List your company

Video Object Segmentation on YouTube-VOS (val)

79.7J Score (Seen)STM
8.87627.26345.6564.037Dec 12, 2018Dec 12, 2019Dec 11, 2020Dec 11, 2021Dec 11, 2022Dec 11, 2023Dec 10, 2024

Evaluation results

MethodLinks
STM2019.0479.772.884.280.979.4————
Official STMExtra data=true, OL (Online learning)=false, FPS=6.32020.1079.784.272.880.9—79.4———
STMFT=false, PP=false2020.1279.772.884.280.979.4————
PTSNetOnline Fine-tuning=true2019.0773.564.3———71.6———
STG-Netonline learning=false, FPS=62020.1272.769.175.274.9—73———
STM-cycle+GCExtra data=true, OL (Online learning)=true, FPS=13.82020.1072.262.876.371.9—70.8———
STM-cycleExtra data=false, OL (Online learning)=false, FPS=432020.1071.761.475.870.4—69.9———
e-OSVOS-50-OnAFT=true, PP=false2020.1271.774.36673.871.4————
BoLTVOS2019.0471.664.3——71.1————
PreMVOS2019.0471.456.575.963.766.9————
PREMVOSFT=true, PP=false, ensemble=true2020.1271.456.575.963.766.9————
AGSS-VOSExtra data=true, OL (Online learning)=false, FPS=12.52020.1071.365.575.273.1—71.3———
AGSSonline learning=false, FPS=122020.1271.365.575.273.1—71.3———
S2SOnline Fine-tuning=true2019.077155.5———64.4———
S2S2019.047155.57061.264.4————
S2SOnline Learning=true, Backbone=ResNet-502019.097155.57061.2—64.4———
S2SExtra data=false, OL (Online learning)=true, FPS=0.062020.107155.57061.2—64.4———
S2SFT=false, PP=false2020.127155.57061.264.4————
S2Sonline learning=true, FPS=0.12020.127155.57061.2—64.4———
PTSNetOnline Fine-tuning=false2019.0769.153.5———63.2———
A-GAME2019.0467.860.8——66.1————
A-GAMEFT=false, PP=false2020.1267.860.8——66.1————
CapsuleVOSOnline Learning=No, Speed (frames/s)=13.52019.0967.353.768.159.962.3————
AGAMEonline learning=false2020.1266.961.2———66———
S2SOnline Fine-tuning=false2019.0766.748.2———57.6———
S2S (offline)Online Learning=No, Speed (frames/s)=6.252019.0966.748.265.550.357.6————
S2SOnline Learning=false, Backbone=ResNet-502019.0966.748.265.550.3—57.76——
S2SExtra data=false, OL (Online learning)=false, FPS=62020.1066.748.265.550.3—57.6———
S2Sonline learning=false, FPS=62020.1266.748.265.550.3—57.7———
RVOS2019.0463.645.567.25156.8————
RVOSOnline Learning=false, Backbone=ResNet-502019.0963.645.567.251—56.824——
RVOSExtra data=false, OL (Online learning)=false, FPS=242020.1063.645.567.251—56.8———
RVOSFT=false, PP=false2020.1263.645.567.25156.8————
RVOSonline learning=false, FPS=242020.1263.645.567.251—56.8———
DMM-Net+Online Learning=true, Backbone=ResNet-1012019.0960.350.663.557.4—58———
DMM-NetExtra data=true, OL (Online learning)=true2020.1060.350.663.557.4—58———
DMMonline learning=true2020.1260.350.663.557.4—58———
SiamMaskFine-tuning=false, Mask initialization=false, Speed (fps)=552018.1260.245.158.247.752.8————
SiamMaskOnline Learning=false, Backbone=ResNet-502019.0960.245.158.247.7—52.855——
SiamMaskonline learning=false, FPS=552020.1260.245.158.247.7—52.8———
OnAVOSFine-tuning=true, Mask initialization=true, Speed (fps)=0.12018.1260.146.662.751.455.2————
OnAVOSOnline Fine-tuning=true2019.0760.146.6———55.2———
OnAVOS2019.0460.146.662.751.455.2————
OnAVOSOnline Learning=true, Backbone=ResNet-502019.0960.146.662.751.4—55.2———
OnAVOSExtra data=true, OL (Online learning)=true, FPS=0.052020.1060.146.662.751.4—55.2———
OnAVOSFT=true, PP=true2020.1260.146.662.751.455.2————
OnAVOSonline learning=true, FPS=0.12020.1260.146.662.751.4—55.2———
OSMNFine-tuning=false, Mask initialization=true, Speed (fps)=8.02018.126040.660.14451.2————
OSMNOnline Fine-tuning=false2019.076040.6———51.2———
OSMN2019.046040.660.14451.2————
OSMNOnline Learning=No, Speed (frames/s)=7.142019.096040.660.14451.2————
OSMNOnline Learning=false, Backbone=ResNet-502019.096040.660.144—51.28——
OSMNFT=false, PP=false2020.126040.660.14451.2————
OSMNonline learning=false, FPS=82020.126040.660.144—51.2———
MaskTrackOnline Fine-tuning=false2019.0759.945———53.1———
MSK2019.0459.94559.547.953.1————
MaskTrackExtra data=true, OL (Online learning)=true, FPS=0.052020.1059.94559.547.9—53.1———
MSKFT=false, PP=false2020.1259.94559.547.953.1————
OSVOSFine-tuning=true, Mask initialization=true, Speed (fps)=0.12018.1259.854.260.560.758.8————
OSVOSOnline Fine-tuning=true2019.0759.854.2———58.8———
OSVOS2019.0459.854.260.560.758.8————
OSVOSOnline Learning=Yes, Speed (frames/s)=0.102019.0959.854.260.560.758.8————
OSVOSOnline Learning=true, Backbone=ResNet-502019.0959.854.260.560.7—58.8———
OSVOSExtra data=true, OL (Online learning)=true2020.1059.854.260.560.7—58.8———
OSVOSFT=true, PP=true2020.1259.854.260.560.758.8————
OSVOSonline learning=true, FPS=0.12020.1259.854.260.560.7—58.8———
RGMPOnline Fine-tuning=false2019.0759.545.2———53.8———
RGMP2019.0459.545.2——53.8————
RGMPOnline Learning=false, Backbone=ResNet-502019.0959.5—45.2——53.87——
RGMPExtra data=true, OL (Online learning)=false, FPS=72020.1059.5—45.2——53.8———
RGMPFT=false, PP=false2020.1259.545.2——53.8————
RGMPonline learning=false, FPS=72020.1259.5————53.8———
DMM-NetOnline Learning=false, Backbone=ResNet-502019.0959.247.662.653.9—55.8———
DMM-Net+Online Learning=false, Backbone=ResNet-1012019.0958.341.660.746.3—51.712——
DMM-NetExtra data=true, OL (Online learning)=false, FPS=122020.1058.341.660.746.3—51.7———
DMMonline learning=false, FPS=122020.1258.341.660.746.3—51.7———
XuAnnotation Percentage=100%, Supervised=true2024.1255.739.655.241.347.9————
Stable Mean TeacherAnnotation Percentage=10%2024.1248.23546.735.441.3————
Stable Mean TeacherAnnotation Percentage=5%2024.1245.33243.232.238.2————
Kumar et al.Annotation Percentage=10%2024.1243.131.440.831.836.8————
XuAnnotation Percentage=10%, Supervised=true2024.1211.610.19.69.210.1————
ColorizationEvaluation protocol=one-shot/semi-supervised, Training supervision=self-supervised, Inference mask provision=first-frame mask only2026.07—————37—37.436.6
CorrFlow2026.07————48.950.2—51.5—
CorrFlowEvaluation protocol=one-shot/semi-supervised, Training supervision=self-supervised, Inference mask provision=first-frame mask only2026.07—————44.7—45.643.8
CTC²2026.07————56.357—57.7—
CTC²Evaluation protocol=one-shot/semi-supervised, Training supervision=self-supervised, Inference mask provision=first-frame mask only2026.07—————62.4—65.759.1
MASTEvaluation protocol=one-shot/semi-supervised, Training supervision=self-supervised, Inference mask provision=first-frame mask only2026.07—————64—67.760.3
MSK2026.07————51.852.8—53.8—
OSMN2026.07————48.551.2—53.9—
OSVOSEvaluation protocol=one-shot/semi-supervised, Training supervision=self-supervised, Inference mask provision=first-frame mask only2026.07—————57.4—60.754.2
RGMP2026.07————53.953.8—53.7—
Video Colorization2026.07————31.432.9—34.5—