Linguistic Promptable Video Object Segmentation on Uni-RARP50
90.5J&FUniSurgSAM
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| UniSurgSAMSetting=Online, Modality=Textual2026.04 | 90.5 | 89.4 | 91.6 | 55 | |
| UniSurgSAMSetting=Online, Modality=Audio2026.04 | 89.8 | 88.7 | 90.8 | 53 | |
| ResurgSAM2Setting=Online, Modality=Textual2026.04 | 84.9 | 83.8 | 86 | 58 | |
| SAMWISESetting=Semi-online, Modality=Textual2026.04 | 82.5 | 81.7 | 83.2 | 12 | |
| ReferFormerSetting=Offline, Modality=Textual2026.04 | 81.7 | 80.6 | 82.8 | 42 | |
| RefSAMSetting=Online, Modality=Textual2026.04 | 78.4 | 78.3 | 78.4 | 25 | |
| SurgRefSetting=Offline, Modality=Textual2026.04 | 76.2 | 75.3 | 77.1 | 40 | |
| MUTRSetting=Offline, Modality=Textual2026.04 | 74.5 | 73.3 | 75.6 | 32 | |
| OnlineReferSetting=Online, Modality=Textual2026.04 | 73.9 | 72.3 | 75.4 | 26 | |
| RSVISSetting=Semi-online, Modality=Textual2026.04 | 72.4 | 71.7 | 73 | 28 |