Video Multimodal Interpretation on OVIS (val)
28.7APSG-FSCFormer
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| SG-FSCFormerMask Decoder=SAM22026.03 | 28.7 | 51.4 | 29.1 | |
| VideoGLaMMMask Decoder=SAM22026.03 | 28 | 49.3 | 26.9 | |
| SG-FSCFormerMask Decoder=Mask2Former2026.03 | 27.8 | 49 | 27.2 | |
| SG-FSCFormer†Mask Decoder=SAM2, Evaluation Protocol=instance-level AP2026.03 | 27.5 | 48.6 | 26.7 | |
| GLEEMask Decoder=MaskDINO2026.03 | 27.1 | 45.4 | 26.3 | |
| OW-VISCapMask Decoder=Mask2Former2026.03 | 25.4 | 48.8 | 22.8 | |
| OVFormerMask Decoder=Mask2Former2026.03 | 21.3 | 38.5 | 20.8 |