Dense Video Captioning on YouCook2
7.9SODA_cVid2Seq
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Vid2SeqPre-trained=true2026.03 | 7.9 | 47.1 | 9.3 | — | — | |
| VideoLoomModel Scale=8B2026.01 | 7.3 | 41.5 | — | 33.6 | — | |
| ROS-DVCPre-trained=false2026.03 | 7.06 | 39.18 | 6.14 | — | 2.1 | |
| TRACEModel Scale=7B2026.01 | 6.7 | 35.5 | — | 31.8 | — | |
| DDVCPre-trained=false2026.03 | 6.68 | 38.75 | 6.92 | — | 1.92 | |
| DIBSPre-trained=true2026.03 | 6.39 | 44.4 | 7.51 | — | — | |
| E2DVCPre-trained=false2026.03 | 5.39 | 34.26 | 6.11 | — | 1.68 | |
| CM2Pre-trained=false2026.03 | 5.34 | 31.66 | 6.08 | — | 1.63 | |
| MCCLPre-trained=false2026.03 | 5.21 | 36.09 | 6.53 | — | 2.04 | |
| PDVCPre-trained=false2026.03 | 4.92 | 29.69 | 5.56 | — | 1.4 | |
| TA-Promptingparameters=7B2026.01 | 4.3 | 15.6 | 4.2 | — | — | |
| VTG-LLMModel Scale=7B2026.01 | 3.6 | 13.4 | — | 20.6 | — | |
| VTG-LLMparameters=7B2026.01 | 3.6 | 13.4 | — | — | — | |
| TimeChatModel Scale=7B2026.01 | 3.4 | 11 | — | 19.5 | — | |
| TimeChatparameters=7B2026.01 | 3.4 | 11 | — | — | — | |
| TemporalVLMEvaluation Protocol=Task-specific fine-tuning2024.12 | 3.4 | 13.2 | — | 20 | — | |
| D²VLM-3.8BYear=ICCV’25, Number of Parameters=3.8B2025.12 | 3.2 | 10.6 | — | 26.4 | — | |
| TimeChatEvaluation Protocol=Task-specific fine-tuning2024.12 | 3.1 | 10.3 | — | 19.5 | — | |
| VTimeLLMparameters=7B2026.01 | 2.7 | 8.6 | 2.7 | — | — | |
| HiVid-NarratorEvaluation Protocol=zero-shot, SPA-Compressor=true2026.01 | 2.4 | 8.4 | — | 30.5 | — | |
| LITAparameters=13B2026.01 | 2.4 | 9 | 2.7 | — | — | |
| LongVLMEvaluation Protocol=Task-specific fine-tuning2024.12 | 2.3 | 8.1 | — | 16.9 | — | |
| TRACEEvaluation Protocol=zero-shot2026.01 | 2.2 | 8.1 | — | 22.4 | — | |
| TRACE-7BYear=ICLR’25, Number of Parameters=7B2025.12 | 2.2 | 8.1 | — | 22.4 | — | |
| HiVid-NarratorEvaluation Protocol=zero-shot, SPA-Compressor=false2026.01 | 2.1 | 6.7 | — | 25.1 | — | |
| E.M.GroundNumber of Parameters=3.8B, Zero-shot=true2026.02 | 1.6 | 5.1 | — | 20.1 | — | |
| E.T.ChatNumber of Parameters=3.8B, Zero-shot=true2026.02 | 1.5 | 4.7 | — | 15.1 | — | |
| VTG-LLMNumber of Parameters=7B, Zero-shot=true2026.02 | 1.5 | 5 | — | 17.5 | — | |
| VTG-LLMEvaluation Protocol=zero-shot2026.01 | 1.5 | 5 | — | 17.5 | — | |
| VTG-LLM-7BYear=AAAI’25, Number of Parameters=7B2025.12 | 1.5 | 5 | — | 17.5 | — | |
| TimeChat + Seq2TimeRelative Position Token (RPT)=true2024.11 | 1.3 | 4.2 | 1.3 | 16.2 | — | |
| Seq2TimeNumber of Parameters=7B, Zero-shot=true2026.02 | 1.3 | 4.2 | — | 16.2 | — | |
| TimeChat + Seq2TimeRelative Position Token (RPT)=false2024.11 | 1.2 | 3.7 | 1.4 | 15.7 | — | |
| TimeChatNumber of Parameters=7B, Zero-shot=true2026.02 | 1.2 | 3.4 | — | 12.6 | — | |
| TimeChatEvaluation Protocol=zero-shot2026.01 | 1.2 | 3.4 | — | 12.6 | — | |
| TimeChat-7BYear=CVPR’24, Number of Parameters=7B2025.12 | 1.2 | 3.4 | — | 12.6 | — | |
| TimeChat [30]*2024.11 | 1 | 2.9 | 1.1 | 12.7 | — | |
| VTimeLLMEvaluation Protocol=zero-shot2026.01 | 1 | 3.6 | — | 9.1 | — | |
| VideoChatEvaluation Protocol=zero-shot2026.01 | 0.2 | 0.6 | — | 3.4 | — | |
| ValleyEvaluation Protocol=zero-shot2026.01 | 0.1 | 0 | — | 1.5 | — |