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/Tube-Link(Swin-base)

Tube-Link(Swin-base)

Reported on 15 benchmarks across 3 tasks · 1 paper · 3 SOTA

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

Medical5 results

Semantic SegmentationonVIPSeg
VPQ· 2023-03-22
50.4
best: 58.5 (CAVIS(VIT-L))
SOTA
Tube-Link: A Flexible Cross Tube Framework for Universal Video Segmentation arXiv:2303.12782
Semantic SegmentationonVIPSeg
STQ· 2023-03-22
49.4
best: 58.2 (UniVS(Swin-L))
Tube-Link: A Flexible Cross Tube Framework for Universal Video Segmentation arXiv:2303.12782
Semantic SegmentationonKITTI-STEP
AQ· uses extra data· 2023-03-22
69
best: 73 (Video K-Net (Swin-L))
Tube-Link: A Flexible Cross Tube Framework for Universal Video Segmentation arXiv:2303.12782
Semantic SegmentationonKITTI-STEP
SQ· uses extra data· 2023-03-22
74
best: 75 (Video K-Net (Swin-L))
Tube-Link: A Flexible Cross Tube Framework for Universal Video Segmentation arXiv:2303.12782
Semantic SegmentationonKITTI-STEP
STQ· uses extra data· 2023-03-22
72
best: 74 (Video K-Net (Swin-L))
Tube-Link: A Flexible Cross Tube Framework for Universal Video Segmentation arXiv:2303.12782

Audio5 results

10-shot image generationonVIPSeg
VPQ· 2023-03-22
50.4
best: 58.5 (CAVIS(VIT-L))
SOTA
Tube-Link: A Flexible Cross Tube Framework for Universal Video Segmentation arXiv:2303.12782
10-shot image generationonVIPSeg
STQ· 2023-03-22
49.4
best: 58.2 (UniVS(Swin-L))
Tube-Link: A Flexible Cross Tube Framework for Universal Video Segmentation arXiv:2303.12782
10-shot image generationonKITTI-STEP
AQ· uses extra data· 2023-03-22
69
best: 73 (Video K-Net (Swin-L))
Tube-Link: A Flexible Cross Tube Framework for Universal Video Segmentation arXiv:2303.12782
10-shot image generationonKITTI-STEP
SQ· uses extra data· 2023-03-22
74
best: 75 (Video K-Net (Swin-L))
Tube-Link: A Flexible Cross Tube Framework for Universal Video Segmentation arXiv:2303.12782
10-shot image generationonKITTI-STEP
STQ· uses extra data· 2023-03-22
72
best: 74 (Video K-Net (Swin-L))
Tube-Link: A Flexible Cross Tube Framework for Universal Video Segmentation arXiv:2303.12782

Computer Vision5 results

Panoptic SegmentationonVIPSeg
VPQ· 2023-03-22
50.4
best: 58.5 (CAVIS(VIT-L))
SOTA
Tube-Link: A Flexible Cross Tube Framework for Universal Video Segmentation arXiv:2303.12782
Panoptic SegmentationonVIPSeg
STQ· 2023-03-22
49.4
best: 58.2 (UniVS(Swin-L))
Tube-Link: A Flexible Cross Tube Framework for Universal Video Segmentation arXiv:2303.12782
Panoptic SegmentationonKITTI-STEP
AQ· uses extra data· 2023-03-22
69
best: 73 (Video K-Net (Swin-L))
Tube-Link: A Flexible Cross Tube Framework for Universal Video Segmentation arXiv:2303.12782
Panoptic SegmentationonKITTI-STEP
SQ· uses extra data· 2023-03-22
74
best: 75 (Video K-Net (Swin-L))
Tube-Link: A Flexible Cross Tube Framework for Universal Video Segmentation arXiv:2303.12782
Panoptic SegmentationonKITTI-STEP
STQ· uses extra data· 2023-03-22
72
best: 74 (Video K-Net (Swin-L))
Tube-Link: A Flexible Cross Tube Framework for Universal Video Segmentation arXiv:2303.12782