Referring Video Object Segmentation on AR2-4FV Bench
77.3P@0.5AR2-4FV
Evaluation Results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| AR2-4FVBackbone=CLIP2026.03 | 77.3 | 72.2 | 64.1 | 49.2 | 2.6 | 49.2 | 66.9 | |
| DUTrackBackbone=ViT-B2026.03 | 76.5 | 71.2 | 62.8 | 44.5 | 1.5 | 46.5 | 63.7 | |
| UVLTrackBackbone=ViT-B2026.03 | 75.8 | 70.5 | 61.3 | 45.1 | 1.5 | 45.8 | 63.5 | |
| OnlineReferBackbone=Video-Swin-B2026.03 | 75.4 | 71.4 | 63.6 | 48.5 | 0.8 | 46.1 | 64.2 | |
| VideoLISABackbone=ViT-H2026.03 | 74.8 | 70.5 | 61.6 | 44.9 | 1.3 | 45.5 | 62.1 | |
| JointNLTBackbone=ResNet-502026.03 | 74.2 | 69.8 | 59.5 | 42.1 | 0.8 | 43.5 | 61.9 | |
| SSABackbone=CLIP2026.03 | 73.6 | 70.3 | 62.4 | 47.1 | 1.4 | 45.2 | 64 | |
| DsHmpBackbone=Video-Swin-T2026.03 | 72.6 | 69.1 | 60.4 | 44.3 | 1.4 | 45 | 63.8 | |
| MTTRBackbone=Video-Swin-T2026.03 | 72.1 | 68 | 60.3 | 45.6 | 1.2 | 44.6 | 64.1 | |
| ReferFormerBackbone=Video-Swin-T2026.03 | 70.5 | 66.9 | 58.8 | 42.7 | 0.9 | 42.8 | 62.9 | |
| SOCBackbone=Video-Swin-T2026.03 | 69.2 | 65.8 | 57.2 | 41.5 | 0.7 | 41.7 | 61.6 |