Tasks
SotA
Datasets
Papers
Methods
Submit
About
SotA
/
Computer Vision
/
Video
/
DAVIS 2017 (val)
Video on DAVIS 2017 (val)
Metric: Jaccard (Mean) (higher is better)
Leaderboard
Dataset
Loading chart...
Results
Submit a result
Hide extra data
Export CSV
Sort:
Jaccard (Mean) (best first)
Jaccard (Mean) (worst first)
Date (newest first)
Date (oldest first)
Model name (A→Z)
#
Model
↕
Jaccard (Mean)
▼
Extra Data
Paper
Date
↕
Code
1
Cutie+ (base)
87.5
Yes
Putting the Object Back into Video Object Segmen...
2023-10-19
Code
2
ISVOS (BL30K, MS)
86.7
Yes
Look Before You Match: Instance Understanding Ma...
2022-12-13
-
3
XMem (BL30K, MS)
86.3
Yes
XMem: Long-Term Video Object Segmentation with a...
2022-07-14
Code
4
ISVOS (MS)
85.8
Yes
Look Before You Match: Instance Understanding Ma...
2022-12-13
-
5
Cutie+ (base, MEGA)
85.5
Yes
Putting the Object Back into Video Object Segmen...
2023-10-19
Code
6
XMem (MS)
85.4
Yes
XMem: Long-Term Video Object Segmentation with a...
2022-07-14
Code
7
JIMD
85.2
No
Memory Matching is not Enough: Jointly Improving...
2024-09-22
-
8
Cutie (base)
84.6
No
Putting the Object Back into Video Object Segmen...
2023-10-19
Code
9
ISVOS (BL30K)
84.5
Yes
Look Before You Match: Instance Understanding Ma...
2022-12-13
-
10
DEVA
84.2
Yes
Tracking Anything with Decoupled Video Segmentat...
2023-09-07
Code
11
SwinB-AOTv2-L (MS)
84.2
No
Scalable Video Object Segmentation with Identifi...
2022-03-22
Code
12
XMem (BL30K)
84
Yes
XMem: Long-Term Video Object Segmentation with a...
2022-07-14
Code
13
SwinB-AOST (L'=3, MS)
83.8
No
Scalable Video Object Segmentation with Identifi...
2022-03-22
Code
14
SwinB-AOTv2-L
83.1
No
Scalable Video Object Segmentation with Identifi...
2022-03-22
Code
15
SwinB-DeAOT-L
83.1
No
Decoupling Features in Hierarchical Propagation ...
2022-10-18
Code
16
XMem
82.9
Yes
XMem: Long-Term Video Object Segmentation with a...
2022-07-14
Code
17
RAVOS
82.9
Yes
Region Aware Video Object Segmentation with Deep...
2022-07-21
-
18
R50-AOST (L'=3)
82.6
No
Scalable Video Object Segmentation with Identifi...
2022-03-22
Code
19
QDMN
82.5
Yes
Learning Quality-aware Dynamic Memory for Video ...
2022-07-16
Code
20
R50-AOST (L'=2)
82.5
No
Scalable Video Object Segmentation with Identifi...
2022-03-22
Code
21
SwinB-AOT-L
82.4
No
Associating Objects with Transformers for Video ...
2021-06-04
Code
22
R50-AOT-L
82.3
No
Associating Objects with Transformers for Video ...
2021-06-04
Code
23
R50-DeAOT-L
82.2
No
Decoupling Features in Hierarchical Propagation ...
2022-10-18
Code
24
STCN
82
Yes
Rethinking Space-Time Networks with Improved Mem...
2021-06-09
Code
25
HMMN
81.9
Yes
Hierarchical Memory Matching Network for Video O...
2021-09-23
Code
26
TarViS
81.7
Yes
TarViS: A Unified Approach for Target-based Vide...
2023-01-06
Code
27
MiVOS
81.7
Yes
Modular Interactive Video Object Segmentation: I...
2021-03-14
Code
28
XMem (DAVIS and YouTubeVOS only)
81.4
Yes
XMem: Long-Term Video Object Segmentation with a...
2022-07-14
Code
29
RPCMVOS
81.3
No
Reliable Propagation-Correction Modulation for V...
2021-12-06
Code
30
R50-AOST (L'=1)
81.2
No
Scalable Video Object Segmentation with Identifi...
2022-03-22
Code
31
AOT-L
81.1
No
Associating Objects with Transformers for Video ...
2021-06-04
Code
32
DeAOT-L
81
No
Decoupling Features in Hierarchical Propagation ...
2022-10-18
Code
33
RMNet
81
No
Efficient Regional Memory Network for Video Obje...
2021-03-24
Code
34
CFBI+
80.1
No
Collaborative Video Object Segmentation by Multi...
2020-10-13
Code
35
KMN
80
No
Kernelized Memory Network for Video Object Segme...
2020-07-16
Code
36
AOT-B
79.7
No
Associating Objects with Transformers for Video ...
2021-06-04
Code
37
DeAOT-B
79.2
No
Decoupling Features in Hierarchical Propagation ...
2022-10-18
Code
38
STM
79.2
Yes
Video Object Segmentation using Space-Time Memor...
2019-04-01
Code
39
CFBI
79.1
No
Collaborative Video Object Segmentation by Foreg...
2020-03-18
Code
40
AOT-S
78.7
No
Associating Objects with Transformers for Video ...
2021-06-04
Code
41
DeAOT-S
77.8
No
Decoupling Features in Hierarchical Propagation ...
2022-10-18
Code
42
DeAOT-T
77.7
No
Decoupling Features in Hierarchical Propagation ...
2022-10-18
Code
43
AOT-T
77.4
No
Associating Objects with Transformers for Video ...
2021-06-04
Code
44
JOINT
76
No
Joint Inductive and Transductive Learning for Vi...
2021-08-08
Code
45
SSM-VOS
75.3
No
-
-
Code
46
SWEM
74.5
No
SWEM: Towards Real-Time Video Object Segmentatio...
2022-08-22
Code
47
e-OSVOS
74.4
Yes
Make One-Shot Video Object Segmentation Efficien...
2020-12-03
Code
48
XMem (DAVIS only)
74.1
No
XMem: Long-Term Video Object Segmentation with a...
2022-07-14
Code
49
PReMVOS
73.9
No
PReMVOS: Proposal-generation, Refinement and Mer...
2018-07-24
Code
50
LSMVOS
73.9
No
LSMVOS: Long-Short-Term Similarity Matching for ...
2020-09-02
Code
51
MHP-VOS
73.4
No
MHP-VOS: Multiple Hypotheses Propagation for Vid...
2019-04-17
Code
52
AFB-URR
73
No
Video Object Segmentation with Adaptive Feature ...
2020-10-15
Code
53
PTSNet
71.6
No
Proposal, Tracking and Segmentation (PTS): A Cas...
2019-07-02
Code
54
DEVA (EntitySeg)
70.4
Yes
Tracking Anything with Decoupled Video Segmentat...
2023-09-07
Code
55
TVOS
69.9
No
A Transductive Approach for Video Object Segment...
2020-04-15
Code
56
AGAME
68.5
No
A Generative Appearance Model for End-to-end Vid...
2018-11-28
Code
57
MAMP
68.3
No
Self-Supervised Video Object Segmentation by Mot...
2021-07-27
Code
58
CINM
67.2
No
CNN in MRF: Video Object Segmentation via Infere...
2018-03-26
-
59
Araslanov et al.
67.1
No
Dense Unsupervised Learning for Video Segmentation
2021-11-11
Code
60
Propose-Reduce
67
Yes
Video Instance Segmentation with a Propose-Reduc...
2021-03-25
Code
61
UnOVOST
66.4
No
UnOVOST: Unsupervised Offline Video Object Segme...
2020-01-15
Code
62
Siam R-CNN
66.1
No
Siam R-CNN: Visual Tracking by Re-Detection
2019-11-28
Code
63
RGMP
64.8
No
-
-
Code
64
OSVOS-S
64.7
No
Video Object Segmentation Without Temporal Infor...
2017-09-18
-
65
AGSS-VOS
63.4
No
-
-
Code
66
MAST
63.3
No
MAST: A Memory-Augmented Self-supervised Tracker
2020-02-18
Code
67
MAST
63.3
Yes
MAST: A Memory-Augmented Self-supervised Tracker
2020-02-18
Code
68
RANet
63.2
No
RANet: Ranking Attention Network for Fast Video ...
2019-08-19
Code
69
OnAVOS
61.6
No
Online Adaptation of Convolutional Neural Networ...
2017-06-28
-
70
STEm-Seg
61.5
Yes
STEm-Seg: Spatio-temporal Embeddings for Instanc...
2020-03-18
Code
71
Spatiotemporal CNN
58.7
No
Spatiotemporal CNN for Video Object Segmentation
2019-04-04
Code
72
VOSwL (Language)
58
No
Video Object Segmentation with Language Referrin...
2018-03-21
-
73
UVC
57.7
No
Joint-task Self-supervised Learning for Temporal...
2019-09-26
Code
74
RVOS
57.5
No
RVOS: End-to-End Recurrent Network for Video Obj...
2019-03-13
Code
75
MATNet
56.7
No
-
-
Code
76
OSVOS
56.6
No
One-Shot Video Object Segmentation
2016-11-16
Code
77
ALBA
56.6
No
ALBA : Reinforcement Learning for Video Object S...
2020-05-26
Code
78
VideoMatch
56.5
No
VideoMatch: Matching based Video Object Segmenta...
2018-09-04
-
79
AGS
55.5
Yes
-
-
Code
80
FAVOS
54.6
No
Fast and Accurate Online Video Object Segmentati...
2018-06-06
Code
81
SiamMask
54.3
No
Fast Online Object Tracking and Segmentation: A ...
2018-12-12
Code
82
MuG-W
54.1
No
Learning Video Object Segmentation from Unlabele...
2020-03-10
Code
83
PDB
53.2
No
-
-
-
84
OSMN
52.5
No
Efficient Video Object Segmentation via Network ...
2018-02-04
Code
85
CorrFlow
48.4
No
Self-supervised Learning for Video Correspondenc...
2019-05-02
Code
86
CycleTime
46.4
No
Learning Correspondence from the Cycle-Consisten...
2019-03-18
Code
87
RVOS
36.8
No
RVOS: End-to-End Recurrent Network for Video Obj...
2019-03-13
Code
#1
Cutie+ (base)
SOTA
87.5
Jaccard (Mean)
· Extra Data
· 2023-10-19
Putting the Object Back into Video Object Segmentation
Code
#2
ISVOS (BL30K, MS)
SOTA
86.7
Jaccard (Mean)
· Extra Data
· 2022-12-13
Look Before You Match: Instance Understanding Matters in Video Object Segmentation
#3
XMem (BL30K, MS)
SOTA
86.3
Jaccard (Mean)
· Extra Data
· 2022-07-14
XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model
Code
#4
ISVOS (MS)
85.8
Jaccard (Mean)
· Extra Data
· 2022-12-13
Look Before You Match: Instance Understanding Matters in Video Object Segmentation
#5
Cutie+ (base, MEGA)
85.5
Jaccard (Mean)
· Extra Data
· 2023-10-19
Putting the Object Back into Video Object Segmentation
Code
#6
XMem (MS)
85.4
Jaccard (Mean)
· Extra Data
· 2022-07-14
XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model
Code
#7
JIMD
85.2
Jaccard (Mean)
· 2024-09-22
Memory Matching is not Enough: Jointly Improving Memory Matching and Decoding for Video Object Segmentation
#8
Cutie (base)
84.6
Jaccard (Mean)
· 2023-10-19
Putting the Object Back into Video Object Segmentation
Code
#9
ISVOS (BL30K)
84.5
Jaccard (Mean)
· Extra Data
· 2022-12-13
Look Before You Match: Instance Understanding Matters in Video Object Segmentation
#10
DEVA
84.2
Jaccard (Mean)
· Extra Data
· 2023-09-07
Tracking Anything with Decoupled Video Segmentation
Code
#11
SwinB-AOTv2-L (MS)
SOTA
84.2
Jaccard (Mean)
· 2022-03-22
Scalable Video Object Segmentation with Identification Mechanism
Code
#12
XMem (BL30K)
84
Jaccard (Mean)
· Extra Data
· 2022-07-14
XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model
Code
#13
SwinB-AOST (L'=3, MS)
83.8
Jaccard (Mean)
· 2022-03-22
Scalable Video Object Segmentation with Identification Mechanism
Code
#14
SwinB-AOTv2-L
83.1
Jaccard (Mean)
· 2022-03-22
Scalable Video Object Segmentation with Identification Mechanism
Code
#15
SwinB-DeAOT-L
83.1
Jaccard (Mean)
· 2022-10-18
Decoupling Features in Hierarchical Propagation for Video Object Segmentation
Code
#16
XMem
82.9
Jaccard (Mean)
· Extra Data
· 2022-07-14
XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model
Code
#17
RAVOS
82.9
Jaccard (Mean)
· Extra Data
· 2022-07-21
Region Aware Video Object Segmentation with Deep Motion Modeling
#18
R50-AOST (L'=3)
82.6
Jaccard (Mean)
· 2022-03-22
Scalable Video Object Segmentation with Identification Mechanism
Code
#19
QDMN
82.5
Jaccard (Mean)
· Extra Data
· 2022-07-16
Learning Quality-aware Dynamic Memory for Video Object Segmentation
Code
#20
R50-AOST (L'=2)
82.5
Jaccard (Mean)
· 2022-03-22
Scalable Video Object Segmentation with Identification Mechanism
Code
#21
SwinB-AOT-L
SOTA
82.4
Jaccard (Mean)
· 2021-06-04
Associating Objects with Transformers for Video Object Segmentation
Code
#22
R50-AOT-L
82.3
Jaccard (Mean)
· 2021-06-04
Associating Objects with Transformers for Video Object Segmentation
Code
#23
R50-DeAOT-L
82.2
Jaccard (Mean)
· 2022-10-18
Decoupling Features in Hierarchical Propagation for Video Object Segmentation
Code
#24
STCN
82
Jaccard (Mean)
· Extra Data
· 2021-06-09
Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation
Code
#25
HMMN
81.9
Jaccard (Mean)
· Extra Data
· 2021-09-23
Hierarchical Memory Matching Network for Video Object Segmentation
Code
#26
TarViS
81.7
Jaccard (Mean)
· Extra Data
· 2023-01-06
TarViS: A Unified Approach for Target-based Video Segmentation
Code
#27
MiVOS
SOTA
81.7
Jaccard (Mean)
· Extra Data
· 2021-03-14
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion
Code
#28
XMem (DAVIS and YouTubeVOS only)
81.4
Jaccard (Mean)
· Extra Data
· 2022-07-14
XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model
Code
#29
RPCMVOS
81.3
Jaccard (Mean)
· 2021-12-06
Reliable Propagation-Correction Modulation for Video Object Segmentation
Code
#30
R50-AOST (L'=1)
81.2
Jaccard (Mean)
· 2022-03-22
Scalable Video Object Segmentation with Identification Mechanism
Code
#31
AOT-L
81.1
Jaccard (Mean)
· 2021-06-04
Associating Objects with Transformers for Video Object Segmentation
Code
#32
DeAOT-L
81
Jaccard (Mean)
· 2022-10-18
Decoupling Features in Hierarchical Propagation for Video Object Segmentation
Code
#33
RMNet
81
Jaccard (Mean)
· 2021-03-24
Efficient Regional Memory Network for Video Object Segmentation
Code
#34
CFBI+
SOTA
80.1
Jaccard (Mean)
· 2020-10-13
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration
Code
#35
KMN
SOTA
80
Jaccard (Mean)
· 2020-07-16
Kernelized Memory Network for Video Object Segmentation
Code
#36
AOT-B
79.7
Jaccard (Mean)
· 2021-06-04
Associating Objects with Transformers for Video Object Segmentation
Code
#37
DeAOT-B
79.2
Jaccard (Mean)
· 2022-10-18
Decoupling Features in Hierarchical Propagation for Video Object Segmentation
Code
#38
STM
SOTA
79.2
Jaccard (Mean)
· Extra Data
· 2019-04-01
Video Object Segmentation using Space-Time Memory Networks
Code
#39
CFBI
79.1
Jaccard (Mean)
· 2020-03-18
Collaborative Video Object Segmentation by Foreground-Background Integration
Code
#40
AOT-S
78.7
Jaccard (Mean)
· 2021-06-04
Associating Objects with Transformers for Video Object Segmentation
Code
#41
DeAOT-S
77.8
Jaccard (Mean)
· 2022-10-18
Decoupling Features in Hierarchical Propagation for Video Object Segmentation
Code
#42
DeAOT-T
77.7
Jaccard (Mean)
· 2022-10-18
Decoupling Features in Hierarchical Propagation for Video Object Segmentation
Code
#43
AOT-T
77.4
Jaccard (Mean)
· 2021-06-04
Associating Objects with Transformers for Video Object Segmentation
Code
#44
JOINT
76
Jaccard (Mean)
· 2021-08-08
Joint Inductive and Transductive Learning for Video Object Segmentation
Code
#45
SSM-VOS
75.3
Jaccard (Mean)
No paper
Code
#46
SWEM
74.5
Jaccard (Mean)
· 2022-08-22
SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-Maximization
Code
#47
e-OSVOS
74.4
Jaccard (Mean)
· Extra Data
· 2020-12-03
Make One-Shot Video Object Segmentation Efficient Again
Code
#48
XMem (DAVIS only)
74.1
Jaccard (Mean)
· 2022-07-14
XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model
Code
#49
PReMVOS
SOTA
73.9
Jaccard (Mean)
· 2018-07-24
PReMVOS: Proposal-generation, Refinement and Merging for Video Object Segmentation
Code
#50
LSMVOS
73.9
Jaccard (Mean)
· 2020-09-02
LSMVOS: Long-Short-Term Similarity Matching for Video Object
Code
#51
MHP-VOS
73.4
Jaccard (Mean)
· 2019-04-17
MHP-VOS: Multiple Hypotheses Propagation for Video Object Segmentation
Code
#52
AFB-URR
73
Jaccard (Mean)
· 2020-10-15
Video Object Segmentation with Adaptive Feature Bank and Uncertain-Region Refinement
Code
#53
PTSNet
71.6
Jaccard (Mean)
· 2019-07-02
Proposal, Tracking and Segmentation (PTS): A Cascaded Network for Video Object Segmentation
Code
#54
DEVA (EntitySeg)
70.4
Jaccard (Mean)
· Extra Data
· 2023-09-07
Tracking Anything with Decoupled Video Segmentation
Code
#55
TVOS
69.9
Jaccard (Mean)
· 2020-04-15
A Transductive Approach for Video Object Segmentation
Code
#56
AGAME
68.5
Jaccard (Mean)
· 2018-11-28
A Generative Appearance Model for End-to-end Video Object Segmentation
Code
#57
MAMP
68.3
Jaccard (Mean)
· 2021-07-27
Self-Supervised Video Object Segmentation by Motion-Aware Mask Propagation
Code
#58
CINM
SOTA
67.2
Jaccard (Mean)
· 2018-03-26
CNN in MRF: Video Object Segmentation via Inference in A CNN-Based Higher-Order Spatio-Temporal MRF
#59
Araslanov et al.
67.1
Jaccard (Mean)
· 2021-11-11
Dense Unsupervised Learning for Video Segmentation
Code
#60
Propose-Reduce
67
Jaccard (Mean)
· Extra Data
· 2021-03-25
Video Instance Segmentation with a Propose-Reduce Paradigm
Code
#61
UnOVOST
66.4
Jaccard (Mean)
· 2020-01-15
UnOVOST: Unsupervised Offline Video Object Segmentation and Tracking
Code
#62
Siam R-CNN
66.1
Jaccard (Mean)
· 2019-11-28
Siam R-CNN: Visual Tracking by Re-Detection
Code
#63
RGMP
64.8
Jaccard (Mean)
No paper
Code
#64
OSVOS-S
SOTA
64.7
Jaccard (Mean)
· 2017-09-18
Video Object Segmentation Without Temporal Information
#65
AGSS-VOS
63.4
Jaccard (Mean)
No paper
Code
#66
MAST
63.3
Jaccard (Mean)
· 2020-02-18
MAST: A Memory-Augmented Self-supervised Tracker
Code
#67
MAST
63.3
Jaccard (Mean)
· Extra Data
· 2020-02-18
MAST: A Memory-Augmented Self-supervised Tracker
Code
#68
RANet
63.2
Jaccard (Mean)
· 2019-08-19
RANet: Ranking Attention Network for Fast Video Object Segmentation
Code
#69
OnAVOS
SOTA
61.6
Jaccard (Mean)
· 2017-06-28
Online Adaptation of Convolutional Neural Networks for Video Object Segmentation
#70
STEm-Seg
61.5
Jaccard (Mean)
· Extra Data
· 2020-03-18
STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos
Code
#71
Spatiotemporal CNN
58.7
Jaccard (Mean)
· 2019-04-04
Spatiotemporal CNN for Video Object Segmentation
Code
#72
VOSwL (Language)
58
Jaccard (Mean)
· 2018-03-21
Video Object Segmentation with Language Referring Expressions
#73
UVC
57.7
Jaccard (Mean)
· 2019-09-26
Joint-task Self-supervised Learning for Temporal Correspondence
Code
#74
RVOS
57.5
Jaccard (Mean)
· 2019-03-13
RVOS: End-to-End Recurrent Network for Video Object Segmentation
Code
#75
MATNet
56.7
Jaccard (Mean)
No paper
Code
#76
OSVOS
SOTA
56.6
Jaccard (Mean)
· 2016-11-16
One-Shot Video Object Segmentation
Code
#77
ALBA
56.6
Jaccard (Mean)
· 2020-05-26
ALBA : Reinforcement Learning for Video Object Segmentation
Code
#78
VideoMatch
56.5
Jaccard (Mean)
· 2018-09-04
VideoMatch: Matching based Video Object Segmentation
#79
AGS
55.5
Jaccard (Mean)
· Extra Data
No paper
Code
#80
FAVOS
54.6
Jaccard (Mean)
· 2018-06-06
Fast and Accurate Online Video Object Segmentation via Tracking Parts
Code
#81
SiamMask
54.3
Jaccard (Mean)
· 2018-12-12
Fast Online Object Tracking and Segmentation: A Unifying Approach
Code
#82
MuG-W
54.1
Jaccard (Mean)
· 2020-03-10
Learning Video Object Segmentation from Unlabeled Videos
Code
#83
PDB
53.2
Jaccard (Mean)
No paper
#84
OSMN
52.5
Jaccard (Mean)
· 2018-02-04
Efficient Video Object Segmentation via Network Modulation
Code
#85
CorrFlow
48.4
Jaccard (Mean)
· 2019-05-02
Self-supervised Learning for Video Correspondence Flow
Code
#86
CycleTime
46.4
Jaccard (Mean)
· 2019-03-18
Learning Correspondence from the Cycle-Consistency of Time
Code
#87
RVOS
36.8
Jaccard (Mean)
· 2019-03-13
RVOS: End-to-End Recurrent Network for Video Object Segmentation
Code