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/URVOS

URVOS

Reported on 20 benchmarks across 4 tasks

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

Computer Vision20 results

  • VideoonMeViS
    F
    29.9
    best: 56.7 (MPG-SAM 2)
  • VideoonMeViS
    J
    25.7
    best: 50.7 (MPG-SAM 2)
  • VideoonMeViS
    J&F
    27.8
    best: 53.7 (MPG-SAM 2)
  • VideoonRef-DAVIS17
    F
    56
    best: 78.5 (FindTrack)
  • VideoonRef-DAVIS17
    J
    47.3
    best: 69.9 (FindTrack)
  • VideoonRef-DAVIS17
    J&F
    51.6
    best: 74.2 (FindTrack)
  • Instance SegmentationonRefer-YouTube-VOS (2021 public validation)
    F
    50.8
    best: 76.1 (MPG-SAM 2)
  • Instance SegmentationonRefer-YouTube-VOS (2021 public validation)
    J
    47
    best: 71.7 (MPG-SAM 2)
  • Instance SegmentationonRefer-YouTube-VOS (2021 public validation)
    J&F
    48.9
    best: 73.9 (MPG-SAM 2)
  • Instance SegmentationonDAVIS 2017 (val)
    J&F 1st frame
    44.1
    best: 72.5 (UNINEXT-H)
  • Video Object SegmentationonMeViS
    F
    29.9
    best: 56.7 (MPG-SAM 2)
  • Video Object SegmentationonMeViS
    J
    25.7
    best: 50.7 (MPG-SAM 2)
  • Video Object SegmentationonMeViS
    J&F
    27.8
    best: 53.7 (MPG-SAM 2)
  • Video Object SegmentationonRef-DAVIS17
    F
    56
    best: 78.5 (FindTrack)
  • Video Object SegmentationonRef-DAVIS17
    J
    47.3
    best: 69.9 (FindTrack)
  • Video Object SegmentationonRef-DAVIS17
    J&F
    51.6
    best: 74.2 (FindTrack)
  • Referring Expression SegmentationonRefer-YouTube-VOS (2021 public validation)
    F
    50.8
    best: 76.1 (MPG-SAM 2)
  • Referring Expression SegmentationonRefer-YouTube-VOS (2021 public validation)
    J
    47
    best: 71.7 (MPG-SAM 2)
  • Referring Expression SegmentationonRefer-YouTube-VOS (2021 public validation)
    J&F
    48.9
    best: 73.9 (MPG-SAM 2)
  • Referring Expression SegmentationonDAVIS 2017 (val)
    J&F 1st frame
    44.1
    best: 72.5 (UNINEXT-H)