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/CMSA+CFSA

CMSA+CFSA

Reported on 28 benchmarks across 2 tasks · 1 paper · 12 SOTA

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

Computer Vision28 results

  • Instance SegmentationonA2D Sentences
    IoU overall· 2021-02-09
    0.618
    best: 0.807 (SOC (Video-Swin-B))
    SOTA
    Referring Segmentation in Images and Videos with Cross-Modal Self-Attention NetworkarXiv:2102.04762
  • Instance SegmentationonJ-HMDB
    IoU mean· 2021-02-09
    0.581
    best: 0.725 (SgMg (Video-Swin-B))
    SOTA
    Referring Segmentation in Images and Videos with Cross-Modal Self-Attention NetworkarXiv:2102.04762
  • Instance SegmentationonJ-HMDB
    IoU overall· 2021-02-09
    0.628
    best: 0.737 (SgMg (Video-Swin-B))
    SOTA
    Referring Segmentation in Images and Videos with Cross-Modal Self-Attention NetworkarXiv:2102.04762
  • Instance SegmentationonJ-HMDB
    Precision@0.7· 2021-02-09
    0.389
    best: 0.714 (SgMg (Video-Swin-B))
    SOTA
    Referring Segmentation in Images and Videos with Cross-Modal Self-Attention NetworkarXiv:2102.04762
  • Instance SegmentationonJ-HMDB
    Precision@0.8· 2021-02-09
    0.09
    best: 0.225 (SgMg (Video-Swin-B))
    SOTA
    Referring Segmentation in Images and Videos with Cross-Modal Self-Attention NetworkarXiv:2102.04762
  • Instance SegmentationonJ-HMDB
    Precision@0.9· 2021-02-09
    0.001
    best: 0.4 (HINet)
    SOTA
    Referring Segmentation in Images and Videos with Cross-Modal Self-Attention NetworkarXiv:2102.04762
  • Referring Expression SegmentationonA2D Sentences
    IoU overall· 2021-02-09
    0.618
    best: 0.807 (SOC (Video-Swin-B))
    SOTA
    Referring Segmentation in Images and Videos with Cross-Modal Self-Attention NetworkarXiv:2102.04762
  • Referring Expression SegmentationonJ-HMDB
    IoU mean· 2021-02-09
    0.581
    best: 0.725 (SgMg (Video-Swin-B))
    SOTA
    Referring Segmentation in Images and Videos with Cross-Modal Self-Attention NetworkarXiv:2102.04762
  • Referring Expression SegmentationonJ-HMDB
    IoU overall· 2021-02-09
    0.628
    best: 0.737 (SgMg (Video-Swin-B))
    SOTA
    Referring Segmentation in Images and Videos with Cross-Modal Self-Attention NetworkarXiv:2102.04762
  • Referring Expression SegmentationonJ-HMDB
    Precision@0.7· 2021-02-09
    0.389
    best: 0.714 (SgMg (Video-Swin-B))
    SOTA
    Referring Segmentation in Images and Videos with Cross-Modal Self-Attention NetworkarXiv:2102.04762
  • Referring Expression SegmentationonJ-HMDB
    Precision@0.8· 2021-02-09
    0.09
    best: 0.225 (SgMg (Video-Swin-B))
    SOTA
    Referring Segmentation in Images and Videos with Cross-Modal Self-Attention NetworkarXiv:2102.04762
  • Referring Expression SegmentationonJ-HMDB
    Precision@0.9· 2021-02-09
    0.001
    best: 0.4 (HINet)
    SOTA
    Referring Segmentation in Images and Videos with Cross-Modal Self-Attention NetworkarXiv:2102.04762
  • Instance SegmentationonA2D Sentences
    IoU mean· 2021-02-09
    0.432
    best: 0.725 (SOC (Video-Swin-B))
    Referring Segmentation in Images and Videos with Cross-Modal Self-Attention NetworkarXiv:2102.04762
  • Instance SegmentationonA2D Sentences
    Precision@0.5· 2021-02-09
    0.487
    best: 0.851 (SOC (Video-Swin-B))
    Referring Segmentation in Images and Videos with Cross-Modal Self-Attention NetworkarXiv:2102.04762
  • Instance SegmentationonA2D Sentences
    Precision@0.6· 2021-02-09
    0.431
    best: 0.827 (SOC (Video-Swin-B))
    Referring Segmentation in Images and Videos with Cross-Modal Self-Attention NetworkarXiv:2102.04762
  • Instance SegmentationonA2D Sentences
    Precision@0.7· 2021-02-09
    0.358
    best: 0.767 (SgMg (Video-Swin-B))
    Referring Segmentation in Images and Videos with Cross-Modal Self-Attention NetworkarXiv:2102.04762
  • Instance SegmentationonA2D Sentences
    Precision@0.8· 2021-02-09
    0.231
    best: 0.617 (SgMg (Video-Swin-B))
    Referring Segmentation in Images and Videos with Cross-Modal Self-Attention NetworkarXiv:2102.04762
  • Instance SegmentationonA2D Sentences
    Precision@0.9· 2021-02-09
    0.052
    best: 0.259 (SgMg (Video-Swin-B))
    Referring Segmentation in Images and Videos with Cross-Modal Self-Attention NetworkarXiv:2102.04762
  • Instance SegmentationonJ-HMDB
    Precision@0.5· 2021-02-09
    0.764
    best: 0.972 (SgMg (Video-Swin-B))
    Referring Segmentation in Images and Videos with Cross-Modal Self-Attention NetworkarXiv:2102.04762
  • Instance SegmentationonJ-HMDB
    Precision@0.6· 2021-02-09
    0.625
    best: 0.917 (SgMg (Video-Swin-B))
    Referring Segmentation in Images and Videos with Cross-Modal Self-Attention NetworkarXiv:2102.04762
  • Referring Expression SegmentationonA2D Sentences
    IoU mean· 2021-02-09
    0.432
    best: 0.725 (SOC (Video-Swin-B))
    Referring Segmentation in Images and Videos with Cross-Modal Self-Attention NetworkarXiv:2102.04762
  • Referring Expression SegmentationonA2D Sentences
    Precision@0.5· 2021-02-09
    0.487
    best: 0.851 (SOC (Video-Swin-B))
    Referring Segmentation in Images and Videos with Cross-Modal Self-Attention NetworkarXiv:2102.04762
  • Referring Expression SegmentationonA2D Sentences
    Precision@0.6· 2021-02-09
    0.431
    best: 0.827 (SOC (Video-Swin-B))
    Referring Segmentation in Images and Videos with Cross-Modal Self-Attention NetworkarXiv:2102.04762
  • Referring Expression SegmentationonA2D Sentences
    Precision@0.7· 2021-02-09
    0.358
    best: 0.767 (SgMg (Video-Swin-B))
    Referring Segmentation in Images and Videos with Cross-Modal Self-Attention NetworkarXiv:2102.04762
  • Referring Expression SegmentationonA2D Sentences
    Precision@0.8· 2021-02-09
    0.231
    best: 0.617 (SgMg (Video-Swin-B))
    Referring Segmentation in Images and Videos with Cross-Modal Self-Attention NetworkarXiv:2102.04762
  • Referring Expression SegmentationonA2D Sentences
    Precision@0.9· 2021-02-09
    0.052
    best: 0.259 (SgMg (Video-Swin-B))
    Referring Segmentation in Images and Videos with Cross-Modal Self-Attention NetworkarXiv:2102.04762
  • Referring Expression SegmentationonJ-HMDB
    Precision@0.5· 2021-02-09
    0.764
    best: 0.972 (SgMg (Video-Swin-B))
    Referring Segmentation in Images and Videos with Cross-Modal Self-Attention NetworkarXiv:2102.04762
  • Referring Expression SegmentationonJ-HMDB
    Precision@0.6· 2021-02-09
    0.625
    best: 0.917 (SgMg (Video-Swin-B))
    Referring Segmentation in Images and Videos with Cross-Modal Self-Attention NetworkarXiv:2102.04762