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/VITA (Swin-L)

VITA (Swin-L)

Reported on 10 benchmarks across 1 task · 1 paper · 10 SOTA

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

Computer Vision10 results

  • Video Instance SegmentationonYouTube-VIS 2021
    AP50· uses extra data· 2022-06-09
    80.6
    best: 87.3 (CAVIS(VIT-L, Offline))
    SOTA
    VITA: Video Instance Segmentation via Object Token AssociationarXiv:2206.04403
  • Video Instance SegmentationonYouTube-VIS 2021
    AP75· uses extra data· 2022-06-09
    61
    best: 73.2 (CAVIS(VIT-L, Offline))
    SOTA
    VITA: Video Instance Segmentation via Object Token AssociationarXiv:2206.04403
  • Video Instance SegmentationonYouTube-VIS 2021
    AR1· uses extra data· 2022-06-09
    47.7
    best: 49.7 (CAVIS(VIT-L, Offline))
    SOTA
    VITA: Video Instance Segmentation via Object Token AssociationarXiv:2206.04403
  • Video Instance SegmentationonYouTube-VIS 2021
    AR10· uses extra data· 2022-06-09
    62.6
    best: 70.7 (DVIS-DAQ(VIT-L, Offline))
    SOTA
    VITA: Video Instance Segmentation via Object Token AssociationarXiv:2206.04403
  • Video Instance SegmentationonYouTube-VIS 2021
    mask AP· uses extra data· 2022-06-09
    57.5
    best: 65.3 (CAVIS(VIT-L, Offline))
    SOTA
    VITA: Video Instance Segmentation via Object Token AssociationarXiv:2206.04403
  • Video Instance SegmentationonOVIS validation
    AP50· uses extra data· 2022-06-09
    51.9
    best: 83.8 (DVIS-DAQ(VIT-L, Offline))
    SOTA
    VITA: Video Instance Segmentation via Object Token AssociationarXiv:2206.04403
  • Video Instance SegmentationonOVIS validation
    AP75· uses extra data· 2022-06-09
    24.9
    best: 63.5 (CAVIS(VIT-L, Offline))
    SOTA
    VITA: Video Instance Segmentation via Object Token AssociationarXiv:2206.04403
  • Video Instance SegmentationonOVIS validation
    AR1· uses extra data· 2022-06-09
    14.9
    best: 21.2 (CAVIS(VIT-L, Offline))
    SOTA
    VITA: Video Instance Segmentation via Object Token AssociationarXiv:2206.04403
  • Video Instance SegmentationonOVIS validation
    AR10· uses extra data· 2022-06-09
    33
    best: 61.8 (CAVIS(VIT-L, Offline))
    SOTA
    VITA: Video Instance Segmentation via Object Token AssociationarXiv:2206.04403
  • Video Instance SegmentationonOVIS validation
    mask AP· uses extra data· 2022-06-09
    27.7
    best: 57.1 (DVIS-DAQ(VIT-L, Offline))
    SOTA
    VITA: Video Instance Segmentation via Object Token AssociationarXiv:2206.04403