Video Question Answering on MSRVTT Open Ended (OE)
59.73AccuracyMiniGPT4-Video
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| MiniGPT4-VideoBackbone=Llama 2-7B, Using Subtitles=true, Zero-shot=true2024.04 | 59.73 | 3.3 | |
| MiniGPT4-VideoBackbone=Llama 2-7B, Using Subtitles=false, Zero-shot=true2024.04 | 58.83 | 3.29 | |
| MiniGPT4-VideoBackbone=Mistral-7B, Using Subtitles=true, Zero-shot=true2024.04 | 58.68 | 3.53 | |
| MiniGPT4-VideoBackbone=Mistral-7B, Using Subtitles=false, Zero-shot=true2024.04 | 58.26 | 3.52 | |
| LLaMA-VID-7BUsing Subtitles=false, Zero-shot=true2024.04 | 57.7 | 3.2 | |
| BT-Adapter-7BUsing Subtitles=false, Zero-shot=true2024.04 | 57 | 3.2 | |
| Video-ChatGPTUsing Subtitles=false, Zero-shot=true2024.04 | 49.3 | 2.8 | |
| Video ChatUsing Subtitles=false, Zero-shot=true2024.04 | 45 | 2.5 | |
| SimVTP2022.12 | 44.7 | — | |
| VIOLET2022.12 | 43.9 | — | |
| LLaMA AdapterUsing Subtitles=false, Zero-shot=true2024.04 | 43.8 | 2.7 | |
| MERLOT2022.12 | 43.1 | — | |
| ALPRO2022.12 | 42.1 | — | |
| JustAsk2022.12 | 41.5 | — | |
| ClipBert2022.12 | 37.4 | — | |
| Video LLaMAUsing Subtitles=false, Zero-shot=true2024.04 | 29 | 1.8 | |
| FrozenBiLMUsing Subtitles=false, Zero-shot=true2024.04 | 16.8 | — |