| Paper | Code | Jaccard (Mean) | mIoU | J&F | F-Score | ModelName | ReleaseDate |
|---|---|---|---|---|---|---|---|
| Towards Robust Video Object Segmentation with Adaptive Object Calibration | ✓ Link | 81.7 | 85.9 | AOC-MF (val) | 2022-07-02 | ||
| ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias | ✓ Link | 79.4 | 82.5 | 85.5 | ViTAE-T-Stage | 2021-06-07 | |
| Video Object Segmentation with Language Referring Expressions | 59 | 62.2 | VOSwL (Mask+Language) | 2018-03-21 | |||
| Do Different Tracking Tasks Require Different Appearance Models? | ✓ Link | 58.4 | UniTrack | 2021-07-05 | |||
| Emerging Properties in Self-Supervised Vision Transformers | ✓ Link | 71.4 | DINO (ViT-B/8, ImageNet retrain) | 2021-04-29 |