Video Object Segmentation on PanoVOS (val)
78.1J&F ScorePanoSAM2
Evaluation results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| PanoSAM2Backbone=Hiera-S, Video Specification Category=360-Video-Specified2026.04 | 78.1 | 71.2 | 85.6 | 69.1 | 86.7 | — | — | |
| PSCFormer-LBackbone=ResNet-50, Video Specification Category=360-Video-Specified2026.04 | 77.9 | 70.5 | 85.2 | 69.5 | 86.4 | — | — | |
| PanoSAM2Backbone=Hiera-T, Video Specification Category=360-Video-Specified2026.04 | 76.1 | 67.4 | 83.4 | 68.6 | 85.6 | — | — | |
| SAM2LongBackbone=Hiera-T, Video Specification Category=Perspective-Video-Specified2026.04 | 74.4 | 63.7 | 78.6 | 69.3 | 86.1 | — | — | |
| SAM2Backbone=Hiera-T, Video Specification Category=Perspective-Video-Specified2026.04 | 74.2 | 64.5 | 79.4 | 68 | 85 | — | — | |
| PSCFormer-BBackbone=ResNet-50, Video Specification Category=360-Video-Specified2026.04 | 74 | 66.4 | 80.4 | 66.2 | 83 | — | — | |
| SAM2LongBackbone=Hiera-S, Video Specification Category=Perspective-Video-Specified2026.04 | 71.9 | 62.6 | 78 | 69.8 | 81.2 | — | — | |
| SAM2Backbone=Hiera-S, Video Specification Category=Perspective-Video-Specified2026.04 | 71.4 | 62.3 | 77.6 | 65.2 | 80.3 | — | — | |
| PanoSAM2Pre-trained on=360VOTS2026.04 | 71.3 | — | — | — | — | 63 | 79.5 | |
| SAM2Pre-trained on=360VOTS2026.04 | 70.6 | — | — | — | — | 63.4 | 77.8 | |
| PSCFormerPre-trained on=360VOTS2026.04 | 69.5 | — | — | — | — | 62.4 | 76.5 | |
| AOTSBackbone=MobileNet-V2, Video Specification Category=Perspective-Video-Specified2026.04 | 67.7 | 61.2 | 70 | 62.4 | 77.1 | — | — | |
| AOTBBackbone=MobileNet-V2, Video Specification Category=Perspective-Video-Specified2026.04 | 67.6 | 62.3 | 72 | 61.5 | 74.8 | — | — | |
| AOTLBackbone=MobileNet-V2, Video Specification Category=Perspective-Video-Specified2026.04 | 66.6 | 61.4 | 71.1 | 59.4 | 74.3 | — | — | |
| AOTTBackbone=MobileNet-V2, Video Specification Category=Perspective-Video-Specified2026.04 | 65.6 | 59.4 | 68.3 | 59.7 | 75 | — | — | |
| AOTLBackbone=ResNet-50, Video Specification Category=Perspective-Video-Specified2026.04 | 65.3 | 61.9 | 71.4 | 56.4 | 71.6 | — | — | |
| AOTLBackbone=Swin-Base, Video Specification Category=Perspective-Video-Specified2026.04 | 62.1 | 58.9 | 66.5 | 54.3 | 68.8 | — | — | |
| XMemBackbone=ResNet-50, Video Specification Category=Perspective-Video-Specified2026.04 | 55.7 | 54.8 | 63.3 | 45.2 | 59.7 | — | — | |
| XMemPre-trained on=360VOTS2026.04 | 52.1 | — | — | — | — | 46.9 | 57.2 | |
| STCNBackbone=ResNet-50, Video Specification Category=Perspective-Video-Specified2026.04 | 52 | 51.2 | 60.8 | 41.5 | 54.5 | — | — | |
| RDEBackbone=ResNet-50, Video Specification Category=Perspective-Video-Specified2026.04 | 50.5 | 49.7 | 58.4 | 39.2 | 54.9 | — | — | |
| SAM-I2VPre-trained on=360VOTS2026.04 | 48.9 | — | — | — | — | 42.8 | 55 | |
| SAM-PTPre-trained on=360VOTS2026.04 | 47.5 | — | — | — | — | 41.4 | 53.7 | |
| CFBI+Backbone=ResNet-101, Video Specification Category=Perspective-Video-Specified2026.04 | 41.3 | 38 | 47.9 | 32.5 | 46.9 | — | — | |
| CFBIBackbone=ResNet-101, Video Specification Category=Perspective-Video-Specified2026.04 | 35.8 | 34.6 | 44.8 | 24.2 | 39.7 | — | — | |
| AFB-URRBackbone=ResNet-50, Video Specification Category=Perspective-Video-Specified2026.04 | 34.3 | 34.8 | 42.8 | 24.9 | 34.5 | — | — | |
| PerSAMPre-trained on=360VOTS2026.04 | 19.1 | — | — | — | — | 14.9 | 23.5 |