Video Question Answering on TGIF-QA zero-shot (test)
81.3AccuracyLinVT-Qwen2-VL
Evaluation results
| Method | Links | ||
|---|---|---|---|
| LinVT-Qwen2-VLSize=7B, Zero-shot=true2024.12 | 81.3 | 4.3 | |
| LinVT-InternVL2Size=8B, Zero-shot=true2024.12 | 79.4 | 4.3 | |
| LinVT-MolmoSize=7B, Zero-shot=true2024.12 | 79.3 | 4.2 | |
| TarsierSize=7B, Zero-shot=true2024.12 | 79.2 | 4.2 | |
| SlowFast-LLaVASize=7B, Zero-shot=true2024.12 | 78.7 | 4.2 | |
| LinVT-BLIP-3Size=4B, Zero-shot=true2024.12 | 78.7 | 4.3 | |
| PLLaVASize=7B, Zero-shot=true2024.12 | 77.5 | 4.1 | |
| BLIP-3-VideoSize=4B, Zero-shot=true2024.12 | 76.5 | 4.3 | |
| LinVT-AquilaSize=2B, Zero-shot=true2024.12 | 73.6 | 4 | |
| MiniGPT4-VideoSize=7B, Zero-shot=true2024.12 | 72.2 | 4.1 | |
| LinVT-MiphaSize=1.6B, Zero-shot=true2024.12 | 71.1 | 3.9 | |
| Video-LLaVASize=7B, Zero-shot=true2024.12 | 70 | 4 | |
| Chat-UniViSize=7B, Zero-shot=true2024.12 | 69 | 3.8 | |
| Video-ChatGPTSize=7B, Zero-shot=true2024.12 | 51.4 | 3 | |
| VideoChatSize=7B, Zero-shot=true2024.12 | 34.4 | 2.3 |