Dense Video Captioning on E.T. Bench Dense Captioning
48.3DVC F1D²VLM-3.8B
Evaluation results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| D²VLM-3.8BYear=ICCV’252025.12 | 48.3 | 25.5 | 26.7 | 18.1 | 37.5 | 21.8 | |
| VTG-LLM-7BYear=AAAI’252025.12 | 40.2 | 18.6 | 20.8 | 14.4 | 30.5 | 16.5 | |
| LITA-13BYear=ECCV’242025.12 | 39.7 | 17.2 | 21 | 12.2 | 30.4 | 14.7 | |
| Qwen2.5-VL-7BYear=arXiv’25, Implementation=Implemented by this paper authors2025.12 | 39 | 21.4 | 25.5 | 15.1 | 32.2 | 18.2 | |
| E.T.Chat-3.8BYear=NeurIPS’242025.12 | 38.4 | 19.7 | 24.4 | 14.6 | 31.4 | 17.2 | |
| Video-LLaVA-7BYear=EMNLP’242025.12 | 28 | 15 | 0.9 | 8.3 | 14.5 | 11.7 | |
| LLaMA-VID-7BYear=ECCV’242025.12 | 27.1 | 12.6 | 5.2 | 11.1 | 16.2 | 11.9 | |
| TimeChat-7BYear=CVPR’242025.12 | 16.6 | 12.5 | 5.6 | 9.2 | 11.1 | 10.9 | |
| PLLaVAYear=arXiv’242025.12 | 13.3 | 10.6 | 9.7 | 11.8 | 11.5 | 11.2 | |
| VTimeLLM-7BYear=CVPR’242025.12 | 12.4 | 13.1 | 8.7 | 6.4 | 10.6 | 9.8 | |
| Video-ChatGPT-7BYear=ACL’242025.12 | 8.8 | 11.3 | 5.7 | 10.2 | 7.3 | 10.8 | |
| Video-LLaMA-2-7BYear=arXiv’242025.12 | 0.6 | 14.5 | 0 | 15.2 | 0.3 | 14.9 |