Tube-Link(Swin-large)

Reported on 4 benchmarks across 4 tasks · 1 paper · 4 SOTA

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

Computer Vision3 results

Scene ParsingonVSPW
mIoU· 2023-03-22
59.6
best: 63.8 (DVIS++(VIT-L))
SOTA
Tube-Link: A Flexible Cross Tube Framework for Universal Video Segmentation arXiv:2303.12782
Video Semantic SegmentationonVSPW
mIoU· 2023-03-22
59.6
best: 63.8 (DVIS++(VIT-L))
SOTA
Tube-Link: A Flexible Cross Tube Framework for Universal Video Segmentation arXiv:2303.12782
Scene UnderstandingonVSPW
mIoU· 2023-03-22
59.6
best: 63.8 (DVIS++(VIT-L))
SOTA
Tube-Link: A Flexible Cross Tube Framework for Universal Video Segmentation arXiv:2303.12782

Audio1 result

2D Semantic SegmentationonVSPW
mIoU· 2023-03-22
59.6
best: 63.8 (DVIS++(VIT-L))
SOTA
Tube-Link: A Flexible Cross Tube Framework for Universal Video Segmentation arXiv:2303.12782