List your company

Moment Retrieval on Charades-STA (test)

70.32R@0.5FlashVTG
45.04851.60958.1764.731Jul 20, 2021May 2, 2022Feb 12, 2023Nov 25, 2023Sep 6, 2024Jun 19, 2025Apr 2, 2026

Evaluation results

MethodLinks
FlashVTGBackbone=InternVideo2-6B2024.1270.32—49.87—————
VideoLights-Bpre-training=true, features=BLIP2024.1261.9673.3341.0552.94————
LA-DETRFeatures=SlowFast/CLIP2024.1261.45—40.22—————
VideoLights-Bpre-training=false, features=BLIP2024.1260.371.7237.2351.25————
UniVTGyear=2023, venue=ICCV, pre-training=true2024.1260.1972.6338.5552.17————
FlashVTGFeatures=SlowFast/CLIP2024.1260.11—38.01—————
VideoLightspre-training=true, features=standard2024.1260.1172.2637.851.44————
FlashVTGBackbone=SlowFast R-50 + CLIP-B/322024.1260.11—38.01—————
BAM-DETRFeatures=SlowFast/CLIP2024.1259.83—39.83—————
R2-TuningFeature Extractors=CLIP-B/322024.0359.7870.9137.0250.86————
UVCOMFeatures=SlowFast/CLIP2024.1259.25—36.64—————
UVCOMFeatures=SlowFast + CLIP2023.1159.25—36.64—————
CG-DETRBackbone=SlowFast R-50 + CLIP-B/322024.1258.44—36.34—————
CG-DETRBackbone=Slowfast and CLIP2023.1158.470.436.350.1————
VideoLightspre-training=false, features=standard2024.1258.0470.6736.8850.2————
UniVTGFeatures=SlowFast/CLIP2024.1258.01—35.65—————
UniVTGFeatures=SlowFast + CLIP2023.1158.01—35.65—————
UniVTGFeat.=SF+C, Protocol=S2@202023.0858.01—35.65—————
UniVTGFeature Extractors=CLIP-B/32 and SlowFast R-502024.0358.0170.8135.6550.1————
UniVTGyear=2023, venue=ICCV2024.1258.0170.8135.6550.1————
UniVTGBackbone=SlowFast R-50 + CLIP-B/322024.1258.01—35.65—————
UniVTGBackbone=Slowfast and CLIP2023.115870.835.750.1————
TR-DETRFeatures=SlowFast/CLIP2024.1257.61—33.52—————
TR-DETRyear=2024, venue=AAAI2024.1257.61—33.52—————
TR-DETRBackbone=SlowFast R-50 + CLIP-B/322024.1257.61—33.52—————
GroundVTS-QBackbone=Qwen2.5VL-7B2026.0457.571.534.250.1————
QD-DETRFeatures=SlowFast/CLIP2024.1257.31—32.55—————
QD-DETRfeat=SF+C, Source Modality=Video2023.0357.31—32.55—————
QD-DETRFeatures=SlowFast + CLIP2023.1157.31—32.55—————
QD-DETRFeat.=SF+C, Protocol=S2@202023.0857.31—32.55—————
QD-DETRyear=2023, venue=CVPR2024.1257.31—32.55—————
QD-DETRBackbone=SlowFast R-50 + CLIP-B/322024.1257.31—32.55—————
QD-DETRBackbone=Slowfast and CLIP2023.1157.3—32.6—————
UVCOMaudio modality=true2023.1156.69—34.76—————
TaskWeaveBackbone=VGG2024.0456.51—33.66—————
LA-DETRFeatures=VGG/GloVe2024.1256.16—36.1—————
LLaViLoBackbone=Slowfast and CLIP2023.1155.7—33.4—————
Moment-DETRPre-training=10K HowTo100M videos2021.0755.65—34.17—————
MomentDiffType=SF+C, C2023.0755.57—32.42—61.0732.5132.85—
QD-DETRfeat=VGG, Source Modality=Video + Audio2023.0355.51—34.17—————
QD-DETRaudio modality=true2023.1155.51—34.17—————
MH-DETRFeat.=VGG, Protocol=S2@202023.0855.47—32.41—————
MomentDiffType=SF+C, Glove2023.0755.42—32.17—60.9332.4732.59—
CG-DETRBackbone=VGG2024.1255.22—34.19—————
CG-DETRBackbone=VGG, Audio modality=false2023.1155.2—34.2—————
UVCOMFeatures=VGG/GloVe2024.1254.57—34.13—————
UVCOMaudio modality=false2023.1154.57—34.13—————
FlashVTGFeatures=VGG/GloVe2024.1254.25—37.42—————
FlashVTGBackbone=VGG2024.1254.25—37.42—————
MomentDiffType=C3D, Glove2023.0753.79—30.18—59.3229.8531.89—
M-DETRFeatures=SlowFast/CLIP2024.1253.63—31.37—————
Moment-DETR2021.0753.63—31.37—————
M-DETRfeat=SF+C, Source Modality=Video2023.0353.63—31.37—————
M-DETRFeatures=SlowFast + CLIP2023.1153.63—31.37—————
M-DETRFeat.=SF+C, Protocol=S2@202023.0853.63—31.37—————
TR-DETRFeatures=VGG/GloVe2024.1253.47—30.81—————
TR-DETRBackbone=VGG2024.1253.47—30.81—————
TaskWeaveBackbone=I3D2024.0453.36—31.4—————
MomentDETRType=SF+C, C, re-implemented=true2023.0753.22—30.87—58.8626.4330.43—
QD-DETRBackbone=VGG, Audio modality=false2023.1152.8—31.1—————
QD-DETRFeatures=VGG/GloVe2024.1252.77—31.13—————
QD-DETRfeat=VGG, Source Modality=Video2023.0352.77—31.13—————
QD-DETRaudio modality=false2023.1152.77—31.13—————
QD-DETRFeat.=VGG, Protocol=S2@202023.0852.77—31.13—————
QD-DETRBackbone=VGG2024.0452.77—31.13—————
QD-DETRBackbone=VGG2024.1252.77—31.13—————
MomentDiffType=VGG+A, Glove, audio data=true2023.0752.62—29.93—60.6929.7431.81—
M-DETRBackbone=Slowfast and CLIP2023.1152.165.830.645.5————
Moment-DETRFeature Extractors=CLIP-B/322024.0352.0765.8330.5945.54————
Moment-DETRyear=2021, venue=NIPS2024.1252.0765.8330.5945.54————
Moment-DETRBackbone=SlowFast R-50 + CLIP-B/322024.1252.07—30.59—————
MomentDiffType=VGG, Glove2023.0751.94—28.25—59.8629.1131.66—
QD-DETRfeat=C3D, Source Modality=Video2023.0350.67—31.02—————
QD-DETRBackbone=I3D2024.0450.67—31.02—————
MomentDETRType=VGG, Glove, re-implemented=true2023.0750.54—28.01—57.3925.6229.87—
MomentDETRType=C3D, Glove, re-implemented=true2023.0750.49—29.95—56.2726.0829.92—
IVG-DCL2021.0750.24—32.88—————
IVG-DCLFeat.=SF+C, Protocol=S2@202023.0850.24—32.88—————
TFVTG(GPT-4T)Fine-tuning=true2025.0149.9——44.5————
UMTFeat.=VGG+Opti., Protocol=S2@202023.0849.35—26.16—————
VSLNetType=C3D, Glove, re-implemented=true2023.0748.67—30.33—56.8825.7930.16—
UMTType=VGG+A, Glove, audio data=true2023.0748.44—29.76—58.0327.4630.37—
UMTfeat=VGG, Source Modality=Video + Audio2023.0348.31—29.25—————
UMTaudio modality=true2023.1148.31—29.25—————
UMTBackbone=VGG, Audio modality=true2024.0448.31—29.25—————
UMT+Backbone=VGG, Audio features=true2024.1248.31—29.25—————
UMTBackbone=VGG, Audio modality=true2023.1148.3—29.3—————
CBLNType=VGG, Glove2023.0747.94—28.22—————
DCMType=VGG, Glove2023.0747.8—28—————
VSLNet2021.0747.31—30.19—————
VSLNetfeat=C3D, Source Modality=Video2023.0347.31—30.19—————
CALFeat.=SF+C, Protocol=S2@202023.0847.31—30.19—————
VSLNetFeat.=SF+C, Protocol=S2@202023.0847.31—30.19—————
VSLNetBackbone=I3D2024.0447.31—30.19—————
MMNType=VGG, Glove, re-implemented=true2023.0746.93—27.07—58.8528.1631.58—
SSRNBackbone=VGG, Audio modality=false2023.1146.7—28—————
MANfeat=C3D, Source Modality=Video2023.0346.53—22.72—————
MANBackbone=I3D2024.0446.53—22.72—————
2D-TANFeatures=SlowFast/CLIP2024.1246.02—27.5—————
2D TANFeatures=SlowFast + CLIP2023.1146.02—27.5—————