OpenCodePapers
video-instance-segmentation-on-youtube-vis-2022-validation
Video Segmentation
Video Instance Segmentation
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Show papers without code
Paper
Code
mAP_L
↕
AP50_L
↕
AP75_L
↕
AR1_L
↕
AR10_L
↕
ModelName
ReleaseDate
↕
DVIS++: Improved Decoupled Framework for Universal Video Segmentation
✓ Link
50.9
75.7
52.8
40.6
55.8
DVIS++(VIT-L)
2023-12-20
Context-Aware Video Instance Segmentation
✓ Link
48.6
CAVIS (VIT-L)
2024-07-03
CTVIS: Consistent Training for Online Video Instance Segmentation
✓ Link
46.4
CTVIS (Swin-L)
2023-07-24
DVIS: Decoupled Video Instance Segmentation Framework
✓ Link
45.9
69.0
48.8
37.2
51.8
DVIS(Swin-L)
2023-06-06
VidEoMT: Your ViT is Secretly Also a Video Segmentation Model
✓ Link
42.6
VidEoMT (extra data)
2026-02-19
DVIS-DAQ: Improving Video Segmentation via Dynamic Anchor Queries
✓ Link
42.0
DVIS-DAQ ViT-L (online) (extra data)
2024-03-29
CTVIS: Consistent Training for Online Video Instance Segmentation
✓ Link
39.4
CTVIS (ResNet-50)
2023-07-24
InstanceFormer: An Online Video Instance Segmentation Framework
✓ Link
26.3
44.6
27.3
25.0
29.2
InstanceFormer (Swin)
2022-08-22
InstanceFormer: An Online Video Instance Segmentation Framework
✓ Link
24.8
49.5
26.7
23.9
30.1
InstanceFormer (Resnet-50)
2022-08-22
×