Video Object Segmentation on PanoVOS (test)
73.4J&F ScorePanoSAM2
Evaluation Results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| PanoSAM2Backbone=Hiera-S, Video Specification Category=360-Video-Specified2026.04 | 73.4 | 67.9 | 84 | 64.4 | 77.4 | — | — | |
| PanoSAM2Backbone=Hiera-T, Video Specification Category=360-Video-Specified2026.04 | 71.9 | 64.8 | 80.5 | 64.3 | 77.8 | — | — | |
| SAM2LongBackbone=Hiera-T, Video Specification Category=Perspective-Video-Specified2026.04 | 70.9 | 62.8 | 79.7 | 64.2 | 76.9 | — | — | |
| SAM2Backbone=Hiera-T, Video Specification Category=Perspective-Video-Specified2026.04 | 70.6 | 62.3 | 79.8 | 63.8 | 76.5 | — | — | |
| SAM2LongBackbone=Hiera-S, Video Specification Category=Perspective-Video-Specified2026.04 | 69.7 | 63.1 | 78.6 | 62.8 | 74.3 | — | — | |
| SAM2Backbone=Hiera-S, Video Specification Category=Perspective-Video-Specified2026.04 | 69.3 | 62.7 | 78 | 62.5 | 74 | — | — | |
| PanoSAM2Pre-trained on=360VOTS2026.04 | 67.9 | — | — | — | — | 61.6 | 74.2 | |
| SAM2Pre-trained on=360VOTS2026.04 | 66.3 | — | — | — | — | 59.4 | 73.2 | |
| PSCFormerPre-trained on=360VOTS2026.04 | 64.1 | — | — | — | — | 58.3 | 69.9 | |
| PSCFormer-LBackbone=ResNet-50, Video Specification Category=360-Video-Specified2026.04 | 59.9 | 54.9 | 69.2 | 53 | 62.4 | — | — | |
| PSCFormer-BBackbone=ResNet-50, Video Specification Category=360-Video-Specified2026.04 | 56.8 | 49.4 | 62.7 | 52.4 | 62.5 | — | — | |
| AOTSBackbone=MobileNet-V2, Video Specification Category=Perspective-Video-Specified2026.04 | 55.9 | 53.2 | 65.1 | 48.6 | 57 | — | — | |
| AOTBBackbone=MobileNet-V2, Video Specification Category=Perspective-Video-Specified2026.04 | 55.4 | 53.5 | 64.2 | 47.7 | 56 | — | — | |
| AOTLBackbone=ResNet-50, Video Specification Category=Perspective-Video-Specified2026.04 | 54.6 | 52.9 | 63.2 | 47.5 | 54.9 | — | — | |
| AOTLBackbone=MobileNet-V2, Video Specification Category=Perspective-Video-Specified2026.04 | 53.8 | 50 | 60.3 | 47.8 | 57.1 | — | — | |
| XMemBackbone=ResNet-50, Video Specification Category=Perspective-Video-Specified2026.04 | 53.5 | 49.5 | 62.6 | 47.1 | 54.8 | — | — | |
| AOTTBackbone=MobileNet-V2, Video Specification Category=Perspective-Video-Specified2026.04 | 53.4 | 49.3 | 61.6 | 47.5 | 55.1 | — | — | |
| AOTLBackbone=Swin-Base, Video Specification Category=Perspective-Video-Specified2026.04 | 53.1 | 49 | 57.8 | 49 | 56.6 | — | — | |
| STCNBackbone=ResNet-50, Video Specification Category=Perspective-Video-Specified2026.04 | 50.8 | 43.6 | 56.5 | 49.3 | 53.7 | — | — | |
| XMemPre-trained on=360VOTS2026.04 | 44.4 | — | — | — | — | 39.6 | 49.1 | |
| RDEBackbone=ResNet-50, Video Specification Category=Perspective-Video-Specified2026.04 | 42.5 | 36.9 | 46.6 | 38.5 | 48.2 | — | — | |
| SAM-PTPre-trained on=360VOTS2026.04 | 41 | — | — | — | — | 35.7 | 46.4 | |
| SAM-I2VPre-trained on=360VOTS2026.04 | 40.5 | — | — | — | — | 34.9 | 46.1 | |
| AFB-URRBackbone=ResNet-50, Video Specification Category=Perspective-Video-Specified2026.04 | 34.2 | 28.2 | 38.8 | 32.9 | 36.8 | — | — | |
| CFBI+Backbone=ResNet-101, Video Specification Category=Perspective-Video-Specified2026.04 | 30.9 | 30.8 | 42.7 | 21.4 | 28.5 | — | — | |
| PerSAMPre-trained on=360VOTS2026.04 | 19.5 | — | — | — | — | 15.6 | 23.3 | |
| CFBIBackbone=ResNet-101, Video Specification Category=Perspective-Video-Specified2026.04 | 19.1 | 18.2 | 26.1 | 12.2 | 19.8 | — | — |