Referring Video Object Segmentation on JHMDB Sentences
46.6mAPReferDINO
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| ReferDINOBackbone=Swin-B2025.01 | 46.6 | 74.2 | 73.2 | |
| LMPM++Backbone=Video-Swin-Base2025.12 | 46.2 | 74.8 | 73.4 | |
| DsHmpBackbone=Swin-B2025.01 | 45.8 | 73.9 | 73 | |
| DsHmpBackbone=Video-Swin-Base2025.12 | 45.8 | 73.9 | 73 | |
| ReferDINOBackbone=Swin-T2025.01 | 45.6 | 74.2 | 73.1 | |
| G-DINO-SHBackbone=Swin-B2025.01 | 45.5 | 74.2 | 72.7 | |
| G-DINO-DHBackbone=Swin-B2025.01 | 45.3 | 74.1 | 73.2 | |
| LMPM++Backbone=Video-Swin-Tiny2025.12 | 45.3 | 73.4 | 72.4 | |
| G-DINO-DHBackbone=Swin-T2025.01 | 45.1 | 73.2 | 71.8 | |
| SgMgBackbone=Swin-B2025.01 | 45 | 73.7 | 72.5 | |
| SgMgBackbone=Video-Swin-Base2025.12 | 45 | 73.7 | 72.5 | |
| DsHmpBackbone=Swin-T2025.01 | 44.9 | 73.1 | 72.1 | |
| DsHmpBackbone=Video-Swin-Tiny2025.12 | 44.9 | 73.1 | 72.1 | |
| G-DINO-SHBackbone=Swin-T2025.01 | 44.6 | 72.7 | 71.6 | |
| SOCBackbone=Swin-B2025.01 | 44.6 | 73.6 | 72.3 | |
| SOCBackbone=Video-Swin-Base2025.12 | 44.6 | 73.6 | 72.3 | |
| SgMgBackbone=Swin-T2025.01 | 44.4 | 72.8 | 71.7 | |
| SgMgBackbone=Video-Swin-Tiny2025.12 | 44.4 | 72.8 | 71.7 | |
| HTMLBackbone=Swin-B2025.01 | 44.2 | — | — | |
| HTMLBackbone=Video-Swin-Base2025.12 | 44.2 | — | — | |
| ReferFormerBackbone=Swin-B2025.01 | 43.7 | 73 | 71.8 | |
| ReferFormerBackbone=Video-Swin-Base2025.12 | 43.7 | 73 | 71.8 | |
| HTMLBackbone=Swin-T2025.01 | 42.7 | — | — | |
| SOCBackbone=Swin-T2025.01 | 42.7 | 72.7 | 71.6 | |
| HTMLBackbone=Video-Swin-Tiny2025.12 | 42.7 | — | — | |
| SOCBackbone=Video-Swin-Tiny2025.12 | 42.7 | 72.7 | 71.6 | |
| ReferFormerBackbone=Swin-T2025.01 | 42.2 | 71.9 | 71 | |
| ReferFormerBackbone=Video-Swin-Tiny2025.12 | 42.2 | 71.9 | 71 | |
| MTTRBackbone=Video-Swin-Tiny2025.12 | 39.2 | 70.1 | 69.8 | |
| OnlineReferBackbone=Video-Swin-Base2025.12 | — | 73.5 | 71.9 |