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/ReferFormer (Video-Swin-B)

ReferFormer (Video-Swin-B)

Reported on 24 benchmarks across 4 tasks · 1 paper · 24 SOTA

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

Computer Vision24 results

  • VideoonReVOS
    F· 2022-01-03
    29.9
    best: 62.5 (VRS-HQ (Chat-UniVi-13B))
    SOTA
    Language as Queries for Referring Video Object SegmentationarXiv:2201.00487
  • VideoonReVOS
    J· 2022-01-03
    26.2
    best: 57.6 (VRS-HQ (Chat-UniVi-13B))
    SOTA
    Language as Queries for Referring Video Object SegmentationarXiv:2201.00487
  • VideoonReVOS
    J&F· 2022-01-03
    28.1
    best: 60 (VRS-HQ (Chat-UniVi-13B))
    SOTA
    Language as Queries for Referring Video Object SegmentationarXiv:2201.00487
  • VideoonReVOS
    R· 2022-01-03
    8.8
    best: 19.7 (VRS-HQ (Chat-UniVi-7B))
    SOTA
    Language as Queries for Referring Video Object SegmentationarXiv:2201.00487
  • Instance SegmentationonA2D Sentences
    AP· uses extra data· 2022-01-03
    0.55
    best: 0.585 (SgMg (Video-Swin-B))
    SOTA
    Language as Queries for Referring Video Object SegmentationarXiv:2201.00487
  • Instance SegmentationonA2D Sentences
    IoU mean· uses extra data· 2022-01-03
    0.703
    best: 0.725 (SOC (Video-Swin-B))
    SOTA
    Language as Queries for Referring Video Object SegmentationarXiv:2201.00487
  • Instance SegmentationonA2D Sentences
    IoU overall· uses extra data· 2022-01-03
    0.786
    best: 0.807 (SOC (Video-Swin-B))
    SOTA
    Language as Queries for Referring Video Object SegmentationarXiv:2201.00487
  • Instance SegmentationonA2D Sentences
    Precision@0.5· uses extra data· 2022-01-03
    0.831
    best: 0.851 (SOC (Video-Swin-B))
    SOTA
    Language as Queries for Referring Video Object SegmentationarXiv:2201.00487
  • Instance SegmentationonA2D Sentences
    Precision@0.6· uses extra data· 2022-01-03
    0.804
    best: 0.827 (SOC (Video-Swin-B))
    SOTA
    Language as Queries for Referring Video Object SegmentationarXiv:2201.00487
  • Instance SegmentationonA2D Sentences
    Precision@0.7· uses extra data· 2022-01-03
    0.741
    best: 0.767 (SgMg (Video-Swin-B))
    SOTA
    Language as Queries for Referring Video Object SegmentationarXiv:2201.00487
  • Instance SegmentationonA2D Sentences
    Precision@0.8· uses extra data· 2022-01-03
    0.579
    best: 0.617 (SgMg (Video-Swin-B))
    SOTA
    Language as Queries for Referring Video Object SegmentationarXiv:2201.00487
  • Instance SegmentationonA2D Sentences
    Precision@0.9· uses extra data· 2022-01-03
    0.212
    best: 0.259 (SgMg (Video-Swin-B))
    SOTA
    Language as Queries for Referring Video Object SegmentationarXiv:2201.00487
  • Video Object SegmentationonReVOS
    F· 2022-01-03
    29.9
    best: 62.5 (VRS-HQ (Chat-UniVi-13B))
    SOTA
    Language as Queries for Referring Video Object SegmentationarXiv:2201.00487
  • Video Object SegmentationonReVOS
    J· 2022-01-03
    26.2
    best: 57.6 (VRS-HQ (Chat-UniVi-13B))
    SOTA
    Language as Queries for Referring Video Object SegmentationarXiv:2201.00487
  • Video Object SegmentationonReVOS
    J&F· 2022-01-03
    28.1
    best: 60 (VRS-HQ (Chat-UniVi-13B))
    SOTA
    Language as Queries for Referring Video Object SegmentationarXiv:2201.00487
  • Video Object SegmentationonReVOS
    R· 2022-01-03
    8.8
    best: 19.7 (VRS-HQ (Chat-UniVi-7B))
    SOTA
    Language as Queries for Referring Video Object SegmentationarXiv:2201.00487
  • Referring Expression SegmentationonA2D Sentences
    AP· uses extra data· 2022-01-03
    0.55
    best: 0.585 (SgMg (Video-Swin-B))
    SOTA
    Language as Queries for Referring Video Object SegmentationarXiv:2201.00487
  • Referring Expression SegmentationonA2D Sentences
    IoU mean· uses extra data· 2022-01-03
    0.703
    best: 0.725 (SOC (Video-Swin-B))
    SOTA
    Language as Queries for Referring Video Object SegmentationarXiv:2201.00487
  • Referring Expression SegmentationonA2D Sentences
    IoU overall· uses extra data· 2022-01-03
    0.786
    best: 0.807 (SOC (Video-Swin-B))
    SOTA
    Language as Queries for Referring Video Object SegmentationarXiv:2201.00487
  • Referring Expression SegmentationonA2D Sentences
    Precision@0.5· uses extra data· 2022-01-03
    0.831
    best: 0.851 (SOC (Video-Swin-B))
    SOTA
    Language as Queries for Referring Video Object SegmentationarXiv:2201.00487
  • Referring Expression SegmentationonA2D Sentences
    Precision@0.6· uses extra data· 2022-01-03
    0.804
    best: 0.827 (SOC (Video-Swin-B))
    SOTA
    Language as Queries for Referring Video Object SegmentationarXiv:2201.00487
  • Referring Expression SegmentationonA2D Sentences
    Precision@0.7· uses extra data· 2022-01-03
    0.741
    best: 0.767 (SgMg (Video-Swin-B))
    SOTA
    Language as Queries for Referring Video Object SegmentationarXiv:2201.00487
  • Referring Expression SegmentationonA2D Sentences
    Precision@0.8· uses extra data· 2022-01-03
    0.579
    best: 0.617 (SgMg (Video-Swin-B))
    SOTA
    Language as Queries for Referring Video Object SegmentationarXiv:2201.00487
  • Referring Expression SegmentationonA2D Sentences
    Precision@0.9· uses extra data· 2022-01-03
    0.212
    best: 0.259 (SgMg (Video-Swin-B))
    SOTA
    Language as Queries for Referring Video Object SegmentationarXiv:2201.00487