Video Object Segmentation on DAVIS 2017
Metric: J&F (higher is better)
Metric: J&F (higher is better)
| # | Model↕ | J&F▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | ViTAE-T-Stage | 82.5 | No | ViTAE: Vision Transformer Advanced by Exploring ... | 2021-06-07 | Code |
| 2 | FEELVOS | 71.55 | No | FEELVOS: Fast End-to-End Embedding Learning for ... | 2019-02-25 | Code |
| 3 | DINO (ViT-B/8, ImageNet retrain) | 71.4 | No | Emerging Properties in Self-Supervised Vision Tr... | 2021-04-29 | Code |
| 4 | VOSwL (Mask+Language) | 62.2 | No | Video Object Segmentation with Language Referrin... | 2018-03-21 | - |