Video Object Segmentation on SegTrack v2
88.4Jaccard IndexSUMO-L
Evaluation results
| Method | Links | |||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| SUMO-LSource=Ours2026.06 | 88.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SUMO-BSource=Ours2026.06 | 86.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SUMO-SSource=Ours2026.06 | 84.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| RCF-AllSource=CVPR’232026.06 | 79.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| STG-NetOnline learning=false2020.12 | 79.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DMMOnline learning=false2020.12 | 76.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| RCF-Stage1Source=CVPR’232026.06 | 76.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ABRSource=ECCV’242026.06 | 76.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Huang et al.Source=CVPR’252026.06 | 76.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| OCLR (test. adap.)HA=false, Sup.=Syn., RGB=true, Flow=true2022.07 | 72.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| OCLR-TTASource=NIPS’222026.06 | 72.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| RGMPOnline learning=false2020.12 | 71.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MOD (test-time adaptation)Human Annotation=false, Supervision=None, RGB Inference=true, Flow Inference=false2022.10 | 69.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| OCLRHuman Annotation=false, Supervision=Synthetic, RGB Inference=false, Flow Inference=true2022.10 | 67.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| OCLR (flow-only)HA=false, Sup.=Syn., RGB=false, Flow=true2022.07 | 67.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| OCLR-flowSource=NIPS’222026.06 | 67.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| NLCHuman Annotation=false, Supervision=None, RGB Inference=true, Flow Inference=true2022.10 | 67.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| NLCHA=false, Sup.=None, RGB=true, Flow=true2022.07 | 67.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| OSVOSOnline learning=true2020.12 | 65.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CISHuman Annotation=false, Supervision=None, RGB Inference=true, Flow Inference=true2022.10 | 62.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MOD (w/o post-processing)Human Annotation=false, Supervision=None, RGB Inference=true, Flow Inference=false2022.10 | 62.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SIMOHuman Annotation=false, Supervision=None, RGB Inference=false, Flow Inference=true2022.10 | 62 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CIS (w. post-process.)HA=false, Sup.=None, RGB=true, Flow=true2022.07 | 62 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SIMOHA=false, Sup.=Syn., RGB=false, Flow=true2022.07 | 62 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CISSource=CVPR’192026.06 | 62 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| FSEGHuman Annotation=true, Supervision=Ground Truth, RGB Inference=true, Flow Inference=true2022.10 | 61.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| FSEGHA=true, Sup.=Real, RGB=true, Flow=true2022.07 | 61.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MGHuman Annotation=false, Supervision=None, RGB Inference=false, Flow Inference=true2022.10 | 58.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Motion GroupingHA=false, Sup.=None, RGB=false, Flow=true2022.07 | 58.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SAGEHuman Annotation=false, Supervision=None, RGB Inference=true, Flow Inference=true2022.10 | 57.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SAGEHA=false, Sup.=None, RGB=true, Flow=true2022.07 | 57.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| LVOHA=true, Sup.=Real, RGB=true, Flow=true2022.07 | 57.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ARPHA=true, Sup.=Real, RGB=true, Flow=true2022.07 | 57.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| AMDHuman Annotation=false, Supervision=None, RGB Inference=true, Flow Inference=false2022.10 | 57 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| EMSource=PAMI’232026.06 | 55.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CUTHA=false, Sup.=None, RGB=true, Flow=true2022.07 | 54.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MATNetHuman Annotation=true, Supervision=Ground Truth, RGB Inference=true, Flow Inference=true2022.10 | 50.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MATNetHA=true, Sup.=Real, RGB=true, Flow=true2022.07 | 50.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| COSNetHuman Annotation=true, Supervision=Ground Truth, RGB Inference=true, Flow Inference=false2022.10 | 49.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| COSNetHA=true, Sup.=Real, RGB=true, Flow=false2022.07 | 49.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| FTSHA=false, Sup.=None, RGB=true, Flow=true2022.07 | 47.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CISHA=false, Sup.=None, RGB=true, Flow=true2022.07 | 45.6 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ABRMotion=Optical Flow, Appearance=DINO2025.03 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 76.6 | |
| ABR2025.12 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 76.6 | |
| ARPTraining Source=input video only2022.04 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 57.2 | |
| ARPTraining=Supervised Features, Input=Image & Flow2022.01 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 57.2 | |
| CISTraining Source=input video only2022.04 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 62 | |
| CISMotion=Optical Flow, Appearance=RGB2025.03 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 62 | |
| CIS2025.12 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 62 | |
| CIS - No PostTraining=Fully Unsupervised, Input=Image & Flow2022.01 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 45.6 | |
| CIS - With PostTraining=Fully Unsupervised, Input=Image & Flow2022.01 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 62 | |
| ConvGRU2017.04 | — | 0.573 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CUT2017.04 | — | 0.478 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Deformable SpritesTraining Source=input video only2022.04 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 72.1 | |
| DMM-NetOnline Learning=false2019.09 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 76.8 | 76.7 | — | |
| DyeNetOnline Learning=false2019.09 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 78.3 | — | |
| DyeNetOnline Learning=true2019.09 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 78.7 | — | |
| Dynapo2025.12 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 83.3 | |
| DyStab - DynTraining=Supervised Features, Input=Flow2022.01 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 40 | |
| DyStab - Stat&DynTraining=Supervised Features, Input=Image & Flow2022.01 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 73.2 | |
| DyStaB*Training Source=video dataset2022.04 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 74.2 | |
| Efficient 3D CNN (Ours)learning_mode=unsupervised2019.07 | — | 62.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| EMMotion=Optical Flow, Appearance=None2025.03 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 55.5 | |
| EM2025.12 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 55.5 | |
| EM-driven networkTraining=Fully Unsupervised, Input=Flow2022.01 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 55.5 | |
| EpO2019.09 | — | 68.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| EpO+2019.09 | — | 70.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| EpO+sequence_exclusion=without birdfall2019.09 | — | 72.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| FSEGlearning_mode=unsupervised2019.07 | — | 61.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| FSG2018.09 | — | 61.4 | 38 | 69.9 | 59.1 | 59.6 | 87.6 | 57 | 66.7 | 65.2 | 80.5 | 32.8 | 51.6 | 71.3 | 69.8 | 50.6 | — | — | — | |
| FSG2019.09 | — | 61.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| FST2017.04 | — | 0.543 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| FST2018.09 | — | 52.7 | 1.4 | 83.7 | 62.1 | 39.6 | 81.1 | 62.9 | 44.1 | 33.5 | 69.9 | 52.3 | 83.9 | 7.4 | 45.3 | 70.5 | — | — | — | |
| FSTlearning_mode=unsupervised2019.07 | — | 53.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| FTSTraining=Fully Unsupervised, Input=Flow2022.01 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 47.8 | |
| KEY2018.09 | — | 57.3 | 49 | 92.2 | 63 | 28.1 | 46.9 | 0 | 87.7 | 60.2 | 79 | 39.6 | 96.3 | 9.3 | 66.6 | 84.4 | — | — | — | |
| KEYlearning_mode=unsupervised2019.07 | — | 57.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| KEY2019.09 | — | 57.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| LRTR2025.12 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 81.2 | |
| LSMOlearning_mode=unsupervised2019.07 | — | 53.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| LSMO2019.09 | — | 59.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| LucidTrackerOnline Learning=false2019.09 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 77.6 | — | |
| LVO2019.09 | — | 57.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MaskRNNOnline Learning=false2019.09 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 72.1 | — | — | |
| MGTraining Source=input video only2022.04 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 58.2 | |
| MoSegTraining=Fully Unsupervised, Input=Flow2022.01 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 58.6 | |
| Motion Saliency-Guided Spatio-Temporal Propagation2018.09 | — | 70.1 | 64.9 | 93.7 | 84.7 | 51.8 | 82.9 | 83.2 | 84.6 | 46.4 | 73.9 | 38.1 | 93.7 | 24 | 80 | 80 | — | — | — | |
| MSKOnline Learning=true2019.09 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 67.4 | 70.3 | — | |
| NLC2017.04 | — | 0.672 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| NLC2018.09 | — | 67.2 | 56.5 | 81.4 | 75.4 | 51.8 | 74.1 | 71.3 | 86 | 62.4 | 82.3 | 52.5 | 85.9 | 13.9 | 69.2 | 78.2 | — | — | — | |
| NLC2019.09 | — | 67.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| OCLR-flowMotion=Optical Flow, Appearance=None2025.03 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 67.6 | |
| OCLR-flowvariant=flow2025.12 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 67.6 | |
| OCLR-TTAMotion=Optical Flow, Appearance=RGB2025.03 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 72.3 | |
| OCLR-TTAvariant=test-time adaptation2025.12 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 72.3 | |
| OFLOnline Learning=true2019.09 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 67.5 | — | — | |
| OSVOSOnline Learning=true2019.09 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 61.9 | 65.4 | — | |
| RCF-AllMotion=Optical Flow, Appearance=DINO2025.03 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 79.6 | |
| RCF-Alltraining_stage=All2025.12 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 79.6 | |
| RCF-Stage1Motion=Optical Flow, Appearance=None2025.03 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 76.7 |