Question Answering On Next Qa Open Ended
評価指標
Accuracy
Confidence Score
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
比較表
| モデル名 | Accuracy | Confidence Score |
|---|---|---|
| moviechat-from-dense-token-to-sparse-memory | 49.9 | 2.7 |
| video-chatgpt-towards-detailed-video | 54.6 | 3.2 |
| videochat-chat-centric-video-understanding | 56.6 | 3.2 |
| vista-llama-reliable-video-narrator-via-equal | 60.7 | 3.4 |
| flash-vstream-memory-based-real-time | 61.6 | 3.4 |
| moviechat-question-aware-sparse-memory-for | 54.8 | 3.0 |