Video Question Answering on Video-ChatGPT benchmark zero-shot (test)
3.07CILLaMA-VID
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| LLaMA-VIDLLM Size=13B, GPT-3.5 Version=JUN, Train Free=false2024.05 | 3.07 | 3.05 | 3.6 | 2.58 | 2.63 | |
| DC+FreeVALLM Size=34B, GPT-3.5 Version=JAN, Train Free=true2024.05 | 3 | 2.53 | 3.25 | 2.65 | 2.92 | |
| LLaVA+FreeVALLM Size=13B, GPT-3.5 Version=JUN, Train Free=true2024.05 | 2.9 | 2.52 | 3.26 | 2.32 | 3.07 | |
| LLaVA+FreeVALLM Size=7B, GPT-3.5 Version=MAR, Train Free=true2024.05 | 2.88 | 2.52 | 3.25 | 2.32 | 3.07 | |
| LLaVA+FreeVALLM Size=13B, GPT-3.5 Version=JAN, Train Free=true2024.05 | 2.88 | 2.52 | 3.25 | 2.34 | 3.05 | |
| DC+FreeVALLM Size=13B, GPT-3.5 Version=JAN, Train Free=true2024.05 | 2.85 | 2.53 | 3.23 | 2.29 | 2.96 | |
| DC+FreeVALLM Size=7B, GPT-3.5 Version=JAN, Train Free=true2024.05 | 2.8 | 2.51 | 3.17 | 2.22 | 3.05 | |
| BT-AdapterLLM Size=7B, GPT-3.5 Version=JUN, Train Free=false2024.05 | 2.68 | 2.69 | 3.27 | 2.34 | 2.46 | |
| Video-ChatGPTLLM Size=7B, GPT-3.5 Version=MAR, Train Free=false2024.05 | 2.5 | 2.57 | 2.69 | 2.16 | 2.2 | |
| VideoChatLLM Size=7B, GPT-3.5 Version=MAR, Train Free=false2024.05 | 2.23 | 2.5 | 2.53 | 1.94 | 2.24 | |
| LLaMA-AdapterLLM Size=7B, GPT-3.5 Version=MAR, Train Free=false2024.05 | 2.03 | 2.32 | 2.3 | 1.98 | 2.15 | |
| Video-LLaMALLM Size=7B, GPT-3.5 Version=MAR, Train Free=false2024.05 | 1.96 | 2.18 | 2.16 | 1.82 | 1.79 |