Video Object Segmentation On Davis 2017
評価指標
mIoU
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
モデル名 | mIoU | Paper Title | Repository |
|---|---|---|---|
| UniTrack | 58.4 | Do Different Tracking Tasks Require Different Appearance Models? | |
| VOSwL (Mask+Language) | 59 | Video Object Segmentation with Language Referring Expressions | - |
| AOC-MF (val) | - | Towards Robust Video Object Segmentation with Adaptive Object Calibration | |
| DINO (ViT-B/8, ImageNet retrain) | - | Emerging Properties in Self-Supervised Vision Transformers | |
| ViTAE-T-Stage | - | ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias |
0 of 5 row(s) selected.