Video Question Answering on VCGBench ActivityNet
3.27CIVideoGPT+
Evaluation results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| VideoGPT+Number of frames=162024.06 | 3.27 | 3.18 | 3.74 | 2.83 | 3.39 | 3.28 | |
| IG-VLMNumber of frames=162024.06 | 3.11 | 2.78 | 3.51 | 2.44 | 3.29 | 3.03 | |
| VideoChat2Number of frames=162024.06 | 3.02 | 2.88 | 3.51 | 2.66 | 2.81 | 2.98 | |
| LLAMA-VIDNumber of frames=162024.06 | 2.96 | 3 | 3.53 | 2.46 | 2.51 | 2.89 | |
| Chat-UniViNumber of frames=642024.06 | 2.89 | 2.91 | 3.46 | 2.89 | 2.81 | 2.99 | |
| Video-LLaVANumber of frames=162024.06 | 2.84 | 2.86 | 3.44 | 2.46 | 2.57 | 2.81 | |
| VTimeLLMNumber of frames=162024.06 | 2.78 | 3.1 | 3.4 | 2.49 | 2.47 | 2.85 | |
| BT-AdapterNumber of frames=162024.06 | 2.68 | 2.69 | 3.27 | 2.34 | 2.46 | 2.69 | |
| Video-ChatGPTNumber of frames=1002024.06 | 2.4 | 2.52 | 2.62 | 1.98 | 2.37 | 2.38 |