 | 61.3 | |
| InternVideoChat2.52025.02 | 56.6 | |
| PeKitBase Model=LLaVA-OneVision-Qwen22025.02 | 35 | |
| LLaVA-OneVision-Qwen22025.02 | 23 |