List your company

Dense Video Captioning on YouCook2 (val)

80.53CIDErSTaRC
0.106820.985941.86562.7441Feb 27, 2023Sep 7, 2023Mar 18, 2024Sep 27, 2024Apr 8, 2025Oct 18, 2025Apr 29, 2026

Evaluation results

MethodLinks
STaRCPT=✓2026.0380.5310.73————34.34
STaRCPretrained=true2026.0380.5310.7313.866.75———
Sali4VidPretrained=true2026.0375.810.2813.546.35———
HiCM2Pretrained=true2026.0371.8410.7312.86.11———
HiCM²Pretrain=✓2026.0471.810.712.8————
Vid2SeqPretrained=true, reproduced_from_official=true2026.0366.299.8712.415.64———
DIBSTraining paradigm=Fully-Supervised, Pre-trained=56k, Backbone=UniVL2024.0459.357.979.41————
Vid2SeqBackbone=CLIP2023.0247.17.99.3————
Vid2SeqTraining paradigm=Fully-Supervised, Pre-trained=15M, Backbone=CLIP2024.0447.17.99.3————
Vid2SeqPretrain=✓2026.0447.17.99.3————
PDVCTraining paradigm=Fully-Supervised, Pre-trained=None, Backbone=UniVL2024.0446.026.877.87————
DIBSTraining paradigm=Fully-Supervised, Pre-trained=56k, Backbone=CLIP2024.0444.446.397.51————
DIBSPretrained=true2026.0344.446.397.51————
TimeExpertPT=✓2026.03397.2————33.5
TRACEPT=✓2026.0335.56.7————31.8
CACMIPretrained=false2026.0334.835.576.211.7———
E2DVCPretrained=false2026.0334.265.396.111.68———
DenseStep2M pipelinePretrain=×2026.0433.65.69.4————
Streaming V2SPretrained=true2026.0332.967.1————
CM²Pretrain=×2026.0431.75.36.1————
CM2Pretrained=false2026.0331.665.346.081.63———
PDVCPretrained=false2026.0329.694.925.561.4———
DIBSTraining paradigm=Weakly-Supervised, Pre-trained=None, Backbone=UniVL2024.0429.624.965.9————
PDVCBackbone=CLIP2023.0228.94.95.7————
PDVCPretrain=×2026.0428.94.95.7————
PDVCTraining paradigm=Fully-Supervised, Pre-trained=None, Backbone=CLIP2024.0428.3755.47————
GVLFeatures=TSN2023.0326.524.915.011.04———
E2ESGTraining paradigm=Fully-Supervised, Pre-trained=None, Backbone=C3D2024.0425—3.49————
E2ESGPretrain=×2026.0425—3.5————
PDVCTraining paradigm=Fully-Supervised, Pre-trained=None, Backbone=TSN2024.0422.714.424.74————
PDVCFeatures=TSN2023.0322.714.424.740.8———
PDVCBackbone=TSN2023.0222.74.44.7————
DIBSTraining paradigm=Weakly-Supervised, Pre-trained=None, Backbone=CLIP2024.0422.054.034.63————
Vid2SeqPretrain=×2026.041844.6————
SAILSetting=Weakly-Supervised, Features=CLIP2026.0314.614.083.63—5.422.94—
ILCACMSetting=Weakly-Supervised, Features=CLIP, Implementation=Re-implementation2026.0313.493.63.41—4.752.59—
VTG-LLMPT=✓2026.0313.43.6————20.6
TimeChatPT=✓2026.03113.4————19.5
PWS-DVCSetting=Weakly-Supervised, Features=C3D, Source=Reported in [11]2026.039.813.142.48————
WSDECSetting=Weakly-Supervised, Features=C3D, Source=Reported in [11]2026.038.432.111.47————
UEDVCTraining paradigm=Fully-Supervised, Pre-trained=676k, Backbone=TSN2024.048.373.342.18————
MTFeatures=TSN2023.036.1—3.180.3———
MTBackbone=TSN2023.023.26.1—————
BCHRBackbone=C3D2023.02—3.8—————
E2ESGBackbone=C3D2023.02—203.5————
ECHRFeatures=TSN2023.03——3.82————
SGRFeatures=TSN2023.03——4.35————