List your company

Video Grounding on QVHighlights (test)

74.11mAP (IoU=0.5)VideoMind
9.286826.115942.94559.7741Apr 6, 2023Aug 2, 2023Nov 29, 2023Mar 26, 2024Jul 23, 2024Nov 18, 2024Mar 17, 2025

Evaluation results

MethodLinks
VideoMindSize=2B, Fine-tuned=true2025.0374.1175.4259.3555.1551.6——
FlashVTGBackbone=InternVideo22024.1272.3370.6953.9653.8552——
R2-Tunning2024.1269.0468.0349.3547.5646.17——
R2-TuningFine-tuned=true2025.0369.0468.0349.3547.5646.17——
FlashVTG2024.1267.9966.085048.747.59——
BAM-DETRPre-training=236K ASR2023.1166.3363.8847.9248.2246.67——
LLMEPET2024.1265.7666.7349.9443.9144.05——
BAM-DETRPre-training=none, Audio modality=true2023.1165.6164.0748.1247.5146.91——
BAM-DETRPre-training=none, Audio modality=false2023.1164.5762.7148.6446.3345.36——
CG-DETR2024.1264.5165.4348.3842.7742.86——
UniVTG DBMBlock=DBM2024.0364.3766.6552.1946.6845.1840.1864.77
UniVTGPre-training=4.2M CLIP2023.1164.0665.4350.0645.0243.63——
UniVTGFine-tuned=true2025.0364.0665.4350.0645.0243.63——
TR-DETR2024.1263.9864.6648.9643.7342.62——
UniVTGBlock=ViM2024.0363.9765.5550.7746.1144.7440.2264.26
QD-DETRPre-training=236K ASR2023.1163.3763.1845.1940.3539.96——
UVCOM2024.1263.3763.5547.4742.6743.18——
QD-NetYear=2023, Setup=fully-supervised2024.0363.1562.3245.6142.0541.46——
QD-DETRPre-training=none, Audio modality=true2023.1163.0463.0645.140.140.19——
QD-DETRPre-training=none, Audio modality=false2023.1162.5262.444.9839.8839.86——
QD-DETR2024.1262.5262.444.9839.8839.86——
QD-DETRFine-tuned=true2025.0362.5262.444.9839.8839.86——
SFABD2024.1262.38——44.3943.79——
DenoiseLoc2023.0461.359.2745.0743.0742.96——
MH-DETRYear=2022, Setup=fully-supervised2024.0360.7560.0542.4838.1338.38——
MH-DETRPre-training=none2023.1160.7560.0542.4838.1338.38——
Moment-DETRPre-training=236K ASR2023.1160.5159.7840.3335.3636.14——
Moment-DETRFine-tuned=true2025.0360.5159.7840.3335.3636.14——
EaTR+Pre-training=none2023.1159.9557.9842.4139.2939——
LLaViLoYear=2023, Setup=fully-supervised2024.0359.7259.2341.42—36.94——
UniVTGBlock=Transformer (6-layer, reproduced)2024.0359.0959.8744.3240.2538.4839.2264.71
UniVTGBlock=Transformer (4-layer)2024.0357.658.8640.8635.5935.4738.260.96
UniVTGPre-training=none2023.1157.658.8640.8635.5935.47——
UniVTG2024.1257.658.8640.8635.5935.47——
UMTPre-training=236K ASR, Audio modality=true2023.1157.3360.8343.2639.1238.08——
UMTFine-tuned=true2025.0357.3360.8343.2639.1238.08——
Moment-DETR2023.0454.8252.8933.0229.430.73——
MDETRBlock=-2024.0354.8252.8933.0229.430.7335.6955.6
Moment-DETRYear=2021, Setup=fully-supervised2024.0354.8252.8933.0229.430.73——
Moment-DETRPre-training=none2023.1154.8252.8933.0229.430.73——
M-DETR2024.1254.8252.8933.0229.1730.73——
MomentDiffFine-tuned=true2025.0354.5758.2141.4837.2136.84——
VTG-GPTYear=2023, Setup=zero-shot2024.0354.1353.8138.1329.2430.5——
Moment DiffPre-training=none2023.1154.0257.4239.6635.7335.95——
MomentDiff2024.1254.0257.4239.6635.7335.95——
UMT2023.0453.8356.2341.1837.0136.12——
UMTBlock=-2024.0353.8356.2341.1837.0136.1238.1859.99
UMTYear=2023, Setup=fully-supervised2024.0353.8356.2341.1837.0136.12——
UMTPre-training=none, Audio modality=true, Reproduced=true2023.1153.8356.2341.1837.0136.12——
UMT2024.1253.8356.2341.1837.0136.12——
XML+2023.0447.8946.6933.4634.6734.9——
XMLPre-training=none2023.1147.8946.6933.4634.6734.9——
XML+Fine-tuned=true2025.0347.8946.6933.4634.6734.9——
XML2023.0444.6341.8330.3531.7332.14——
XMLFine-tuned=true2025.0344.6341.8330.3531.7332.14——
UniVTGYear=2023, Setup=zero-shot2024.0327.4225.168.957.6410.87——
MCN2023.0424.9411.412.728.2210.67——
MCNPre-training=none2023.1124.9411.412.728.2210.67——
CPIYear=2022, Setup=weakly supervised2024.0323.7432.2611.818.25———
CAL2023.0423.425.4911.547.659.89——
CALPre-training=none2023.1123.425.4911.547.659.89——
CPLYear=2022, Setup=weakly supervised2024.0322.7730.7210.757.48———
CLIPPre-training=none2023.1118.1116.885.1977.67——
CNMYear=2022, Setup=weakly supervised2024.0311.7814.113.972.12———