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/AGAME

AGAME

Reported on 63 benchmarks across 3 tasks · 1 paper · 6 SOTA

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

Computer Vision63 results

  • VideoonDAVIS 2017 (test-dev)
    F-measure (Decay)· 2018-11-28
    27.6
    best: 37.2 (RGMP)
    SOTA
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • VideoonDAVIS 2017 (test-dev)
    Jaccard (Decay)· 2018-11-28
    28.9
    best: 35.7 (RVOS)
    SOTA
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • Video Object SegmentationonDAVIS 2017 (test-dev)
    F-measure (Decay)· 2018-11-28
    27.6
    best: 37.2 (RGMP)
    SOTA
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • Video Object SegmentationonDAVIS 2017 (test-dev)
    Jaccard (Decay)· 2018-11-28
    28.9
    best: 35.7 (RVOS)
    SOTA
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • Semi-Supervised Video Object SegmentationonDAVIS 2017 (test-dev)
    F-measure (Decay)· 2018-11-28
    27.6
    best: 37.2 (RGMP)
    SOTA
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • Semi-Supervised Video Object SegmentationonDAVIS 2017 (test-dev)
    Jaccard (Decay)· 2018-11-28
    28.9
    best: 35.7 (RVOS)
    SOTA
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • VideoonDAVIS 2017 (val)
    F-measure (Decay)· 2018-11-28
    15.8
    best: 85.3 (STCN)
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • VideoonDAVIS 2017 (val)
    F-measure (Mean)· 2018-11-28
    73.6
    best: 93.4 (Cutie+ (base))
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • VideoonDAVIS 2017 (val)
    F-measure (Recall)· 2018-11-28
    83.4
    best: 94.6 (STCN)
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • VideoonDAVIS 2017 (val)
    J&F· 2018-11-28
    71.05
    best: 90.7 (SAM2)
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • VideoonDAVIS 2017 (val)
    Jaccard (Decay)· 2018-11-28
    14
    best: 32.5 (MuG-W)
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • VideoonDAVIS 2017 (val)
    Jaccard (Mean)· 2018-11-28
    68.5
    best: 87.5 (Cutie+ (base))
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • VideoonDAVIS 2017 (val)
    Jaccard (Recall)· 2018-11-28
    78.4
    best: 91.4 (ISVOS (MS))
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • VideoonDAVIS 2016
    F-measure (Decay)· 2018-11-28
    9.8
    best: 27.2 (OFL)
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • VideoonDAVIS 2016
    F-measure (Mean)· 2018-11-28
    82.2
    best: 94.7 (SwinB-DeAOT-L)
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • VideoonDAVIS 2016
    F-measure (Recall)· 2018-11-28
    90.3
    best: 97.1 (STCN)
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • VideoonDAVIS 2016
    J&F· 2018-11-28
    81.85
    best: 93.4 (ISVOS (BL30K, MS))
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • VideoonDAVIS 2016
    Jaccard (Decay)· 2018-11-28
    9.4
    best: 28.9 (BVS)
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • VideoonDAVIS 2016
    Jaccard (Mean)· 2018-11-28
    81.5
    best: 92.5 (ISVOS (BL30K, MS))
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • VideoonDAVIS 2016
    Jaccard (Recall)· 2018-11-28
    93.6
    best: 98.1 (STCN)
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • VideoonDAVIS 2017 (test-dev)
    F-measure (Mean)· 2018-11-28
    55.3
    best: 91.4 (Cutie+ (base, MEGA))
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • VideoonDAVIS 2017 (test-dev)
    F-measure (Recall)· 2018-11-28
    61.1
    best: 89.7 (STCN)
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • VideoonDAVIS 2017 (test-dev)
    J&F· 2018-11-28
    52.3
    best: 88.1 (Cutie+ (base, MEGA))
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • VideoonDAVIS 2017 (test-dev)
    Jaccard (Mean)· 2018-11-28
    49.2
    best: 84.7 (Cutie+ (base, MEGA))
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • VideoonDAVIS 2017 (test-dev)
    Jaccard (Recall)· 2018-11-28
    53.2
    best: 85.5 (STCN)
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • Video Object SegmentationonDAVIS 2017 (val)
    F-measure (Decay)· 2018-11-28
    15.8
    best: 85.3 (STCN)
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • Video Object SegmentationonDAVIS 2017 (val)
    F-measure (Mean)· 2018-11-28
    73.6
    best: 93.4 (Cutie+ (base))
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • Video Object SegmentationonDAVIS 2017 (val)
    F-measure (Recall)· 2018-11-28
    83.4
    best: 94.6 (STCN)
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • Video Object SegmentationonDAVIS 2017 (val)
    J&F· 2018-11-28
    71.05
    best: 90.7 (SAM2)
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • Video Object SegmentationonDAVIS 2017 (val)
    Jaccard (Decay)· 2018-11-28
    14
    best: 32.5 (MuG-W)
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • Video Object SegmentationonDAVIS 2017 (val)
    Jaccard (Mean)· 2018-11-28
    68.5
    best: 87.5 (Cutie+ (base))
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • Video Object SegmentationonDAVIS 2017 (val)
    Jaccard (Recall)· 2018-11-28
    78.4
    best: 91.4 (ISVOS (MS))
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • Video Object SegmentationonDAVIS 2016
    F-measure (Decay)· 2018-11-28
    9.8
    best: 27.2 (OFL)
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • Video Object SegmentationonDAVIS 2016
    F-measure (Mean)· 2018-11-28
    82.2
    best: 94.7 (SwinB-DeAOT-L)
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • Video Object SegmentationonDAVIS 2016
    F-measure (Recall)· 2018-11-28
    90.3
    best: 97.1 (STCN)
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • Video Object SegmentationonDAVIS 2016
    J&F· 2018-11-28
    81.85
    best: 93.4 (ISVOS (BL30K, MS))
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • Video Object SegmentationonDAVIS 2016
    Jaccard (Decay)· 2018-11-28
    9.4
    best: 28.9 (BVS)
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • Video Object SegmentationonDAVIS 2016
    Jaccard (Mean)· 2018-11-28
    81.5
    best: 92.5 (ISVOS (BL30K, MS))
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • Video Object SegmentationonDAVIS 2016
    Jaccard (Recall)· 2018-11-28
    93.6
    best: 98.1 (STCN)
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • Video Object SegmentationonDAVIS 2017 (test-dev)
    F-measure (Mean)· 2018-11-28
    55.3
    best: 91.4 (Cutie+ (base, MEGA))
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • Video Object SegmentationonDAVIS 2017 (test-dev)
    F-measure (Recall)· 2018-11-28
    61.1
    best: 89.7 (STCN)
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • Video Object SegmentationonDAVIS 2017 (test-dev)
    J&F· 2018-11-28
    52.3
    best: 88.1 (Cutie+ (base, MEGA))
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • Video Object SegmentationonDAVIS 2017 (test-dev)
    Jaccard (Mean)· 2018-11-28
    49.2
    best: 84.7 (Cutie+ (base, MEGA))
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • Video Object SegmentationonDAVIS 2017 (test-dev)
    Jaccard (Recall)· 2018-11-28
    53.2
    best: 85.5 (STCN)
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • Semi-Supervised Video Object SegmentationonDAVIS 2017 (val)
    F-measure (Decay)· 2018-11-28
    15.8
    best: 85.3 (STCN)
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • Semi-Supervised Video Object SegmentationonDAVIS 2017 (val)
    F-measure (Mean)· 2018-11-28
    73.6
    best: 93.4 (Cutie+ (base))
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • Semi-Supervised Video Object SegmentationonDAVIS 2017 (val)
    F-measure (Recall)· 2018-11-28
    83.4
    best: 94.6 (STCN)
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • Semi-Supervised Video Object SegmentationonDAVIS 2017 (val)
    J&F· 2018-11-28
    71.05
    best: 90.7 (SAM2)
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • Semi-Supervised Video Object SegmentationonDAVIS 2017 (val)
    Jaccard (Decay)· 2018-11-28
    14
    best: 32.5 (MuG-W)
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • Semi-Supervised Video Object SegmentationonDAVIS 2017 (val)
    Jaccard (Mean)· 2018-11-28
    68.5
    best: 87.5 (Cutie+ (base))
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • Semi-Supervised Video Object SegmentationonDAVIS 2017 (val)
    Jaccard (Recall)· 2018-11-28
    78.4
    best: 91.4 (ISVOS (MS))
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • Semi-Supervised Video Object SegmentationonDAVIS 2016
    F-measure (Decay)· 2018-11-28
    9.8
    best: 27.2 (OFL)
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • Semi-Supervised Video Object SegmentationonDAVIS 2016
    F-measure (Mean)· 2018-11-28
    82.2
    best: 94.7 (SwinB-DeAOT-L)
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • Semi-Supervised Video Object SegmentationonDAVIS 2016
    F-measure (Recall)· 2018-11-28
    90.3
    best: 97.1 (STCN)
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • Semi-Supervised Video Object SegmentationonDAVIS 2016
    J&F· 2018-11-28
    81.85
    best: 93.4 (ISVOS (BL30K, MS))
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • Semi-Supervised Video Object SegmentationonDAVIS 2016
    Jaccard (Decay)· 2018-11-28
    9.4
    best: 28.9 (BVS)
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • Semi-Supervised Video Object SegmentationonDAVIS 2016
    Jaccard (Mean)· 2018-11-28
    81.5
    best: 92.5 (ISVOS (BL30K, MS))
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • Semi-Supervised Video Object SegmentationonDAVIS 2016
    Jaccard (Recall)· 2018-11-28
    93.6
    best: 98.1 (STCN)
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • Semi-Supervised Video Object SegmentationonDAVIS 2017 (test-dev)
    F-measure (Mean)· 2018-11-28
    55.3
    best: 91.4 (Cutie+ (base, MEGA))
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • Semi-Supervised Video Object SegmentationonDAVIS 2017 (test-dev)
    F-measure (Recall)· 2018-11-28
    61.1
    best: 89.7 (STCN)
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • Semi-Supervised Video Object SegmentationonDAVIS 2017 (test-dev)
    J&F· 2018-11-28
    52.3
    best: 88.1 (Cutie+ (base, MEGA))
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • Semi-Supervised Video Object SegmentationonDAVIS 2017 (test-dev)
    Jaccard (Mean)· 2018-11-28
    49.2
    best: 84.7 (Cutie+ (base, MEGA))
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611
  • Semi-Supervised Video Object SegmentationonDAVIS 2017 (test-dev)
    Jaccard (Recall)· 2018-11-28
    53.2
    best: 85.5 (STCN)
    A Generative Appearance Model for End-to-end Video Object SegmentationarXiv:1811.11611