Dense Video Captioning on E.T.Bench
43.4DVC F1MeCo (ETChat 3.8B)
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| MeCo (ETChat 3.8B)SFT Data=164K, Epochs=1, LoRA=true2025.03 | 43.4 | 20.3 | 27.3 | 15.7 | — | |
| MeCo (ETChat 7B)SFT Data=164K, Epochs=1, LoRA=true2025.03 | 43.4 | 20.7 | 30.1 | 16.5 | — | |
| E.M.GroundModel Parameters=3.8B, Zero-shot Evaluation=true2026.02 | 41.6 | 21.5 | 25.6 | 16.2 | — | |
| MeCo (QWen2VL 7B)SFT Data=164K, Epochs=1, LoRA=true2025.03 | 41.5 | 22.8 | 28.1 | 16.5 | — | |
| VTG-LLMModel Parameters=7B, Zero-shot Evaluation=true2026.02 | 40.2 | 18.6 | 20.8 | 14.4 | — | |
| LITAModel Parameters=7B, Zero-shot Evaluation=true2026.02 | 39.7 | 17.2 | 21 | 12.2 | — | |
| E.T.ChatModel Parameters=3.8B, Zero-shot Evaluation=true2026.02 | 38.4 | 19.7 | 24.4 | 14.6 | — | |
| Video-LLaVAModel Parameters=7B, Zero-shot Evaluation=true2026.02 | 28 | 15 | 0.9 | 8.3 | — | |
| LLaMA-VIDModel Parameters=7B, Zero-shot Evaluation=true2026.02 | 27.1 | 12.6 | 5.2 | 11.1 | — | |
| TimeChatModel Parameters=7B, Zero-shot Evaluation=true2026.02 | 16.6 | 12.5 | 5.6 | 9.2 | — | |
| PLLaVAModel Parameters=7B, Zero-shot Evaluation=true2026.02 | 13.3 | 10.6 | 9.7 | 11.8 | — | |
| VTimeLLMModel Parameters=7B, Zero-shot Evaluation=true2026.02 | 12.4 | 13.1 | 8.7 | 6.4 | — | |
| Video-ChatGPTModel Parameters=7B, Zero-shot Evaluation=true2026.02 | 8.8 | 11.3 | 5.7 | 10.2 | — | |
| Video-ChatGPT (7B)Setting=Zero-shot baseline2025.03 | 8.8 | 11.3 | 5.7 | 10.2 | — | |
| Dispider2026.03 | — | — | — | — | 33.8 | |
| Qwen2-VL2026.03 | — | — | — | — | 22.6 | |
| StreamBridge2026.03 | — | — | — | — | 38.3 | |
| StreamReady2026.03 | — | — | — | — | 43.4 |