Tasks
SotA
Datasets
Papers
Methods
Submit
About
SotA
/
Computer Vision
/
Video
/
DAVIS (no YouTube-VOS training)
Video on DAVIS (no YouTube-VOS training)
Metric: FPS (higher is better)
Leaderboard
Dataset
Loading chart...
Results
Submit a result
Export CSV
Sort:
FPS (best first)
FPS (worst first)
Date (newest first)
Date (oldest first)
Model name (A→Z)
#
Model
↕
FPS
▼
Extra Data
Paper
Date
↕
Code
1
TBD
50.1
No
Tackling Background Distraction in Video Object ...
2022-07-14
Code
2
BMVOS
45.9
No
Pixel-Level Bijective Matching for Video Object ...
2021-10-04
Code
3
AOT-S
40
No
Associating Objects with Transformers for Video ...
2021-06-04
Code
4
TVOS
37
No
A Transductive Approach for Video Object Segment...
2020-04-15
Code
5
SWEM
36
No
SWEM: Towards Real-Time Video Object Segmentatio...
2022-08-22
Code
6
RANet
30.3
No
RANet: Ranking Attention Network for Fast Video ...
2019-08-19
Code
7
XMem
29.6
No
XMem: Long-Term Video Object Segmentation with a...
2022-07-14
Code
8
GC
25
No
Fast Video Object Segmentation using the Global ...
2020-01-30
Code
9
FRTM
21.9
No
Learning Fast and Robust Target Models for Video...
2020-02-27
Code
10
DTN
14.3
No
-
-
-
11
LWL
14
No
Learning What to Learn for Video Object Segmenta...
2020-03-25
Code
12
RMNet
11.9
No
Efficient Regional Memory Network for Video Obje...
2021-03-24
Code
13
HMMN
10
No
Hierarchical Memory Matching Network for Video O...
2021-09-23
Code
14
AGSS-VOS
10
No
-
-
Code
15
LCM
8.47
No
Learning Position and Target Consistency for Mem...
2021-04-09
-
16
KMN
8.33
No
Kernelized Memory Network for Video Object Segme...
2020-07-16
Code
17
STM
6.25
No
Video Object Segmentation using Space-Time Memor...
2019-04-01
Code
18
CFBI
5.56
No
Collaborative Video Object Segmentation by Foreg...
2020-03-18
Code
19
JOINT
4
No
Joint Inductive and Transductive Learning for Vi...
2021-08-08
Code
20
AFB-URR
4
No
Video Object Segmentation with Adaptive Feature ...
2020-10-15
Code
21
FEELVOS
2.22
No
FEELVOS: Fast End-to-End Embedding Learning for ...
2019-02-25
Code
22
DIPNet
0.92
No
-
-
-
23
STCNN
0.26
No
Spatiotemporal CNN for Video Object Segmentation
2019-04-04
Code
#1
TBD
SOTA
50.1
FPS
· 2022-07-14
Tackling Background Distraction in Video Object Segmentation
Code
#2
BMVOS
SOTA
45.9
FPS
· 2021-10-04
Pixel-Level Bijective Matching for Video Object Segmentation
Code
#3
AOT-S
SOTA
40
FPS
· 2021-06-04
Associating Objects with Transformers for Video Object Segmentation
Code
#4
TVOS
SOTA
37
FPS
· 2020-04-15
A Transductive Approach for Video Object Segmentation
Code
#5
SWEM
36
FPS
· 2022-08-22
SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-Maximization
Code
#6
RANet
SOTA
30.3
FPS
· 2019-08-19
RANet: Ranking Attention Network for Fast Video Object Segmentation
Code
#7
XMem
29.6
FPS
· 2022-07-14
XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model
Code
#8
GC
25
FPS
· 2020-01-30
Fast Video Object Segmentation using the Global Context Module
Code
#9
FRTM
21.9
FPS
· 2020-02-27
Learning Fast and Robust Target Models for Video Object Segmentation
Code
#10
DTN
14.3
FPS
No paper
#11
LWL
14
FPS
· 2020-03-25
Learning What to Learn for Video Object Segmentation
Code
#12
RMNet
11.9
FPS
· 2021-03-24
Efficient Regional Memory Network for Video Object Segmentation
Code
#13
HMMN
10
FPS
· 2021-09-23
Hierarchical Memory Matching Network for Video Object Segmentation
Code
#14
AGSS-VOS
10
FPS
No paper
Code
#15
LCM
8.47
FPS
· 2021-04-09
Learning Position and Target Consistency for Memory-based Video Object Segmentation
#16
KMN
8.33
FPS
· 2020-07-16
Kernelized Memory Network for Video Object Segmentation
Code
#17
STM
SOTA
6.25
FPS
· 2019-04-01
Video Object Segmentation using Space-Time Memory Networks
Code
#18
CFBI
5.56
FPS
· 2020-03-18
Collaborative Video Object Segmentation by Foreground-Background Integration
Code
#19
JOINT
4
FPS
· 2021-08-08
Joint Inductive and Transductive Learning for Video Object Segmentation
Code
#20
AFB-URR
4
FPS
· 2020-10-15
Video Object Segmentation with Adaptive Feature Bank and Uncertain-Region Refinement
Code
#21
FEELVOS
SOTA
2.22
FPS
· 2019-02-25
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation
Code
#22
DIPNet
0.92
FPS
No paper
#23
STCNN
0.26
FPS
· 2019-04-04
Spatiotemporal CNN for Video Object Segmentation
Code