Dense Video Captioning on ActivityNet (val)
35.38CIDErSAIL
Evaluation results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| SAILSetting=Weakly-Supervised, Features=CLIP2026.03 | 35.38 | 6.29 | 8.63 | 15.29 | 15.86 | 8.3 | 4.27 | 2.3 | |
| E^2DVCSetting=Fully-Supervised, Features=CLIP2026.03 | 33.63 | 6.13 | 8.57 | — | — | — | — | 2.43 | |
| ILCACMSetting=Weakly-Supervised, Features=CLIP2026.03 | 33.42 | 6.08 | 8.48 | 14.77 | 15.36 | 8.12 | 4.17 | 2.26 | |
| CM^2Setting=Fully-Supervised, Features=CLIP2026.03 | 33.01 | 6.18 | 8.55 | — | — | — | — | 2.38 | |
| DIBSTraining paradigm=Fully-Supervised, Pre-trained=56k, Backbone=CLIP2024.04 | 31.89 | 5.85 | 8.93 | — | — | — | — | — | |
| PDVCTraining paradigm=Fully-Supervised, Pre-trained=None, Backbone=CLIP2024.04 | 30.11 | 5.63 | 8.31 | — | — | — | — | — | |
| Vid2SeqBackbone=CLIP2023.02 | 30.1 | 5.8 | 8.5 | — | — | — | — | — | |
| Vid2SeqTraining paradigm=Fully-Supervised, Pre-trained=15M, Backbone=CLIP2024.04 | 30.1 | 5.8 | 8.5 | — | — | — | — | — | |
| Vid2SeqSetting=Fully-Supervised, Features=CLIP2026.03 | 30.1 | 5.8 | 8.5 | — | — | — | — | — | |
| PDVCBackbone=CLIP2023.02 | 29.3 | 6 | 7.6 | — | — | — | — | — | |
| PDVCTraining paradigm=Fully-Supervised, Pre-trained=None, Backbone=TSN2024.04 | 28.96 | 5.44 | 7.96 | — | — | — | — | — | |
| DIBSTraining paradigm=Fully-Supervised, Pre-trained=56k, Backbone=UniVL2024.04 | 28.85 | 5.35 | 8.25 | — | — | — | — | — | |
| PDVCTraining paradigm=Fully-Supervised, Pre-trained=None, Backbone=UniVL2024.04 | 28.21 | 5.43 | 8.24 | — | — | — | — | — | |
| PDVCSetting=Fully-Supervised, Features=C3D2026.03 | 25.87 | 5.26 | 7.5 | — | — | — | — | 1.65 | |
| PDVCBackbone=TSN2023.02 | 25 | 5.4 | 8 | — | — | — | — | — | |
| EC-SLTraining paradigm=Weakly-Supervised, Pre-trained=None, Backbone=C3D2024.04 | 21.21 | — | 7.49 | — | — | — | — | — | |
| EC-SLSetting=Weakly-Supervised, Features=C3D2026.03 | 21.21 | — | 7.49 | 13.02 | 13.36 | 5.96 | 2.78 | 1.33 | |
| PWS-DVC*Setting=Weakly-Supervised, Features=C3D2026.03 | 20.59 | — | 7.28 | 12.71 | — | — | — | 1.35 | |
| WS-DECTraining paradigm=Weakly-Supervised, Pre-trained=None, Backbone=C3D2024.04 | 18.77 | — | 6.3 | — | — | — | — | — | |
| WSDECSetting=Weakly-Supervised, Features=C3D2026.03 | 18.77 | — | 6.3 | 12.55 | 12.41 | 5.5 | 2.62 | 1.27 | |
| DIBSTraining paradigm=Weakly-Supervised, Pre-trained=None, Backbone=CLIP2024.04 | 15.86 | 4.67 | 7.33 | — | — | — | — | — | |
| BCHRBackbone=C3D2023.02 | 14.7 | 3.2 | 7.2 | — | — | — | — | — | |
| ECGSetting=Weakly-Supervised, Features=C3D2026.03 | 14.25 | — | 7.06 | — | 11.85 | 5.64 | 2.71 | 1.33 | |
| WLTTraining paradigm=Weakly-Supervised, Pre-trained=None, Backbone=TSN2024.04 | 13.79 | — | 4.93 | — | — | — | — | — | |
| DIBSTraining paradigm=Weakly-Supervised, Pre-trained=None, Backbone=UniVL2024.04 | 13.75 | 4.26 | 6.76 | — | — | — | — | — | |
| DVCSetting=Fully-Supervised, Features=C3D2026.03 | 12.61 | — | 6.93 | — | 12.22 | 5.72 | 2.27 | 0.73 | |
| DCESetting=Fully-Supervised, Features=C3D2026.03 | 12.43 | — | 5.69 | — | 10.81 | 4.57 | 1.9 | 0.71 | |
| MTBackbone=TSN2023.02 | 5 | 9.3 | — | — | — | — | — | — | |
| UEDVCBackbone=TSN2023.02 | — | 5.5 | — | — | — | — | — | — |