Metric: STQ (higher is better)
| # | Model↕ | STQ▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | UniVS(Swin-L) | 58.2 | Yes | UniVS: Unified and Universal Video Segmentation ... | 2024-02-28 | Code |
| 2 | CAVIS(VIT-L) | 56.1 | No | Context-Aware Video Instance Segmentation | 2024-07-03 | Code |
| 3 | DVIS++(VIT-L) | 56 | No | DVIS++: Improved Decoupled Framework for Univers... | 2023-12-20 | Code |
| 4 | DVIS(Swin-L) | 55.3 | No | DVIS: Decoupled Video Instance Segmentation Fram... | 2023-06-06 | Code |
| 5 | TarViS (Swin-L) | 52.9 | Yes | TarViS: A Unified Approach for Target-based Vide... | 2023-01-06 | Code |
| 6 | DEVA (Mask2Former - SwinB) | 52.2 | Yes | Tracking Anything with Decoupled Video Segmentat... | 2023-09-07 | Code |
| 7 | Tube-Link(Swin-base) | 49.4 | No | Tube-Link: A Flexible Cross Tube Framework for U... | 2023-03-22 | Code |
| 8 | TarViS (Swin-T) | 45.3 | Yes | TarViS: A Unified Approach for Target-based Vide... | 2023-01-06 | Code |
| 9 | TarViS (ResNet-50) | 43.1 | Yes | TarViS: A Unified Approach for Target-based Vide... | 2023-01-06 | Code |