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/STMask(R101-DCN-FPN)

STMask(R101-DCN-FPN)

Reported on 18 benchmarks across 1 task · 1 paper · 11 SOTA

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

Computer Vision18 results

Video Instance SegmentationonYouTube-VIS 2021
AP50· 2021-04-06
54
best: 87.3 (CAVIS(VIT-L, Offline))
SOTA
Spatial Feature Calibration and Temporal Fusion for Effective One-stage Video Instance Segmentation arXiv:2104.05606
Video Instance SegmentationonYouTube-VIS 2021
AP75· 2021-04-06
38
best: 73.2 (CAVIS(VIT-L, Offline))
SOTA
Spatial Feature Calibration and Temporal Fusion for Effective One-stage Video Instance Segmentation arXiv:2104.05606
Video Instance SegmentationonYouTube-VIS 2021
AR1· 2021-04-06
29.4
best: 49.7 (CAVIS(VIT-L, Offline))
SOTA
Spatial Feature Calibration and Temporal Fusion for Effective One-stage Video Instance Segmentation arXiv:2104.05606
Video Instance SegmentationonYouTube-VIS 2021
AR10· 2021-04-06
39.1
best: 70.7 (DVIS-DAQ(VIT-L, Offline))
SOTA
Spatial Feature Calibration and Temporal Fusion for Effective One-stage Video Instance Segmentation arXiv:2104.05606
Video Instance SegmentationonYouTube-VIS 2021
mask AP· 2021-04-06
34.6
best: 65.3 (CAVIS(VIT-L, Offline))
SOTA
Spatial Feature Calibration and Temporal Fusion for Effective One-stage Video Instance Segmentation arXiv:2104.05606
Video Instance SegmentationonOVIS validation
AP50· 2021-04-06
35.4
best: 83.8 (DVIS-DAQ(VIT-L, Offline))
SOTA
Spatial Feature Calibration and Temporal Fusion for Effective One-stage Video Instance Segmentation arXiv:2104.05606
Video Instance SegmentationonOVIS validation
AP75· 2021-04-06
15.2
best: 63.5 (CAVIS(VIT-L, Offline))
SOTA
Spatial Feature Calibration and Temporal Fusion for Effective One-stage Video Instance Segmentation arXiv:2104.05606
Video Instance SegmentationonOVIS validation
APho· 2021-04-06
23.7
best: 27.1 (DVIS++(VIT-L, Online))
SOTA
Spatial Feature Calibration and Temporal Fusion for Effective One-stage Video Instance Segmentation arXiv:2104.05606
Video Instance SegmentationonOVIS validation
AR1· 2021-04-06
8.4
best: 21.2 (CAVIS(VIT-L, Offline))
SOTA
Spatial Feature Calibration and Temporal Fusion for Effective One-stage Video Instance Segmentation arXiv:2104.05606
Video Instance SegmentationonOVIS validation
AR10· 2021-04-06
23.1
best: 61.8 (CAVIS(VIT-L, Offline))
SOTA
Spatial Feature Calibration and Temporal Fusion for Effective One-stage Video Instance Segmentation arXiv:2104.05606
Video Instance SegmentationonOVIS validation
mask AP· 2021-04-06
17.3
best: 57.1 (DVIS-DAQ(VIT-L, Offline))
SOTA
Spatial Feature Calibration and Temporal Fusion for Effective One-stage Video Instance Segmentation arXiv:2104.05606
Video Instance SegmentationonYouTube-VIS validation
AP50· 2021-04-06
56.8
best: 89.3 (CAVIS(ViT-L, Online))
Spatial Feature Calibration and Temporal Fusion for Effective One-stage Video Instance Segmentation arXiv:2104.05606
Video Instance SegmentationonYouTube-VIS validation
AP75· 2021-04-06
38
best: 76.2 (CAVIS(ViT-L, Online))
Spatial Feature Calibration and Temporal Fusion for Effective One-stage Video Instance Segmentation arXiv:2104.05606
Video Instance SegmentationonYouTube-VIS validation
AR1· 2021-04-06
34.8
best: 58.3 (CAVIS(ViT-L, Online))
Spatial Feature Calibration and Temporal Fusion for Effective One-stage Video Instance Segmentation arXiv:2104.05606
Video Instance SegmentationonYouTube-VIS validation
AR10· 2021-04-06
41.8
best: 73.7 (DVIS++(ViT-L, Online))
Spatial Feature Calibration and Temporal Fusion for Effective One-stage Video Instance Segmentation arXiv:2104.05606
Video Instance SegmentationonYouTube-VIS validation
mask AP· 2021-04-06
36.8
best: 68.9 (CAVIS(ViT-L, Online))
Spatial Feature Calibration and Temporal Fusion for Effective One-stage Video Instance Segmentation arXiv:2104.05606
Video Instance SegmentationonOVIS validation
APmo· 2021-04-06
14.7
best: 56.6 (DVIS++(VIT-L, Online))
Spatial Feature Calibration and Temporal Fusion for Effective One-stage Video Instance Segmentation arXiv:2104.05606
Video Instance SegmentationonOVIS validation
APso· 2021-04-06
11.1
best: 69.9 (DVIS++(VIT-L, Online))
Spatial Feature Calibration and Temporal Fusion for Effective One-stage Video Instance Segmentation arXiv:2104.05606