List your company

Video Object Segmentation on YouTube-VOS S

74.1J & F-MeanDINOv3
33.12443.76254.465.038Mar 15, 2026

Evaluation results

MethodLinks
DINOv3Param.=7B, Patch Size=16, Input Resolution=480px (short side)2026.0374.1
DINOv3 ViT-H+Param.=0.8B, Patch Size=16, Input Resolution=480px (short side)2026.0374
V-JEPA 2.1 ViT-GParam.=2B, Patch Size=16, Input Resolution=480px (short side)2026.0372.7
V-JEPA 2.1 ViT-gParam.=1B, Patch Size=16, Input Resolution=480px (short side)2026.0372.3
AM-RADIOv2.5Param.=1B, Patch Size=14, Input Resolution=420px (short side)2026.0370.1
PEspatialParam.=2B, Patch Size=14, Input Resolution=420px (short side)2026.0368.5
DINOv2Param.=1B, Patch Size=14, Input Resolution=420px (short side)2026.0365.6
V-JEPA2 ViT-gParam.=1B, Patch Size=16, Input Resolution=480px (short side)2026.0353.7
SigLIP 2Param.=1B, Patch Size=16, Input Resolution=480px (short side)2026.0352
InternVideo2-1BParam.=1B, Patch Size=14, Input Resolution=420px (short side)2026.0351.2
Web-DINOParam.=7B, Patch Size=14, Input Resolution=420px (short side)2026.0343.9
PEcoreParam.=2B, Patch Size=14, Input Resolution=420px (short side)2026.0334.7