STEm-Seg (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 Vision5 results

Video Instance SegmentationonYouTube-VIS validation
AP50· 2020-03-18
50.7
best: 89.3 (CAVIS(ViT-L, Online))
STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos arXiv:2003.08429
Video Instance SegmentationonYouTube-VIS validation
AP75· 2020-03-18
37.9
best: 76.2 (CAVIS(ViT-L, Online))
STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos arXiv:2003.08429
Video Instance SegmentationonYouTube-VIS validation
AR1· 2020-03-18
34.4
best: 58.3 (CAVIS(ViT-L, Online))
STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos arXiv:2003.08429
Video Instance SegmentationonYouTube-VIS validation
AR10· 2020-03-18
41.6
best: 73.7 (DVIS++(ViT-L, Online))
STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos arXiv:2003.08429
Video Instance SegmentationonYouTube-VIS validation
mask AP· 2020-03-18
30.6
best: 68.9 (CAVIS(ViT-L, Online))
STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos arXiv:2003.08429