VisTR(ResNet-101)

Reported on 5 benchmarks across 1 task · 1 paper · 5 SOTA

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

Computer Vision5 results

Video Instance SegmentationonYouTube-VIS validation
AP50· 2020-11-30
64
best: 89.3 (CAVIS(ViT-L, Online))
SOTA
End-to-End Video Instance Segmentation with Transformers arXiv:2011.14503
Video Instance SegmentationonYouTube-VIS validation
AP75· 2020-11-30
45
best: 76.2 (CAVIS(ViT-L, Online))
SOTA
End-to-End Video Instance Segmentation with Transformers arXiv:2011.14503
Video Instance SegmentationonYouTube-VIS validation
AR1· 2020-11-30
38.3
best: 58.3 (CAVIS(ViT-L, Online))
SOTA
End-to-End Video Instance Segmentation with Transformers arXiv:2011.14503
Video Instance SegmentationonYouTube-VIS validation
AR10· 2020-11-30
44.9
best: 73.7 (DVIS++(ViT-L, Online))
SOTA
End-to-End Video Instance Segmentation with Transformers arXiv:2011.14503
Video Instance SegmentationonYouTube-VIS validation
mask AP· 2020-11-30
40.1
best: 68.9 (CAVIS(ViT-L, Online))
SOTA
End-to-End Video Instance Segmentation with Transformers arXiv:2011.14503