TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/PDB

PDB

Reported on 282 benchmarks across 8 tasks

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision158 results

  • VideoonDAVIS 2017 (test-dev)
    F-measure (Decay)
    3.7
    best: 37.2 (RGMP)
  • VideoonDAVIS 2017 (test-dev)
    F-measure (Mean)
    43
    best: 91.4 (Cutie+ (base, MEGA))
  • VideoonDAVIS 2017 (test-dev)
    F-measure (Recall)
    44.6
    best: 89.7 (STCN)
  • VideoonDAVIS 2017 (test-dev)
    J&F
    40.4
    best: 88.1 (Cutie+ (base, MEGA))
  • VideoonDAVIS 2017 (test-dev)
    Jaccard (Decay)
    4
    best: 35.7 (RVOS)
  • VideoonDAVIS 2017 (test-dev)
    Jaccard (Mean)
    37.7
    best: 84.7 (Cutie+ (base, MEGA))
  • VideoonDAVIS 2017 (test-dev)
    Jaccard (Recall)
    42.6
    best: 85.5 (STCN)
  • VideoonDAVIS 2016 val
    F
    74.5
    best: 90.2 (DEVA (DIS))
  • VideoonDAVIS 2016 val
    G
    75.9
    best: 88.9 (GSANet)
  • VideoonDAVIS 2016 val
    J
    77.2
    best: 88.3 (GSANet)
  • VideoonYouTube-Objects
    J
    65.5
    best: 75.1 (FakeFlow)
  • VideoonDAVIS 2017 (val)
    F-measure (Mean)
    57
    best: 93.4 (Cutie+ (base))
  • VideoonDAVIS 2017 (val)
    F-measure (Recall)
    60.2
    best: 94.6 (STCN)
  • VideoonDAVIS 2017 (val)
    J&F
    55.1
    best: 90.7 (SAM2)
  • VideoonDAVIS 2017 (val)
    Jaccard (Mean)
    53.2
    best: 87.5 (Cutie+ (base))
  • VideoonDAVIS 2017 (val)
    Jaccard (Recall)
    58.9
    best: 91.4 (ISVOS (MS))
  • VideoonFBMS test
    J
    74
    best: 84.7 (FakeFlow)
  • VideoonDAVSOD-easy35
    Average MAE· uses extra data
    0.114
    best: 0.066 (RealFlow)
  • VideoonDAVSOD-easy35
    S-Measure· uses extra data
    0.706
    best: 0.803 (RealFlow)
  • VideoonDAVSOD-easy35
    max E-Measure· uses extra data
    0.749
    best: 0.806 (SSAV)
  • VideoonDAVSOD-easy35
    max F-Measure· uses extra data
    0.591
    best: 0.732 (RealFlow)
  • VideoonFBMS-59
    AVERAGE MAE· uses extra data
    0.064
    best: 0.028 (RealFlow)
  • VideoonFBMS-59
    MAX F-MEASURE· uses extra data
    0.821
    best: 0.906 (RealFlow)
  • VideoonFBMS-59
    S-Measure· uses extra data
    0.851
    best: 0.926 (RealFlow)
  • VideoonUVSD
    Average MAE· uses extra data
    0.018
  • VideoonUVSD
    S-Measure· uses extra data
    0.901
  • VideoonUVSD
    max E-measure· uses extra data
    0.975
  • VideoonVOS-T
    Average MAE· uses extra data
    0.078
    best: 0.049 (RCRNet+NER)
  • VideoonVOS-T
    S-Measure· uses extra data
    0.818
    best: 0.872 (RCRNet+NER)
  • VideoonVOS-T
    max E-measure· uses extra data
    0.837
    best: 0.856 (RCRNet+NER)
  • VideoonSegTrack v2
    AVERAGE MAE· uses extra data
    0.024
    best: 0.022 (UFO)
  • VideoonSegTrack v2
    S-Measure· uses extra data
    0.864
    best: 0.892 (UFO)
  • VideoonSegTrack v2
    max E-measure· uses extra data
    0.935
  • VideoonDAVSOD-Difficult20
    Average MAE· uses extra data
    0.107
  • VideoonDAVSOD-Difficult20
    S-Measure· uses extra data
    0.608
    best: 0.619 (SSAV)
  • VideoonDAVSOD-Difficult20
    max E-measure· uses extra data
    0.678
    best: 0.698 (FGRN)
  • VideoonDAVIS-2016
    AVERAGE MAE· uses extra data
    0.028
    best: 0.01 (RealFlow)
  • VideoonDAVIS-2016
    MAX E-MEASURE· uses extra data
    0.951
    best: 0.966 (MBNM)
  • VideoonDAVIS-2016
    S-Measure· uses extra data
    0.882
    best: 0.945 (RealFlow)
  • VideoonViSal
    Average MAE· uses extra data
    0.032
    best: 0.01 (RealFlow)
  • VideoonViSal
    S-Measure· uses extra data
    0.907
    best: 0.962 (RealFlow)
  • VideoonViSal
    max E-measure· uses extra data
    0.846
    best: 0.987 (UFO)
  • VideoonDAVSOD-Normal25
    Average MAE· uses extra data
    0.132
    best: 0.117 (SSAV)
  • VideoonDAVSOD-Normal25
    S-Measure· uses extra data
    0.649
    best: 0.661 (SSAV)
  • VideoonDAVSOD-Normal25
    max E-measure· uses extra data
    0.698
    best: 0.723 (SSAV)
  • VideoonMCL
    AVERAGE MAE
    0.021
  • VideoonMCL
    MAX E-MEASURE
    0.911
  • VideoonMCL
    S-Measure
    0.856
  • Object DetectiononDAVSOD-easy35
    Average MAE· uses extra data
    0.114
    best: 0.066 (RealFlow)
  • Object DetectiononDAVSOD-easy35
    S-Measure· uses extra data
    0.706
    best: 0.803 (RealFlow)
  • Object DetectiononDAVSOD-easy35
    max E-Measure· uses extra data
    0.749
    best: 0.806 (SSAV)
  • Object DetectiononDAVSOD-easy35
    max F-Measure· uses extra data
    0.591
    best: 0.732 (RealFlow)
  • Object DetectiononFBMS-59
    AVERAGE MAE· uses extra data
    0.064
    best: 0.028 (RealFlow)
  • Object DetectiononFBMS-59
    MAX F-MEASURE· uses extra data
    0.821
    best: 0.906 (RealFlow)
  • Object DetectiononFBMS-59
    S-Measure· uses extra data
    0.851
    best: 0.926 (RealFlow)
  • Object DetectiononUVSD
    Average MAE· uses extra data
    0.018
  • Object DetectiononUVSD
    S-Measure· uses extra data
    0.901
  • Object DetectiononUVSD
    max E-measure· uses extra data
    0.975
  • Object DetectiononVOS-T
    Average MAE· uses extra data
    0.078
    best: 0.049 (RCRNet+NER)
  • Object DetectiononVOS-T
    S-Measure· uses extra data
    0.818
    best: 0.872 (RCRNet+NER)
  • Object DetectiononVOS-T
    max E-measure· uses extra data
    0.837
    best: 0.856 (RCRNet+NER)
  • Object DetectiononSegTrack v2
    AVERAGE MAE· uses extra data
    0.024
    best: 0.022 (UFO)
  • Object DetectiononSegTrack v2
    S-Measure· uses extra data
    0.864
    best: 0.892 (UFO)
  • Object DetectiononSegTrack v2
    max E-measure· uses extra data
    0.935
  • Object DetectiononDAVSOD-Difficult20
    Average MAE· uses extra data
    0.107
  • Object DetectiononDAVSOD-Difficult20
    S-Measure· uses extra data
    0.608
    best: 0.619 (SSAV)
  • Object DetectiononDAVSOD-Difficult20
    max E-measure· uses extra data
    0.678
    best: 0.698 (FGRN)
  • Object DetectiononDAVIS-2016
    AVERAGE MAE· uses extra data
    0.028
    best: 0.01 (RealFlow)
  • Object DetectiononDAVIS-2016
    MAX E-MEASURE· uses extra data
    0.951
    best: 0.966 (MBNM)
  • Object DetectiononDAVIS-2016
    S-Measure· uses extra data
    0.882
    best: 0.945 (RealFlow)
  • Object DetectiononViSal
    Average MAE· uses extra data
    0.032
    best: 0.01 (RealFlow)
  • Object DetectiononViSal
    S-Measure· uses extra data
    0.907
    best: 0.962 (RealFlow)
  • Object DetectiononViSal
    max E-measure· uses extra data
    0.846
    best: 0.987 (UFO)
  • Object DetectiononDAVSOD-Normal25
    Average MAE· uses extra data
    0.132
    best: 0.117 (SSAV)
  • Object DetectiononDAVSOD-Normal25
    S-Measure· uses extra data
    0.649
    best: 0.661 (SSAV)
  • Object DetectiononDAVSOD-Normal25
    max E-measure· uses extra data
    0.698
    best: 0.723 (SSAV)
  • Object DetectiononMCL
    AVERAGE MAE
    0.021
  • Object DetectiononMCL
    MAX E-MEASURE
    0.911
  • Object DetectiononMCL
    S-Measure
    0.856
  • Video Object SegmentationonDAVIS 2017 (test-dev)
    F-measure (Decay)
    3.7
    best: 37.2 (RGMP)
  • Video Object SegmentationonDAVIS 2017 (test-dev)
    F-measure (Mean)
    43
    best: 91.4 (Cutie+ (base, MEGA))
  • Video Object SegmentationonDAVIS 2017 (test-dev)
    F-measure (Recall)
    44.6
    best: 89.7 (STCN)
  • Video Object SegmentationonDAVIS 2017 (test-dev)
    J&F
    40.4
    best: 88.1 (Cutie+ (base, MEGA))
  • Video Object SegmentationonDAVIS 2017 (test-dev)
    Jaccard (Decay)
    4
    best: 35.7 (RVOS)
  • Video Object SegmentationonDAVIS 2017 (test-dev)
    Jaccard (Mean)
    37.7
    best: 84.7 (Cutie+ (base, MEGA))
  • Video Object SegmentationonDAVIS 2017 (test-dev)
    Jaccard (Recall)
    42.6
    best: 85.5 (STCN)
  • Video Object SegmentationonDAVIS 2016 val
    F
    74.5
    best: 90.2 (DEVA (DIS))
  • Video Object SegmentationonDAVIS 2016 val
    G
    75.9
    best: 88.9 (GSANet)
  • Video Object SegmentationonDAVIS 2016 val
    J
    77.2
    best: 88.3 (GSANet)
  • Video Object SegmentationonYouTube-Objects
    J
    65.5
    best: 75.1 (FakeFlow)
  • Video Object SegmentationonDAVIS 2017 (val)
    F-measure (Mean)
    57
    best: 93.4 (Cutie+ (base))
  • Video Object SegmentationonDAVIS 2017 (val)
    F-measure (Recall)
    60.2
    best: 94.6 (STCN)
  • Video Object SegmentationonDAVIS 2017 (val)
    J&F
    55.1
    best: 90.7 (SAM2)
  • Video Object SegmentationonDAVIS 2017 (val)
    Jaccard (Mean)
    53.2
    best: 87.5 (Cutie+ (base))
  • Video Object SegmentationonDAVIS 2017 (val)
    Jaccard (Recall)
    58.9
    best: 91.4 (ISVOS (MS))
  • Video Object SegmentationonFBMS test
    J
    74
    best: 84.7 (FakeFlow)
  • Video Object SegmentationonDAVSOD-easy35
    Average MAE· uses extra data
    0.114
    best: 0.066 (RealFlow)
  • Video Object SegmentationonDAVSOD-easy35
    S-Measure· uses extra data
    0.706
    best: 0.803 (RealFlow)
  • Video Object SegmentationonDAVSOD-easy35
    max E-Measure· uses extra data
    0.749
    best: 0.806 (SSAV)
  • Video Object SegmentationonDAVSOD-easy35
    max F-Measure· uses extra data
    0.591
    best: 0.732 (RealFlow)
  • Video Object SegmentationonFBMS-59
    AVERAGE MAE· uses extra data
    0.064
    best: 0.028 (RealFlow)
  • Video Object SegmentationonFBMS-59
    MAX F-MEASURE· uses extra data
    0.821
    best: 0.906 (RealFlow)
  • Video Object SegmentationonFBMS-59
    S-Measure· uses extra data
    0.851
    best: 0.926 (RealFlow)
  • Video Object SegmentationonUVSD
    Average MAE· uses extra data
    0.018
  • Video Object SegmentationonUVSD
    S-Measure· uses extra data
    0.901
  • Video Object SegmentationonUVSD
    max E-measure· uses extra data
    0.975
  • Video Object SegmentationonVOS-T
    Average MAE· uses extra data
    0.078
    best: 0.049 (RCRNet+NER)
  • Video Object SegmentationonVOS-T
    S-Measure· uses extra data
    0.818
    best: 0.872 (RCRNet+NER)
  • Video Object SegmentationonVOS-T
    max E-measure· uses extra data
    0.837
    best: 0.856 (RCRNet+NER)
  • Video Object SegmentationonSegTrack v2
    AVERAGE MAE· uses extra data
    0.024
    best: 0.022 (UFO)
  • Video Object SegmentationonSegTrack v2
    S-Measure· uses extra data
    0.864
    best: 0.892 (UFO)
  • Video Object SegmentationonSegTrack v2
    max E-measure· uses extra data
    0.935
  • Video Object SegmentationonDAVSOD-Difficult20
    Average MAE· uses extra data
    0.107
  • Video Object SegmentationonDAVSOD-Difficult20
    S-Measure· uses extra data
    0.608
    best: 0.619 (SSAV)
  • Video Object SegmentationonDAVSOD-Difficult20
    max E-measure· uses extra data
    0.678
    best: 0.698 (FGRN)
  • Video Object SegmentationonDAVIS-2016
    AVERAGE MAE· uses extra data
    0.028
    best: 0.01 (RealFlow)
  • Video Object SegmentationonDAVIS-2016
    MAX E-MEASURE· uses extra data
    0.951
    best: 0.966 (MBNM)
  • Video Object SegmentationonDAVIS-2016
    S-Measure· uses extra data
    0.882
    best: 0.945 (RealFlow)
  • Video Object SegmentationonViSal
    Average MAE· uses extra data
    0.032
    best: 0.01 (RealFlow)
  • Video Object SegmentationonViSal
    S-Measure· uses extra data
    0.907
    best: 0.962 (RealFlow)
  • Video Object SegmentationonViSal
    max E-measure· uses extra data
    0.846
    best: 0.987 (UFO)
  • Video Object SegmentationonDAVSOD-Normal25
    Average MAE· uses extra data
    0.132
    best: 0.117 (SSAV)
  • Video Object SegmentationonDAVSOD-Normal25
    S-Measure· uses extra data
    0.649
    best: 0.661 (SSAV)
  • Video Object SegmentationonDAVSOD-Normal25
    max E-measure· uses extra data
    0.698
    best: 0.723 (SSAV)
  • Video Object SegmentationonMCL
    AVERAGE MAE
    0.021
  • Video Object SegmentationonMCL
    MAX E-MEASURE
    0.911
  • Video Object SegmentationonMCL
    S-Measure
    0.856
  • RGB Salient Object DetectiononDAVSOD-easy35
    Average MAE· uses extra data
    0.114
    best: 0.066 (RealFlow)
  • RGB Salient Object DetectiononDAVSOD-easy35
    S-Measure· uses extra data
    0.706
    best: 0.803 (RealFlow)
  • RGB Salient Object DetectiononDAVSOD-easy35
    max E-Measure· uses extra data
    0.749
    best: 0.806 (SSAV)
  • RGB Salient Object DetectiononDAVSOD-easy35
    max F-Measure· uses extra data
    0.591
    best: 0.732 (RealFlow)
  • RGB Salient Object DetectiononFBMS-59
    AVERAGE MAE· uses extra data
    0.064
    best: 0.028 (RealFlow)
  • RGB Salient Object DetectiononFBMS-59
    MAX F-MEASURE· uses extra data
    0.821
    best: 0.906 (RealFlow)
  • RGB Salient Object DetectiononFBMS-59
    S-Measure· uses extra data
    0.851
    best: 0.926 (RealFlow)
  • RGB Salient Object DetectiononUVSD
    Average MAE· uses extra data
    0.018
  • RGB Salient Object DetectiononUVSD
    S-Measure· uses extra data
    0.901
  • RGB Salient Object DetectiononUVSD
    max E-measure· uses extra data
    0.975
  • RGB Salient Object DetectiononVOS-T
    Average MAE· uses extra data
    0.078
    best: 0.049 (RCRNet+NER)
  • RGB Salient Object DetectiononVOS-T
    S-Measure· uses extra data
    0.818
    best: 0.872 (RCRNet+NER)
  • RGB Salient Object DetectiononVOS-T
    max E-measure· uses extra data
    0.837
    best: 0.856 (RCRNet+NER)
  • RGB Salient Object DetectiononSegTrack v2
    AVERAGE MAE· uses extra data
    0.024
    best: 0.022 (UFO)
  • RGB Salient Object DetectiononSegTrack v2
    S-Measure· uses extra data
    0.864
    best: 0.892 (UFO)
  • RGB Salient Object DetectiononSegTrack v2
    max E-measure· uses extra data
    0.935
  • RGB Salient Object DetectiononDAVSOD-Difficult20
    Average MAE· uses extra data
    0.107
  • RGB Salient Object DetectiononDAVSOD-Difficult20
    S-Measure· uses extra data
    0.608
    best: 0.619 (SSAV)
  • RGB Salient Object DetectiononDAVSOD-Difficult20
    max E-measure· uses extra data
    0.678
    best: 0.698 (FGRN)
  • RGB Salient Object DetectiononDAVIS-2016
    AVERAGE MAE· uses extra data
    0.028
    best: 0.01 (RealFlow)
  • RGB Salient Object DetectiononDAVIS-2016
    MAX E-MEASURE· uses extra data
    0.951
    best: 0.966 (MBNM)
  • RGB Salient Object DetectiononDAVIS-2016
    S-Measure· uses extra data
    0.882
    best: 0.945 (RealFlow)
  • RGB Salient Object DetectiononViSal
    Average MAE· uses extra data
    0.032
    best: 0.01 (RealFlow)
  • RGB Salient Object DetectiononViSal
    S-Measure· uses extra data
    0.907
    best: 0.962 (RealFlow)
  • RGB Salient Object DetectiononViSal
    max E-measure· uses extra data
    0.846
    best: 0.987 (UFO)
  • RGB Salient Object DetectiononDAVSOD-Normal25
    Average MAE· uses extra data
    0.132
    best: 0.117 (SSAV)
  • RGB Salient Object DetectiononDAVSOD-Normal25
    S-Measure· uses extra data
    0.649
    best: 0.661 (SSAV)
  • RGB Salient Object DetectiononDAVSOD-Normal25
    max E-measure· uses extra data
    0.698
    best: 0.723 (SSAV)
  • RGB Salient Object DetectiononMCL
    AVERAGE MAE
    0.021
  • RGB Salient Object DetectiononMCL
    MAX E-MEASURE
    0.911
  • RGB Salient Object DetectiononMCL
    S-Measure
    0.856

Methodology124 results

  • 3DonDAVSOD-easy35
    Average MAE· uses extra data
    0.114
    best: 0.066 (RealFlow)
  • 3DonDAVSOD-easy35
    S-Measure· uses extra data
    0.706
    best: 0.803 (RealFlow)
  • 3DonDAVSOD-easy35
    max E-Measure· uses extra data
    0.749
    best: 0.806 (SSAV)
  • 3DonDAVSOD-easy35
    max F-Measure· uses extra data
    0.591
    best: 0.732 (RealFlow)
  • 3DonFBMS-59
    AVERAGE MAE· uses extra data
    0.064
    best: 0.028 (RealFlow)
  • 3DonFBMS-59
    MAX F-MEASURE· uses extra data
    0.821
    best: 0.906 (RealFlow)
  • 3DonFBMS-59
    S-Measure· uses extra data
    0.851
    best: 0.926 (RealFlow)
  • 3DonUVSD
    Average MAE· uses extra data
    0.018
  • 3DonUVSD
    S-Measure· uses extra data
    0.901
  • 3DonUVSD
    max E-measure· uses extra data
    0.975
  • 3DonVOS-T
    Average MAE· uses extra data
    0.078
    best: 0.049 (RCRNet+NER)
  • 3DonVOS-T
    S-Measure· uses extra data
    0.818
    best: 0.872 (RCRNet+NER)
  • 3DonVOS-T
    max E-measure· uses extra data
    0.837
    best: 0.856 (RCRNet+NER)
  • 3DonSegTrack v2
    AVERAGE MAE· uses extra data
    0.024
    best: 0.022 (UFO)
  • 3DonSegTrack v2
    S-Measure· uses extra data
    0.864
    best: 0.892 (UFO)
  • 3DonSegTrack v2
    max E-measure· uses extra data
    0.935
  • 3DonDAVSOD-Difficult20
    Average MAE· uses extra data
    0.107
  • 3DonDAVSOD-Difficult20
    S-Measure· uses extra data
    0.608
    best: 0.619 (SSAV)
  • 3DonDAVSOD-Difficult20
    max E-measure· uses extra data
    0.678
    best: 0.698 (FGRN)
  • 3DonDAVIS-2016
    AVERAGE MAE· uses extra data
    0.028
    best: 0.01 (RealFlow)
  • 3DonDAVIS-2016
    MAX E-MEASURE· uses extra data
    0.951
    best: 0.966 (MBNM)
  • 3DonDAVIS-2016
    S-Measure· uses extra data
    0.882
    best: 0.945 (RealFlow)
  • 3DonViSal
    Average MAE· uses extra data
    0.032
    best: 0.01 (RealFlow)
  • 3DonViSal
    S-Measure· uses extra data
    0.907
    best: 0.962 (RealFlow)
  • 3DonViSal
    max E-measure· uses extra data
    0.846
    best: 0.987 (UFO)
  • 3DonDAVSOD-Normal25
    Average MAE· uses extra data
    0.132
    best: 0.117 (SSAV)
  • 3DonDAVSOD-Normal25
    S-Measure· uses extra data
    0.649
    best: 0.661 (SSAV)
  • 3DonDAVSOD-Normal25
    max E-measure· uses extra data
    0.698
    best: 0.723 (SSAV)
  • 3DonMCL
    AVERAGE MAE
    0.021
  • 3DonMCL
    MAX E-MEASURE
    0.911
  • 3DonMCL
    S-Measure
    0.856
  • 2D ClassificationonDAVSOD-easy35
    Average MAE· uses extra data
    0.114
    best: 0.066 (RealFlow)
  • 2D ClassificationonDAVSOD-easy35
    S-Measure· uses extra data
    0.706
    best: 0.803 (RealFlow)
  • 2D ClassificationonDAVSOD-easy35
    max E-Measure· uses extra data
    0.749
    best: 0.806 (SSAV)
  • 2D ClassificationonDAVSOD-easy35
    max F-Measure· uses extra data
    0.591
    best: 0.732 (RealFlow)
  • 2D ClassificationonFBMS-59
    AVERAGE MAE· uses extra data
    0.064
    best: 0.028 (RealFlow)
  • 2D ClassificationonFBMS-59
    MAX F-MEASURE· uses extra data
    0.821
    best: 0.906 (RealFlow)
  • 2D ClassificationonFBMS-59
    S-Measure· uses extra data
    0.851
    best: 0.926 (RealFlow)
  • 2D ClassificationonUVSD
    Average MAE· uses extra data
    0.018
  • 2D ClassificationonUVSD
    S-Measure· uses extra data
    0.901
  • 2D ClassificationonUVSD
    max E-measure· uses extra data
    0.975
  • 2D ClassificationonVOS-T
    Average MAE· uses extra data
    0.078
    best: 0.049 (RCRNet+NER)
  • 2D ClassificationonVOS-T
    S-Measure· uses extra data
    0.818
    best: 0.872 (RCRNet+NER)
  • 2D ClassificationonVOS-T
    max E-measure· uses extra data
    0.837
    best: 0.856 (RCRNet+NER)
  • 2D ClassificationonSegTrack v2
    AVERAGE MAE· uses extra data
    0.024
    best: 0.022 (UFO)
  • 2D ClassificationonSegTrack v2
    S-Measure· uses extra data
    0.864
    best: 0.892 (UFO)
  • 2D ClassificationonSegTrack v2
    max E-measure· uses extra data
    0.935
  • 2D ClassificationonDAVSOD-Difficult20
    Average MAE· uses extra data
    0.107
  • 2D ClassificationonDAVSOD-Difficult20
    S-Measure· uses extra data
    0.608
    best: 0.619 (SSAV)
  • 2D ClassificationonDAVSOD-Difficult20
    max E-measure· uses extra data
    0.678
    best: 0.698 (FGRN)
  • 2D ClassificationonDAVIS-2016
    AVERAGE MAE· uses extra data
    0.028
    best: 0.01 (RealFlow)
  • 2D ClassificationonDAVIS-2016
    MAX E-MEASURE· uses extra data
    0.951
    best: 0.966 (MBNM)
  • 2D ClassificationonDAVIS-2016
    S-Measure· uses extra data
    0.882
    best: 0.945 (RealFlow)
  • 2D ClassificationonViSal
    Average MAE· uses extra data
    0.032
    best: 0.01 (RealFlow)
  • 2D ClassificationonViSal
    S-Measure· uses extra data
    0.907
    best: 0.962 (RealFlow)
  • 2D ClassificationonViSal
    max E-measure· uses extra data
    0.846
    best: 0.987 (UFO)
  • 2D ClassificationonDAVSOD-Normal25
    Average MAE· uses extra data
    0.132
    best: 0.117 (SSAV)
  • 2D ClassificationonDAVSOD-Normal25
    S-Measure· uses extra data
    0.649
    best: 0.661 (SSAV)
  • 2D ClassificationonDAVSOD-Normal25
    max E-measure· uses extra data
    0.698
    best: 0.723 (SSAV)
  • 2D ClassificationonMCL
    AVERAGE MAE
    0.021
  • 2D ClassificationonMCL
    MAX E-MEASURE
    0.911
  • 2D ClassificationonMCL
    S-Measure
    0.856
  • 2D Object DetectiononDAVSOD-easy35
    Average MAE· uses extra data
    0.114
    best: 0.066 (RealFlow)
  • 2D Object DetectiononDAVSOD-easy35
    S-Measure· uses extra data
    0.706
    best: 0.803 (RealFlow)
  • 2D Object DetectiononDAVSOD-easy35
    max E-Measure· uses extra data
    0.749
    best: 0.806 (SSAV)
  • 2D Object DetectiononDAVSOD-easy35
    max F-Measure· uses extra data
    0.591
    best: 0.732 (RealFlow)
  • 2D Object DetectiononFBMS-59
    AVERAGE MAE· uses extra data
    0.064
    best: 0.028 (RealFlow)
  • 2D Object DetectiononFBMS-59
    MAX F-MEASURE· uses extra data
    0.821
    best: 0.906 (RealFlow)
  • 2D Object DetectiononFBMS-59
    S-Measure· uses extra data
    0.851
    best: 0.926 (RealFlow)
  • 2D Object DetectiononUVSD
    Average MAE· uses extra data
    0.018
  • 2D Object DetectiononUVSD
    S-Measure· uses extra data
    0.901
  • 2D Object DetectiononUVSD
    max E-measure· uses extra data
    0.975
  • 2D Object DetectiononVOS-T
    Average MAE· uses extra data
    0.078
    best: 0.049 (RCRNet+NER)
  • 2D Object DetectiononVOS-T
    S-Measure· uses extra data
    0.818
    best: 0.872 (RCRNet+NER)
  • 2D Object DetectiononVOS-T
    max E-measure· uses extra data
    0.837
    best: 0.856 (RCRNet+NER)
  • 2D Object DetectiononSegTrack v2
    AVERAGE MAE· uses extra data
    0.024
    best: 0.022 (UFO)
  • 2D Object DetectiononSegTrack v2
    S-Measure· uses extra data
    0.864
    best: 0.892 (UFO)
  • 2D Object DetectiononSegTrack v2
    max E-measure· uses extra data
    0.935
  • 2D Object DetectiononDAVSOD-Difficult20
    Average MAE· uses extra data
    0.107
  • 2D Object DetectiononDAVSOD-Difficult20
    S-Measure· uses extra data
    0.608
    best: 0.619 (SSAV)
  • 2D Object DetectiononDAVSOD-Difficult20
    max E-measure· uses extra data
    0.678
    best: 0.698 (FGRN)
  • 2D Object DetectiononDAVIS-2016
    AVERAGE MAE· uses extra data
    0.028
    best: 0.01 (RealFlow)
  • 2D Object DetectiononDAVIS-2016
    MAX E-MEASURE· uses extra data
    0.951
    best: 0.966 (MBNM)
  • 2D Object DetectiononDAVIS-2016
    S-Measure· uses extra data
    0.882
    best: 0.945 (RealFlow)
  • 2D Object DetectiononViSal
    Average MAE· uses extra data
    0.032
    best: 0.01 (RealFlow)
  • 2D Object DetectiononViSal
    S-Measure· uses extra data
    0.907
    best: 0.962 (RealFlow)
  • 2D Object DetectiononViSal
    max E-measure· uses extra data
    0.846
    best: 0.987 (UFO)
  • 2D Object DetectiononDAVSOD-Normal25
    Average MAE· uses extra data
    0.132
    best: 0.117 (SSAV)
  • 2D Object DetectiononDAVSOD-Normal25
    S-Measure· uses extra data
    0.649
    best: 0.661 (SSAV)
  • 2D Object DetectiononDAVSOD-Normal25
    max E-measure· uses extra data
    0.698
    best: 0.723 (SSAV)
  • 2D Object DetectiononMCL
    AVERAGE MAE
    0.021
  • 2D Object DetectiononMCL
    MAX E-MEASURE
    0.911
  • 2D Object DetectiononMCL
    S-Measure
    0.856
  • 16konDAVSOD-easy35
    Average MAE· uses extra data
    0.114
    best: 0.066 (RealFlow)
  • 16konDAVSOD-easy35
    S-Measure· uses extra data
    0.706
    best: 0.803 (RealFlow)
  • 16konDAVSOD-easy35
    max E-Measure· uses extra data
    0.749
    best: 0.806 (SSAV)
  • 16konDAVSOD-easy35
    max F-Measure· uses extra data
    0.591
    best: 0.732 (RealFlow)
  • 16konFBMS-59
    AVERAGE MAE· uses extra data
    0.064
    best: 0.028 (RealFlow)
  • 16konFBMS-59
    MAX F-MEASURE· uses extra data
    0.821
    best: 0.906 (RealFlow)
  • 16konFBMS-59
    S-Measure· uses extra data
    0.851
    best: 0.926 (RealFlow)
  • 16konUVSD
    Average MAE· uses extra data
    0.018
  • 16konUVSD
    S-Measure· uses extra data
    0.901
  • 16konUVSD
    max E-measure· uses extra data
    0.975
  • 16konVOS-T
    Average MAE· uses extra data
    0.078
    best: 0.049 (RCRNet+NER)
  • 16konVOS-T
    S-Measure· uses extra data
    0.818
    best: 0.872 (RCRNet+NER)
  • 16konVOS-T
    max E-measure· uses extra data
    0.837
    best: 0.856 (RCRNet+NER)
  • 16konSegTrack v2
    AVERAGE MAE· uses extra data
    0.024
    best: 0.022 (UFO)
  • 16konSegTrack v2
    S-Measure· uses extra data
    0.864
    best: 0.892 (UFO)
  • 16konSegTrack v2
    max E-measure· uses extra data
    0.935
  • 16konDAVSOD-Difficult20
    Average MAE· uses extra data
    0.107
  • 16konDAVSOD-Difficult20
    S-Measure· uses extra data
    0.608
    best: 0.619 (SSAV)
  • 16konDAVSOD-Difficult20
    max E-measure· uses extra data
    0.678
    best: 0.698 (FGRN)
  • 16konDAVIS-2016
    AVERAGE MAE· uses extra data
    0.028
    best: 0.01 (RealFlow)
  • 16konDAVIS-2016
    MAX E-MEASURE· uses extra data
    0.951
    best: 0.966 (MBNM)
  • 16konDAVIS-2016
    S-Measure· uses extra data
    0.882
    best: 0.945 (RealFlow)
  • 16konViSal
    Average MAE· uses extra data
    0.032
    best: 0.01 (RealFlow)
  • 16konViSal
    S-Measure· uses extra data
    0.907
    best: 0.962 (RealFlow)
  • 16konViSal
    max E-measure· uses extra data
    0.846
    best: 0.987 (UFO)
  • 16konDAVSOD-Normal25
    Average MAE· uses extra data
    0.132
    best: 0.117 (SSAV)
  • 16konDAVSOD-Normal25
    S-Measure· uses extra data
    0.649
    best: 0.661 (SSAV)
  • 16konDAVSOD-Normal25
    max E-measure· uses extra data
    0.698
    best: 0.723 (SSAV)
  • 16konMCL
    AVERAGE MAE
    0.021
  • 16konMCL
    MAX E-MEASURE
    0.911
  • 16konMCL
    S-Measure
    0.856