|
CAVIS(VIT-L, Offline)
|
Context-Aware Video Instance Segmentation
|
87.30
|
2024-07-03
|
|
|
DVIS++(VIT-L, Offline)
|
DVIS++: Improved Decoupled Framework for Universa…
|
86.70
|
2023-12-20
|
|
|
DVIS-DAQ(VIT-L, Offline)
|
DVIS-DAQ: Improving Video Segmentation via Dynami…
|
86.10
|
2024-03-29
|
|
|
RefineVIS (Swin-L, online)
|
RefineVIS: Video Instance Segmentation with Tempo…
|
84.10
|
2023-06-07
|
|
|
DVIS(Swin-L)
|
DVIS: Decoupled Video Instance Segmentation Frame…
|
83.00
|
2023-06-06
|
|
|
DVIS++(VIT-L, Online)
|
DVIS++: Improved Decoupled Framework for Universa…
|
82.70
|
2023-12-20
|
|
|
NOVIS (Swin-L)
|
NOVIS: A Case for End-to-End Near-Online Video In…
|
82.00
|
2023-08-29
|
|
|
TarViS (Swin-L)
|
TarViS: A Unified Approach for Target-based Video…
|
81.40
|
2023-01-06
|
|
|
GRAtt-VIS (Swin-L)
|
GRAtt-VIS: Gated Residual Attention for Auto Rect…
|
81.30
|
2023-05-26
|
|
|
GenVIS (Swin-L)
|
A Generalized Framework for Video Instance Segmen…
|
80.90
|
2022-11-16
|
|
|
IDOL (Swin-L)
|
In Defense of Online Models for Video Instance Se…
|
80.80
|
2022-07-21
|
|
|
MDQE(Swin-L)
|
MDQE: Mining Discriminative Query Embeddings to S…
|
80.70
|
2023-03-25
|
|
|
VITA (Swin-L)
|
VITA: Video Instance Segmentation via Object Toke…
|
80.60
|
2022-06-09
|
|
|
Tube-Link(Swin-L)
|
Tube-Link: A Flexible Cross Tube Framework for Un…
|
79.40
|
2023-03-22
|
|
|
UniVS(Swin-L)
|
UniVS: Unified and Universal Video Segmentation w…
|
79.40
|
2024-02-28
|
|
|
DeVIS (Swin-L)
|
DeVIS: Making Deformable Transformers Work for Vi…
|
77.70
|
2022-07-22
|
|
|
MinVIS (Swin-L)
|
MinVIS: A Minimal Video Instance Segmentation Fra…
|
76.60
|
2022-08-03
|
|
|
BoxVIS(Swin-L & Box-sup)
|
BoxVIS: Video Instance Segmentation with Box Anno…
|
76.40
|
2023-03-26
|
|
|
InstanceFormer (Swin-L)
|
InstanceFormer: An Online Video Instance Segmenta…
|
73.70
|
2022-08-22
|
|
|
TarViS (Swin-T)
|
TarViS: A Unified Approach for Target-based Video…
|
71.60
|
2023-01-06
|
|
|
TarViS (ResNet-50)
|
TarViS: A Unified Approach for Target-based Video…
|
69.60
|
2023-01-06
|
|
|
NOVIS (ResNet-50)
|
NOVIS: A Case for End-to-End Near-Online Video In…
|
69.40
|
2023-08-29
|
|
|
GRAtt-VIS (ResNet-50)
|
GRAtt-VIS: Gated Residual Attention for Auto Rect…
|
69.20
|
2023-05-26
|
|
|
DeVIS (ResNet-50)
|
DeVIS: Making Deformable Transformers Work for Vi…
|
66.80
|
2022-07-22
|
|
|
InstanceFormer (ResNet-50)
|
InstanceFormer: An Online Video Instance Segmenta…
|
62.40
|
2022-08-22
|
|
|
STMask(R101-DCN-FPN)
|
Spatial Feature Calibration and Temporal Fusion f…
|
54.00
|
2021-04-06
|
|