Video Instance Segmentation on YouTube-VIS 2022
35.3AP50S2D
Evaluation results
| Method | Links | ||
|---|---|---|---|
| S2DTraining Data=13K Real Videos, Evaluation Protocol=Zero-Shot2025.12 | 35.3 | 16.4 | |
| VideoCutLERTraining Data=1.3M Syn. Videos, Evaluation Protocol=Zero-Shot2025.12 | 31.7 | 15 |