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/FEELVOS

FEELVOS

Reported on 95 benchmarks across 3 tasks · 1 paper · 59 SOTA

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

Computer Vision95 results

VideoonYouTube
mIoU· 2019-02-25
0.821
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
VideoonDAVIS 2017
F-measure (Decay)· 2019-02-25
20.1
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
VideoonDAVIS 2017
F-measure (Mean)· 2019-02-25
74
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
VideoonDAVIS 2017
F-measure (Recall)· 2019-02-25
83.8
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
VideoonDAVIS 2017
J&F· 2019-02-25
71.55
best: 82.5 (ViTAE-T-Stage)
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
VideoonDAVIS 2017
Jaccard (Decay)· 2019-02-25
17.5
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
VideoonDAVIS 2017
Jaccard (Mean)· 2019-02-25
69.1
best: 81.7 (AOC-MF (val))
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
VideoonDAVIS 2017
Jaccard (Recall)· 2019-02-25
79.1
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
VideoonDAVIS 2017 (test-dev)
F-measure (Decay)· 2019-02-25
33.5
best: 37.2 (RGMP)
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
VideoonDAVIS 2017 (test-dev)
Jaccard (Decay)· 2019-02-25
29.8
best: 35.7 (RVOS)
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
VideoonDAVIS (no YouTube-VOS training)
D16 val (F)· 2019-02-25
83.1
best: 90.6 (HMMN)
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
VideoonDAVIS (no YouTube-VOS training)
D16 val (G)· 2019-02-25
81.7
best: 89.4 (HMMN)
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
VideoonDAVIS (no YouTube-VOS training)
D16 val (J)· 2019-02-25
80.3
best: 88.2 (HMMN)
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
VideoonDAVIS (no YouTube-VOS training)
D17 test (F)· 2019-02-25
57.5
best: 72.2 (TBD)
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
VideoonDAVIS (no YouTube-VOS training)
D17 test (G)· 2019-02-25
54.4
best: 69.4 (TBD)
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
VideoonDAVIS (no YouTube-VOS training)
D17 test (J)· 2019-02-25
51.2
best: 66.6 (TBD)
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
VideoonDAVIS (no YouTube-VOS training)
D17 val (F)· 2019-02-25
72.3
best: 83.1 (HMMN)
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
VideoonDAVIS (no YouTube-VOS training)
D17 val (G)· 2019-02-25
69.1
best: 80.4 (HMMN)
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
VideoonDAVIS (no YouTube-VOS training)
D17 val (J)· 2019-02-25
65.9
best: 77.7 (HMMN)
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
VideoonDAVIS (no YouTube-VOS training)
FPS· 2019-02-25
2.22
best: 50.1 (TBD)
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Video Object SegmentationonYouTube
mIoU· 2019-02-25
0.821
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Video Object SegmentationonDAVIS 2017
F-measure (Decay)· 2019-02-25
20.1
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Video Object SegmentationonDAVIS 2017
F-measure (Mean)· 2019-02-25
74
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Video Object SegmentationonDAVIS 2017
F-measure (Recall)· 2019-02-25
83.8
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Video Object SegmentationonDAVIS 2017
J&F· 2019-02-25
71.55
best: 82.5 (ViTAE-T-Stage)
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Video Object SegmentationonDAVIS 2017
Jaccard (Decay)· 2019-02-25
17.5
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Video Object SegmentationonDAVIS 2017
Jaccard (Mean)· 2019-02-25
69.1
best: 81.7 (AOC-MF (val))
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Video Object SegmentationonDAVIS 2017
Jaccard (Recall)· 2019-02-25
79.1
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Video Object SegmentationonDAVIS 2017 (test-dev)
F-measure (Decay)· 2019-02-25
33.5
best: 37.2 (RGMP)
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Video Object SegmentationonDAVIS 2017 (test-dev)
Jaccard (Decay)· 2019-02-25
29.8
best: 35.7 (RVOS)
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Video Object SegmentationonDAVIS (no YouTube-VOS training)
D16 val (F)· 2019-02-25
83.1
best: 90.6 (HMMN)
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Video Object SegmentationonDAVIS (no YouTube-VOS training)
D16 val (G)· 2019-02-25
81.7
best: 89.4 (HMMN)
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Video Object SegmentationonDAVIS (no YouTube-VOS training)
D16 val (J)· 2019-02-25
80.3
best: 88.2 (HMMN)
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Video Object SegmentationonDAVIS (no YouTube-VOS training)
D17 test (F)· 2019-02-25
57.5
best: 72.2 (TBD)
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Video Object SegmentationonDAVIS (no YouTube-VOS training)
D17 test (G)· 2019-02-25
54.4
best: 69.4 (TBD)
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Video Object SegmentationonDAVIS (no YouTube-VOS training)
D17 test (J)· 2019-02-25
51.2
best: 66.6 (TBD)
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Video Object SegmentationonDAVIS (no YouTube-VOS training)
D17 val (F)· 2019-02-25
72.3
best: 83.1 (HMMN)
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Video Object SegmentationonDAVIS (no YouTube-VOS training)
D17 val (G)· 2019-02-25
69.1
best: 80.4 (HMMN)
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Video Object SegmentationonDAVIS (no YouTube-VOS training)
D17 val (J)· 2019-02-25
65.9
best: 77.7 (HMMN)
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Video Object SegmentationonDAVIS (no YouTube-VOS training)
FPS· 2019-02-25
2.22
best: 50.1 (TBD)
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Semi-Supervised Video Object SegmentationonDAVIS 2017
F-measure (Decay)· 2019-02-25
20.1
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Semi-Supervised Video Object SegmentationonDAVIS 2017
F-measure (Mean)· 2019-02-25
74
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Semi-Supervised Video Object SegmentationonDAVIS 2017
F-measure (Recall)· 2019-02-25
83.8
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Semi-Supervised Video Object SegmentationonDAVIS 2017
J&F· 2019-02-25
71.55
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Semi-Supervised Video Object SegmentationonDAVIS 2017
Jaccard (Decay)· 2019-02-25
17.5
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Semi-Supervised Video Object SegmentationonDAVIS 2017
Jaccard (Mean)· 2019-02-25
69.1
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Semi-Supervised Video Object SegmentationonDAVIS 2017
Jaccard (Recall)· 2019-02-25
79.1
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Semi-Supervised Video Object SegmentationonDAVIS 2017 (test-dev)
F-measure (Decay)· 2019-02-25
33.5
best: 37.2 (RGMP)
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Semi-Supervised Video Object SegmentationonDAVIS 2017 (test-dev)
Jaccard (Decay)· 2019-02-25
29.8
best: 35.7 (RVOS)
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Semi-Supervised Video Object SegmentationonDAVIS (no YouTube-VOS training)
D16 val (F)· 2019-02-25
83.1
best: 90.6 (HMMN)
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Semi-Supervised Video Object SegmentationonDAVIS (no YouTube-VOS training)
D16 val (G)· 2019-02-25
81.7
best: 89.4 (HMMN)
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Semi-Supervised Video Object SegmentationonDAVIS (no YouTube-VOS training)
D16 val (J)· 2019-02-25
80.3
best: 88.2 (HMMN)
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Semi-Supervised Video Object SegmentationonDAVIS (no YouTube-VOS training)
D17 test (F)· 2019-02-25
57.5
best: 72.2 (TBD)
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Semi-Supervised Video Object SegmentationonDAVIS (no YouTube-VOS training)
D17 test (G)· 2019-02-25
54.4
best: 69.4 (TBD)
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Semi-Supervised Video Object SegmentationonDAVIS (no YouTube-VOS training)
D17 test (J)· 2019-02-25
51.2
best: 66.6 (TBD)
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Semi-Supervised Video Object SegmentationonDAVIS (no YouTube-VOS training)
D17 val (F)· 2019-02-25
72.3
best: 83.1 (HMMN)
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Semi-Supervised Video Object SegmentationonDAVIS (no YouTube-VOS training)
D17 val (G)· 2019-02-25
69.1
best: 80.4 (HMMN)
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Semi-Supervised Video Object SegmentationonDAVIS (no YouTube-VOS training)
D17 val (J)· 2019-02-25
65.9
best: 77.7 (HMMN)
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Semi-Supervised Video Object SegmentationonDAVIS (no YouTube-VOS training)
FPS· 2019-02-25
2.22
best: 50.1 (TBD)
SOTA
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
VideoonDAVIS 2016
F-measure (Decay)· 2019-02-25
14.1
best: 27.2 (OFL)
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
VideoonDAVIS 2016
F-measure (Mean)· 2019-02-25
82.2
best: 94.7 (SwinB-DeAOT-L)
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
VideoonDAVIS 2016
F-measure (Recall)· 2019-02-25
86.6
best: 97.1 (STCN)
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
VideoonDAVIS 2016
J&F· 2019-02-25
81.65
best: 93.4 (ISVOS (BL30K, MS))
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
VideoonDAVIS 2016
Jaccard (Decay)· 2019-02-25
13.7
best: 28.9 (BVS)
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
VideoonDAVIS 2016
Jaccard (Mean)· 2019-02-25
81.1
best: 92.5 (ISVOS (BL30K, MS))
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
VideoonDAVIS 2016
Jaccard (Recall)· 2019-02-25
90.5
best: 98.1 (STCN)
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
VideoonDAVIS 2017 (test-dev)
F-measure (Mean)· 2019-02-25
60.9
best: 91.4 (Cutie+ (base, MEGA))
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
VideoonDAVIS 2017 (test-dev)
F-measure (Recall)· 2019-02-25
68.5
best: 89.7 (STCN)
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
VideoonDAVIS 2017 (test-dev)
J&F· 2019-02-25
57.8
best: 88.1 (Cutie+ (base, MEGA))
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
VideoonDAVIS 2017 (test-dev)
Jaccard (Mean)· 2019-02-25
55.1
best: 84.7 (Cutie+ (base, MEGA))
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
VideoonDAVIS 2017 (test-dev)
Jaccard (Recall)· 2019-02-25
62.6
best: 85.5 (STCN)
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Video Object SegmentationonDAVIS 2016
F-measure (Decay)· 2019-02-25
14.1
best: 27.2 (OFL)
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Video Object SegmentationonDAVIS 2016
F-measure (Mean)· 2019-02-25
82.2
best: 94.7 (SwinB-DeAOT-L)
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Video Object SegmentationonDAVIS 2016
F-measure (Recall)· 2019-02-25
86.6
best: 97.1 (STCN)
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Video Object SegmentationonDAVIS 2016
J&F· 2019-02-25
81.65
best: 93.4 (ISVOS (BL30K, MS))
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Video Object SegmentationonDAVIS 2016
Jaccard (Decay)· 2019-02-25
13.7
best: 28.9 (BVS)
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Video Object SegmentationonDAVIS 2016
Jaccard (Mean)· 2019-02-25
81.1
best: 92.5 (ISVOS (BL30K, MS))
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Video Object SegmentationonDAVIS 2016
Jaccard (Recall)· 2019-02-25
90.5
best: 98.1 (STCN)
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Video Object SegmentationonDAVIS 2017 (test-dev)
F-measure (Mean)· 2019-02-25
60.9
best: 91.4 (Cutie+ (base, MEGA))
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Video Object SegmentationonDAVIS 2017 (test-dev)
F-measure (Recall)· 2019-02-25
68.5
best: 89.7 (STCN)
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Video Object SegmentationonDAVIS 2017 (test-dev)
J&F· 2019-02-25
57.8
best: 88.1 (Cutie+ (base, MEGA))
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Video Object SegmentationonDAVIS 2017 (test-dev)
Jaccard (Mean)· 2019-02-25
55.1
best: 84.7 (Cutie+ (base, MEGA))
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Video Object SegmentationonDAVIS 2017 (test-dev)
Jaccard (Recall)· 2019-02-25
62.6
best: 85.5 (STCN)
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Semi-Supervised Video Object SegmentationonDAVIS 2016
F-measure (Decay)· 2019-02-25
14.1
best: 27.2 (OFL)
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Semi-Supervised Video Object SegmentationonDAVIS 2016
F-measure (Mean)· 2019-02-25
82.2
best: 94.7 (SwinB-DeAOT-L)
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Semi-Supervised Video Object SegmentationonDAVIS 2016
F-measure (Recall)· 2019-02-25
86.6
best: 97.1 (STCN)
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Semi-Supervised Video Object SegmentationonDAVIS 2016
J&F· 2019-02-25
81.65
best: 93.4 (ISVOS (BL30K, MS))
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Semi-Supervised Video Object SegmentationonDAVIS 2016
Jaccard (Decay)· 2019-02-25
13.7
best: 28.9 (BVS)
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Semi-Supervised Video Object SegmentationonDAVIS 2016
Jaccard (Mean)· 2019-02-25
81.1
best: 92.5 (ISVOS (BL30K, MS))
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Semi-Supervised Video Object SegmentationonDAVIS 2016
Jaccard (Recall)· 2019-02-25
90.5
best: 98.1 (STCN)
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Semi-Supervised Video Object SegmentationonDAVIS 2017 (test-dev)
F-measure (Mean)· 2019-02-25
60.9
best: 91.4 (Cutie+ (base, MEGA))
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Semi-Supervised Video Object SegmentationonDAVIS 2017 (test-dev)
F-measure (Recall)· 2019-02-25
68.5
best: 89.7 (STCN)
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Semi-Supervised Video Object SegmentationonDAVIS 2017 (test-dev)
J&F· 2019-02-25
57.8
best: 88.1 (Cutie+ (base, MEGA))
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Semi-Supervised Video Object SegmentationonDAVIS 2017 (test-dev)
Jaccard (Mean)· 2019-02-25
55.1
best: 84.7 (Cutie+ (base, MEGA))
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513
Semi-Supervised Video Object SegmentationonDAVIS 2017 (test-dev)
Jaccard (Recall)· 2019-02-25
62.6
best: 85.5 (STCN)
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation arXiv:1902.09513