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/SeqFormer (Swin-L)

SeqFormer (Swin-L)

Reported on 6 benchmarks across 1 task · 1 paper · 6 SOTA

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

Computer Vision6 results

  • Video Instance SegmentationonYouTube-VIS validation
    AP50· uses extra data· 2021-12-15
    82.1
    best: 89.3 (CAVIS(ViT-L, Online))
    SOTA
    SeqFormer: Sequential Transformer for Video Instance SegmentationarXiv:2112.08275
  • Video Instance SegmentationonYouTube-VIS validation
    AP75· uses extra data· 2021-12-15
    66.4
    best: 76.2 (CAVIS(ViT-L, Online))
    SOTA
    SeqFormer: Sequential Transformer for Video Instance SegmentationarXiv:2112.08275
  • Video Instance SegmentationonYouTube-VIS validation
    AR1· uses extra data· 2021-12-15
    51.7
    best: 58.3 (CAVIS(ViT-L, Online))
    SOTA
    SeqFormer: Sequential Transformer for Video Instance SegmentationarXiv:2112.08275
  • Video Instance SegmentationonYouTube-VIS validation
    AR10· uses extra data· 2021-12-15
    64.4
    best: 73.7 (DVIS++(ViT-L, Online))
    SOTA
    SeqFormer: Sequential Transformer for Video Instance SegmentationarXiv:2112.08275
  • Video Instance SegmentationonYouTube-VIS validation
    mask AP· uses extra data· 2021-12-15
    59.3
    best: 68.9 (CAVIS(ViT-L, Online))
    SOTA
    SeqFormer: Sequential Transformer for Video Instance SegmentationarXiv:2112.08275
  • Video Instance SegmentationonHQ-YTVIS
    Tube-Boundary AP· 2021-12-15
    43.3
    best: 44.8 (VMT (Swin-L))
    SOTA
    SeqFormer: Sequential Transformer for Video Instance SegmentationarXiv:2112.08275