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/MiVOS

MiVOS

Reported on 92 benchmarks across 3 tasks · 1 paper · 50 SOTA

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

Computer Vision92 results

VideoonDAVIS 2017 (val)
F-measure (Mean)· uses extra data· 2021-03-14
87.4
best: 93.4 (Cutie+ (base))
SOTA
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
VideoonDAVIS 2017 (val)
F-measure (Recall)· uses extra data· 2021-03-14
93.1
best: 94.6 (STCN)
SOTA
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
VideoonDAVIS 2017 (val)
J&F· uses extra data· 2021-03-14
84.5
best: 90.7 (SAM2)
SOTA
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
VideoonDAVIS 2017 (val)
Jaccard (Mean)· uses extra data· 2021-03-14
81.7
best: 87.5 (Cutie+ (base))
SOTA
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
VideoonDAVIS 2017 (val)
Jaccard (Recall)· uses extra data· 2021-03-14
90.9
best: 91.4 (ISVOS (MS))
SOTA
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
VideoonDAVIS 2017 (val)
Speed (FPS)· uses extra data· 2021-03-14
11.2
best: 90.6 (MobileVOS (BL30K))
SOTA
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
VideoonDAVIS 2016
F-measure (Mean)· uses extra data· 2021-03-14
92.4
best: 94.7 (SwinB-DeAOT-L)
SOTA
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
VideoonDAVIS 2016
F-measure (Recall)· uses extra data· 2021-03-14
96.4
best: 97.1 (STCN)
SOTA
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
VideoonDAVIS 2016
J&F· uses extra data· 2021-03-14
91
best: 93.4 (ISVOS (BL30K, MS))
SOTA
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
VideoonDAVIS 2016
Jaccard (Mean)· uses extra data· 2021-03-14
89.7
best: 92.5 (ISVOS (BL30K, MS))
SOTA
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
VideoonDAVIS 2016
Jaccard (Recall)· uses extra data· 2021-03-14
97.5
best: 98.1 (STCN)
SOTA
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
VideoonDAVIS 2017 (test-dev)
F-measure (Recall)· uses extra data· 2021-03-14
87.6
best: 89.7 (STCN)
SOTA
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
VideoonDAVIS 2017 (test-dev)
Jaccard (Recall)· uses extra data· 2021-03-14
81.2
best: 85.5 (STCN)
SOTA
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
VideoonYouTube-VOS 2018
Jaccard (Unseen)· uses extra data· 2021-03-14
77.3
best: 82.2 (Cutie+ (base, MEGA))
SOTA
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
VideoonDAVIS 2017
AUC-J· uses extra data· 2021-03-14
0.849
SOTA
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
VideoonDAVIS 2017
AUC-J&F· uses extra data· 2021-03-14
0.879
SOTA
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
VideoonDAVIS 2017
J&F@60s· uses extra data· 2021-03-14
0.885
SOTA
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
VideoonDAVIS 2017
J@60s· uses extra data· 2021-03-14
0.854
SOTA
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Video Object SegmentationonDAVIS 2017 (val)
F-measure (Mean)· uses extra data· 2021-03-14
87.4
best: 93.4 (Cutie+ (base))
SOTA
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Video Object SegmentationonDAVIS 2017 (val)
F-measure (Recall)· uses extra data· 2021-03-14
93.1
best: 94.6 (STCN)
SOTA
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Video Object SegmentationonDAVIS 2017 (val)
J&F· uses extra data· 2021-03-14
84.5
best: 90.7 (SAM2)
SOTA
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Video Object SegmentationonDAVIS 2017 (val)
Jaccard (Mean)· uses extra data· 2021-03-14
81.7
best: 87.5 (Cutie+ (base))
SOTA
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Video Object SegmentationonDAVIS 2017 (val)
Jaccard (Recall)· uses extra data· 2021-03-14
90.9
best: 91.4 (ISVOS (MS))
SOTA
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Video Object SegmentationonDAVIS 2017 (val)
Speed (FPS)· uses extra data· 2021-03-14
11.2
best: 90.6 (MobileVOS (BL30K))
SOTA
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Video Object SegmentationonDAVIS 2016
F-measure (Mean)· uses extra data· 2021-03-14
92.4
best: 94.7 (SwinB-DeAOT-L)
SOTA
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Video Object SegmentationonDAVIS 2016
F-measure (Recall)· uses extra data· 2021-03-14
96.4
best: 97.1 (STCN)
SOTA
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Video Object SegmentationonDAVIS 2016
J&F· uses extra data· 2021-03-14
91
best: 93.4 (ISVOS (BL30K, MS))
SOTA
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Video Object SegmentationonDAVIS 2016
Jaccard (Mean)· uses extra data· 2021-03-14
89.7
best: 92.5 (ISVOS (BL30K, MS))
SOTA
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Video Object SegmentationonDAVIS 2016
Jaccard (Recall)· uses extra data· 2021-03-14
97.5
best: 98.1 (STCN)
SOTA
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Video Object SegmentationonDAVIS 2017 (test-dev)
F-measure (Recall)· uses extra data· 2021-03-14
87.6
best: 89.7 (STCN)
SOTA
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Video Object SegmentationonDAVIS 2017 (test-dev)
Jaccard (Recall)· uses extra data· 2021-03-14
81.2
best: 85.5 (STCN)
SOTA
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Video Object SegmentationonYouTube-VOS 2018
Jaccard (Unseen)· uses extra data· 2021-03-14
77.3
best: 82.2 (Cutie+ (base, MEGA))
SOTA
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Video Object SegmentationonDAVIS 2017
AUC-J· uses extra data· 2021-03-14
0.849
SOTA
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Video Object SegmentationonDAVIS 2017
AUC-J&F· uses extra data· 2021-03-14
0.879
SOTA
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Video Object SegmentationonDAVIS 2017
J&F@60s· uses extra data· 2021-03-14
0.885
SOTA
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Video Object SegmentationonDAVIS 2017
J@60s· uses extra data· 2021-03-14
0.854
SOTA
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Semi-Supervised Video Object SegmentationonDAVIS 2017 (val)
F-measure (Mean)· uses extra data· 2021-03-14
87.4
best: 93.4 (Cutie+ (base))
SOTA
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Semi-Supervised Video Object SegmentationonDAVIS 2017 (val)
F-measure (Recall)· uses extra data· 2021-03-14
93.1
best: 94.6 (STCN)
SOTA
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Semi-Supervised Video Object SegmentationonDAVIS 2017 (val)
J&F· uses extra data· 2021-03-14
84.5
best: 90.7 (SAM2)
SOTA
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Semi-Supervised Video Object SegmentationonDAVIS 2017 (val)
Jaccard (Mean)· uses extra data· 2021-03-14
81.7
best: 87.5 (Cutie+ (base))
SOTA
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Semi-Supervised Video Object SegmentationonDAVIS 2017 (val)
Jaccard (Recall)· uses extra data· 2021-03-14
90.9
best: 91.4 (ISVOS (MS))
SOTA
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Semi-Supervised Video Object SegmentationonDAVIS 2017 (val)
Speed (FPS)· uses extra data· 2021-03-14
11.2
best: 90.6 (MobileVOS (BL30K))
SOTA
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Semi-Supervised Video Object SegmentationonDAVIS 2016
F-measure (Mean)· uses extra data· 2021-03-14
92.4
best: 94.7 (SwinB-DeAOT-L)
SOTA
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Semi-Supervised Video Object SegmentationonDAVIS 2016
F-measure (Recall)· uses extra data· 2021-03-14
96.4
best: 97.1 (STCN)
SOTA
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Semi-Supervised Video Object SegmentationonDAVIS 2016
J&F· uses extra data· 2021-03-14
91
best: 93.4 (ISVOS (BL30K, MS))
SOTA
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Semi-Supervised Video Object SegmentationonDAVIS 2016
Jaccard (Mean)· uses extra data· 2021-03-14
89.7
best: 92.5 (ISVOS (BL30K, MS))
SOTA
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Semi-Supervised Video Object SegmentationonDAVIS 2016
Jaccard (Recall)· uses extra data· 2021-03-14
97.5
best: 98.1 (STCN)
SOTA
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Semi-Supervised Video Object SegmentationonDAVIS 2017 (test-dev)
F-measure (Recall)· uses extra data· 2021-03-14
87.6
best: 89.7 (STCN)
SOTA
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Semi-Supervised Video Object SegmentationonDAVIS 2017 (test-dev)
Jaccard (Recall)· uses extra data· 2021-03-14
81.2
best: 85.5 (STCN)
SOTA
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Semi-Supervised Video Object SegmentationonYouTube-VOS 2018
Jaccard (Unseen)· uses extra data· 2021-03-14
77.3
best: 82.2 (Cutie+ (base, MEGA))
SOTA
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
VideoonDAVIS 2017 (val)
F-measure (Decay)· uses extra data· 2021-03-14
8.2
best: 85.3 (STCN)
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
VideoonDAVIS 2017 (val)
Jaccard (Decay)· uses extra data· 2021-03-14
7
best: 32.5 (MuG-W)
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
VideoonDAVIS 2016
F-measure (Decay)· uses extra data· 2021-03-14
5.1
best: 27.2 (OFL)
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
VideoonDAVIS 2016
Jaccard (Decay)· uses extra data· 2021-03-14
6.6
best: 28.9 (BVS)
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
VideoonDAVIS 2016
Speed (FPS)· uses extra data· 2021-03-14
16.9
best: 100.1 (MobileVOS (BL30K))
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
VideoonDAVIS 2017 (test-dev)
F-measure (Decay)· uses extra data· 2021-03-14
14.5
best: 37.2 (RGMP)
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
VideoonDAVIS 2017 (test-dev)
F-measure (Mean)· uses extra data· 2021-03-14
80.2
best: 91.4 (Cutie+ (base, MEGA))
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
VideoonDAVIS 2017 (test-dev)
J&F· uses extra data· 2021-03-14
76.5
best: 88.1 (Cutie+ (base, MEGA))
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
VideoonDAVIS 2017 (test-dev)
Jaccard (Decay)· uses extra data· 2021-03-14
14.9
best: 35.7 (RVOS)
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
VideoonDAVIS 2017 (test-dev)
Jaccard (Mean)· uses extra data· 2021-03-14
72.7
best: 84.7 (Cutie+ (base, MEGA))
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
VideoonYouTube-VOS 2018
F-Measure (Seen)· uses extra data· 2021-03-14
84.7
best: 91 (Cutie+ (base, MEGA))
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
VideoonYouTube-VOS 2018
F-Measure (Unseen)· uses extra data· 2021-03-14
85.5
best: 90.2 (XMem (BL30K, MS))
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
VideoonYouTube-VOS 2018
Jaccard (Seen)· uses extra data· 2021-03-14
80.6
best: 86.6 (Cutie+ (base, MEGA))
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
VideoonYouTube-VOS 2018
Overall· uses extra data· 2021-03-14
82
best: 87.5 (Cutie+ (base, MEGA))
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Video Object SegmentationonDAVIS 2017 (val)
F-measure (Decay)· uses extra data· 2021-03-14
8.2
best: 85.3 (STCN)
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Video Object SegmentationonDAVIS 2017 (val)
Jaccard (Decay)· uses extra data· 2021-03-14
7
best: 32.5 (MuG-W)
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Video Object SegmentationonDAVIS 2016
F-measure (Decay)· uses extra data· 2021-03-14
5.1
best: 27.2 (OFL)
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Video Object SegmentationonDAVIS 2016
Jaccard (Decay)· uses extra data· 2021-03-14
6.6
best: 28.9 (BVS)
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Video Object SegmentationonDAVIS 2016
Speed (FPS)· uses extra data· 2021-03-14
16.9
best: 100.1 (MobileVOS (BL30K))
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Video Object SegmentationonDAVIS 2017 (test-dev)
F-measure (Decay)· uses extra data· 2021-03-14
14.5
best: 37.2 (RGMP)
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Video Object SegmentationonDAVIS 2017 (test-dev)
F-measure (Mean)· uses extra data· 2021-03-14
80.2
best: 91.4 (Cutie+ (base, MEGA))
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Video Object SegmentationonDAVIS 2017 (test-dev)
J&F· uses extra data· 2021-03-14
76.5
best: 88.1 (Cutie+ (base, MEGA))
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Video Object SegmentationonDAVIS 2017 (test-dev)
Jaccard (Decay)· uses extra data· 2021-03-14
14.9
best: 35.7 (RVOS)
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Video Object SegmentationonDAVIS 2017 (test-dev)
Jaccard (Mean)· uses extra data· 2021-03-14
72.7
best: 84.7 (Cutie+ (base, MEGA))
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Video Object SegmentationonYouTube-VOS 2018
F-Measure (Seen)· uses extra data· 2021-03-14
84.7
best: 91 (Cutie+ (base, MEGA))
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Video Object SegmentationonYouTube-VOS 2018
F-Measure (Unseen)· uses extra data· 2021-03-14
85.5
best: 90.2 (XMem (BL30K, MS))
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Video Object SegmentationonYouTube-VOS 2018
Jaccard (Seen)· uses extra data· 2021-03-14
80.6
best: 86.6 (Cutie+ (base, MEGA))
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Video Object SegmentationonYouTube-VOS 2018
Overall· uses extra data· 2021-03-14
82
best: 87.5 (Cutie+ (base, MEGA))
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Semi-Supervised Video Object SegmentationonDAVIS 2017 (val)
F-measure (Decay)· uses extra data· 2021-03-14
8.2
best: 85.3 (STCN)
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Semi-Supervised Video Object SegmentationonDAVIS 2017 (val)
Jaccard (Decay)· uses extra data· 2021-03-14
7
best: 32.5 (MuG-W)
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Semi-Supervised Video Object SegmentationonDAVIS 2016
F-measure (Decay)· uses extra data· 2021-03-14
5.1
best: 27.2 (OFL)
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Semi-Supervised Video Object SegmentationonDAVIS 2016
Jaccard (Decay)· uses extra data· 2021-03-14
6.6
best: 28.9 (BVS)
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Semi-Supervised Video Object SegmentationonDAVIS 2016
Speed (FPS)· uses extra data· 2021-03-14
16.9
best: 100.1 (MobileVOS (BL30K))
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Semi-Supervised Video Object SegmentationonDAVIS 2017 (test-dev)
F-measure (Decay)· uses extra data· 2021-03-14
14.5
best: 37.2 (RGMP)
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Semi-Supervised Video Object SegmentationonDAVIS 2017 (test-dev)
F-measure (Mean)· uses extra data· 2021-03-14
80.2
best: 91.4 (Cutie+ (base, MEGA))
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Semi-Supervised Video Object SegmentationonDAVIS 2017 (test-dev)
J&F· uses extra data· 2021-03-14
76.5
best: 88.1 (Cutie+ (base, MEGA))
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Semi-Supervised Video Object SegmentationonDAVIS 2017 (test-dev)
Jaccard (Decay)· uses extra data· 2021-03-14
14.9
best: 35.7 (RVOS)
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Semi-Supervised Video Object SegmentationonDAVIS 2017 (test-dev)
Jaccard (Mean)· uses extra data· 2021-03-14
72.7
best: 84.7 (Cutie+ (base, MEGA))
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Semi-Supervised Video Object SegmentationonYouTube-VOS 2018
F-Measure (Seen)· uses extra data· 2021-03-14
84.7
best: 91 (Cutie+ (base, MEGA))
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Semi-Supervised Video Object SegmentationonYouTube-VOS 2018
F-Measure (Unseen)· uses extra data· 2021-03-14
85.5
best: 90.2 (XMem (BL30K, MS))
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Semi-Supervised Video Object SegmentationonYouTube-VOS 2018
Jaccard (Seen)· uses extra data· 2021-03-14
80.6
best: 86.6 (Cutie+ (base, MEGA))
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941
Semi-Supervised Video Object SegmentationonYouTube-VOS 2018
Overall· uses extra data· 2021-03-14
82
best: 87.5 (Cutie+ (base, MEGA))
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion arXiv:2103.07941