| Paper | Code | mIoU | ModelName | ReleaseDate |
|---|---|---|---|---|
| LVMT: Video Mask Transformer for Long-term Video Segmentation | ✓ Link | 66.4 | LVMT ViT-L (DINOv3) | 2026-09-29 |
| PMT: Plain Mask Transformer for Image and Video Segmentation with Frozen Vision Encoders | ✓ Link | 65.7 | PMT-L (DINOv3-L frozen, online VSS) (extra data) | 2026-03-26 |
| VidEoMT: Your ViT is Secretly Also a Video Segmentation Model | ✓ Link | 64.9 | VidEoMT (extra data) | 2026-02-19 |
| DVIS++: Improved Decoupled Framework for Universal Video Segmentation | ✓ Link | 63.8 | DVIS++(VIT-L) | 2023-12-20 |
| UniVS: Unified and Universal Video Segmentation with Prompts as Queries | ✓ Link | 59.8 | UniVS(Swin-L) | 2024-02-28 |
| Tube-Link: A Flexible Cross Tube Framework for Universal Video Segmentation | ✓ Link | 59.6 | Tube-Link(Swin-large) | 2023-03-22 |
| Mining Relations among Cross-Frame Affinities for Video Semantic Segmentation | ✓ Link | 49.9 | MRCFA(MiT-B5) | 2022-07-21 |
| Learning Local and Global Temporal Contexts for Video Semantic Segmentation | ✓ Link | 49.3 | CFFM(MiT-B5) | 2022-04-07 |