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/VLIDE

VLIDE

Reported on 38 benchmarks across 2 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 Vision38 results

  • Instance SegmentationonJ-HMDB
    AP· 2022-03-30
    0.441
    best: 0.45 (SgMg (Video-Swin-B))
    SOTA
    Deeply Interleaved Two-Stream Encoder for Referring Video SegmentationarXiv:2203.15969
  • Instance SegmentationonJ-HMDB
    Precision@0.8· 2022-03-30
    0.182
    best: 0.225 (SgMg (Video-Swin-B))
    SOTA
    Deeply Interleaved Two-Stream Encoder for Referring Video SegmentationarXiv:2203.15969
  • Instance SegmentationonJ-HMDB
    Precision@0.9· 2022-03-30
    0.3
    best: 0.4 (HINet)
    SOTA
    Deeply Interleaved Two-Stream Encoder for Referring Video SegmentationarXiv:2203.15969
  • Referring Expression SegmentationonJ-HMDB
    AP· 2022-03-30
    0.441
    best: 0.45 (SgMg (Video-Swin-B))
    SOTA
    Deeply Interleaved Two-Stream Encoder for Referring Video SegmentationarXiv:2203.15969
  • Referring Expression SegmentationonJ-HMDB
    Precision@0.8· 2022-03-30
    0.182
    best: 0.225 (SgMg (Video-Swin-B))
    SOTA
    Deeply Interleaved Two-Stream Encoder for Referring Video SegmentationarXiv:2203.15969
  • Referring Expression SegmentationonJ-HMDB
    Precision@0.9· 2022-03-30
    0.3
    best: 0.4 (HINet)
    SOTA
    Deeply Interleaved Two-Stream Encoder for Referring Video SegmentationarXiv:2203.15969
  • Instance SegmentationonRefer-YouTube-VOS (2021 public validation)
    F· 2022-03-30
    50.67
    best: 76.1 (MPG-SAM 2)
    Deeply Interleaved Two-Stream Encoder for Referring Video SegmentationarXiv:2203.15969
  • Instance SegmentationonRefer-YouTube-VOS (2021 public validation)
    J· 2022-03-30
    48.44
    best: 71.7 (MPG-SAM 2)
    Deeply Interleaved Two-Stream Encoder for Referring Video SegmentationarXiv:2203.15969
  • Instance SegmentationonRefer-YouTube-VOS (2021 public validation)
    J&F· 2022-03-30
    49.56
    best: 73.9 (MPG-SAM 2)
    Deeply Interleaved Two-Stream Encoder for Referring Video SegmentationarXiv:2203.15969
  • Instance SegmentationonA2D Sentences
    AP· 2022-03-30
    0.469
    best: 0.585 (SgMg (Video-Swin-B))
    Deeply Interleaved Two-Stream Encoder for Referring Video SegmentationarXiv:2203.15969
  • Instance SegmentationonA2D Sentences
    IoU mean· 2022-03-30
    0.598
    best: 0.725 (SOC (Video-Swin-B))
    Deeply Interleaved Two-Stream Encoder for Referring Video SegmentationarXiv:2203.15969
  • Instance SegmentationonA2D Sentences
    IoU overall· 2022-03-30
    0.714
    best: 0.807 (SOC (Video-Swin-B))
    Deeply Interleaved Two-Stream Encoder for Referring Video SegmentationarXiv:2203.15969
  • Instance SegmentationonA2D Sentences
    Precision@0.5· 2022-03-30
    0.702
    best: 0.851 (SOC (Video-Swin-B))
    Deeply Interleaved Two-Stream Encoder for Referring Video SegmentationarXiv:2203.15969
  • Instance SegmentationonA2D Sentences
    Precision@0.6· 2022-03-30
    0.663
    best: 0.827 (SOC (Video-Swin-B))
    Deeply Interleaved Two-Stream Encoder for Referring Video SegmentationarXiv:2203.15969
  • Instance SegmentationonA2D Sentences
    Precision@0.7· 2022-03-30
    0.585
    best: 0.767 (SgMg (Video-Swin-B))
    Deeply Interleaved Two-Stream Encoder for Referring Video SegmentationarXiv:2203.15969
  • Instance SegmentationonA2D Sentences
    Precision@0.8· 2022-03-30
    0.428
    best: 0.617 (SgMg (Video-Swin-B))
    Deeply Interleaved Two-Stream Encoder for Referring Video SegmentationarXiv:2203.15969
  • Instance SegmentationonA2D Sentences
    Precision@0.9· 2022-03-30
    0.151
    best: 0.259 (SgMg (Video-Swin-B))
    Deeply Interleaved Two-Stream Encoder for Referring Video SegmentationarXiv:2203.15969
  • Instance SegmentationonJ-HMDB
    IoU mean· 2022-03-30
    0.666
    best: 0.725 (SgMg (Video-Swin-B))
    Deeply Interleaved Two-Stream Encoder for Referring Video SegmentationarXiv:2203.15969
  • Instance SegmentationonJ-HMDB
    IoU overall· 2022-03-30
    0.68
    best: 0.737 (SgMg (Video-Swin-B))
    Deeply Interleaved Two-Stream Encoder for Referring Video SegmentationarXiv:2203.15969
  • Instance SegmentationonJ-HMDB
    Precision@0.5· 2022-03-30
    0.874
    best: 0.972 (SgMg (Video-Swin-B))
    Deeply Interleaved Two-Stream Encoder for Referring Video SegmentationarXiv:2203.15969
  • Instance SegmentationonJ-HMDB
    Precision@0.6· 2022-03-30
    0.791
    best: 0.917 (SgMg (Video-Swin-B))
    Deeply Interleaved Two-Stream Encoder for Referring Video SegmentationarXiv:2203.15969
  • Instance SegmentationonJ-HMDB
    Precision@0.7· 2022-03-30
    0.586
    best: 0.714 (SgMg (Video-Swin-B))
    Deeply Interleaved Two-Stream Encoder for Referring Video SegmentationarXiv:2203.15969
  • Referring Expression SegmentationonRefer-YouTube-VOS (2021 public validation)
    F· 2022-03-30
    50.67
    best: 76.1 (MPG-SAM 2)
    Deeply Interleaved Two-Stream Encoder for Referring Video SegmentationarXiv:2203.15969
  • Referring Expression SegmentationonRefer-YouTube-VOS (2021 public validation)
    J· 2022-03-30
    48.44
    best: 71.7 (MPG-SAM 2)
    Deeply Interleaved Two-Stream Encoder for Referring Video SegmentationarXiv:2203.15969
  • Referring Expression SegmentationonRefer-YouTube-VOS (2021 public validation)
    J&F· 2022-03-30
    49.56
    best: 73.9 (MPG-SAM 2)
    Deeply Interleaved Two-Stream Encoder for Referring Video SegmentationarXiv:2203.15969
  • Referring Expression SegmentationonA2D Sentences
    AP· 2022-03-30
    0.469
    best: 0.585 (SgMg (Video-Swin-B))
    Deeply Interleaved Two-Stream Encoder for Referring Video SegmentationarXiv:2203.15969
  • Referring Expression SegmentationonA2D Sentences
    IoU mean· 2022-03-30
    0.598
    best: 0.725 (SOC (Video-Swin-B))
    Deeply Interleaved Two-Stream Encoder for Referring Video SegmentationarXiv:2203.15969
  • Referring Expression SegmentationonA2D Sentences
    IoU overall· 2022-03-30
    0.714
    best: 0.807 (SOC (Video-Swin-B))
    Deeply Interleaved Two-Stream Encoder for Referring Video SegmentationarXiv:2203.15969
  • Referring Expression SegmentationonA2D Sentences
    Precision@0.5· 2022-03-30
    0.702
    best: 0.851 (SOC (Video-Swin-B))
    Deeply Interleaved Two-Stream Encoder for Referring Video SegmentationarXiv:2203.15969
  • Referring Expression SegmentationonA2D Sentences
    Precision@0.6· 2022-03-30
    0.663
    best: 0.827 (SOC (Video-Swin-B))
    Deeply Interleaved Two-Stream Encoder for Referring Video SegmentationarXiv:2203.15969
  • Referring Expression SegmentationonA2D Sentences
    Precision@0.7· 2022-03-30
    0.585
    best: 0.767 (SgMg (Video-Swin-B))
    Deeply Interleaved Two-Stream Encoder for Referring Video SegmentationarXiv:2203.15969
  • Referring Expression SegmentationonA2D Sentences
    Precision@0.8· 2022-03-30
    0.428
    best: 0.617 (SgMg (Video-Swin-B))
    Deeply Interleaved Two-Stream Encoder for Referring Video SegmentationarXiv:2203.15969
  • Referring Expression SegmentationonA2D Sentences
    Precision@0.9· 2022-03-30
    0.151
    best: 0.259 (SgMg (Video-Swin-B))
    Deeply Interleaved Two-Stream Encoder for Referring Video SegmentationarXiv:2203.15969
  • Referring Expression SegmentationonJ-HMDB
    IoU mean· 2022-03-30
    0.666
    best: 0.725 (SgMg (Video-Swin-B))
    Deeply Interleaved Two-Stream Encoder for Referring Video SegmentationarXiv:2203.15969
  • Referring Expression SegmentationonJ-HMDB
    IoU overall· 2022-03-30
    0.68
    best: 0.737 (SgMg (Video-Swin-B))
    Deeply Interleaved Two-Stream Encoder for Referring Video SegmentationarXiv:2203.15969
  • Referring Expression SegmentationonJ-HMDB
    Precision@0.5· 2022-03-30
    0.874
    best: 0.972 (SgMg (Video-Swin-B))
    Deeply Interleaved Two-Stream Encoder for Referring Video SegmentationarXiv:2203.15969
  • Referring Expression SegmentationonJ-HMDB
    Precision@0.6· 2022-03-30
    0.791
    best: 0.917 (SgMg (Video-Swin-B))
    Deeply Interleaved Two-Stream Encoder for Referring Video SegmentationarXiv:2203.15969
  • Referring Expression SegmentationonJ-HMDB
    Precision@0.7· 2022-03-30
    0.586
    best: 0.714 (SgMg (Video-Swin-B))
    Deeply Interleaved Two-Stream Encoder for Referring Video SegmentationarXiv:2203.15969