Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/SeqFormer (ResNet-50)

SeqFormer (ResNet-50)

Reported on 5 benchmarks across 1 task · 1 paper

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 validation
AP50· uses extra data· 2021-12-15
69.8
best: 89.3 (CAVIS(ViT-L, Online))
SeqFormer: Sequential Transformer for Video Instance Segmentation arXiv:2112.08275
Video Instance SegmentationonYouTube-VIS validation
AP75· uses extra data· 2021-12-15
51.8
best: 76.2 (CAVIS(ViT-L, Online))
SeqFormer: Sequential Transformer for Video Instance Segmentation arXiv:2112.08275
Video Instance SegmentationonYouTube-VIS validation
AR1· uses extra data· 2021-12-15
45.5
best: 58.3 (CAVIS(ViT-L, Online))
SeqFormer: Sequential Transformer for Video Instance Segmentation arXiv:2112.08275
Video Instance SegmentationonYouTube-VIS validation
AR10· uses extra data· 2021-12-15
54.8
best: 73.7 (DVIS++(ViT-L, Online))
SeqFormer: Sequential Transformer for Video Instance Segmentation arXiv:2112.08275
Video Instance SegmentationonYouTube-VIS validation
mask AP· uses extra data· 2021-12-15
47.4
best: 68.9 (CAVIS(ViT-L, Online))
SeqFormer: Sequential Transformer for Video Instance Segmentation arXiv:2112.08275
Video Instance SegmentationonYouTube-VIS validation
AP50· 2021-12-15
66.9
best: 89.3 (CAVIS(ViT-L, Online))
SeqFormer: Sequential Transformer for Video Instance Segmentation arXiv:2112.08275
Video Instance SegmentationonYouTube-VIS validation
AP75· 2021-12-15
50.5
best: 76.2 (CAVIS(ViT-L, Online))
SeqFormer: Sequential Transformer for Video Instance Segmentation arXiv:2112.08275
Video Instance SegmentationonYouTube-VIS validation
AR1· 2021-12-15
45.6
best: 58.3 (CAVIS(ViT-L, Online))
SeqFormer: Sequential Transformer for Video Instance Segmentation arXiv:2112.08275
Video Instance SegmentationonYouTube-VIS validation
AR10· 2021-12-15
54.6
best: 73.7 (DVIS++(ViT-L, Online))
SeqFormer: Sequential Transformer for Video Instance Segmentation arXiv:2112.08275
Video Instance SegmentationonYouTube-VIS validation
mask AP· 2021-12-15
45.1
best: 68.9 (CAVIS(ViT-L, Online))
SeqFormer: Sequential Transformer for Video Instance Segmentation arXiv:2112.08275