Referring Video Object Segmentation on YoURVOS (test)
34.6J&FOMFormer
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| OMFormerYear=2025, Venue=Ours, Backbone (L)=RoBERTa-base, Backbone (V)=Video-Swin-T2026.03 | 34.6 | 34.3 | 34.9 | 45.7 | |
| OMFormerYear=2025, Venue=Ours, Backbone (L)=RoBERTa-base, Backbone (V)=ResNet-502026.03 | 33.7 | 33.6 | 33.8 | 44.9 | |
| ReferDINOYear=2025, Venue=ICCV, Backbone (L)=BERT-base, Backbone (V)=Swin-B2026.03 | 27 | 26.7 | 27.4 | 35.1 | |
| AL-Ref-SAM 2Year=2025, Venue=AAAI, Backbone (L)=GPT-4, Backbone (V)=SAM-V22026.03 | 26.3 | 26.2 | 26.3 | 34.4 | |
| MUTRYear=2024, Venue=AAAI, Backbone (L)=RoBERTa-base, Backbone (V)=Swin-L2026.03 | 26.2 | 25.9 | 26.5 | 35.1 | |
| HTRYear=2024, Venue=T-CSVT, Backbone (L)=RoBERTa, Backbone (V)=Swin-L2026.03 | 26.1 | 26.2 | 26.1 | 34.1 | |
| VRS-HQYear=2025, Venue=CVPR, Backbone (L)=Chat-UniVi-7B, Backbone (V)=SAM-V2-L2026.03 | 25.9 | 25.9 | 25.8 | 35.4 | |
| VISAYear=2024, Venue=ECCV, Backbone (L)=Chat-UniVi-7B, Backbone (V)=SAM-V1-H2026.03 | 25.8 | 25.8 | 25.7 | 36.4 | |
| MUTRYear=2024, Venue=AAAI, Backbone (L)=RoBERTa-base, Backbone (V)=Video-Swin-B2026.03 | 25.7 | 25.5 | 26 | 34.6 | |
| SgMgYear=2023, Venue=ICCV, Backbone (L)=RoBERTa-base, Backbone (V)=Video-Swin-B2026.03 | 25.3 | 25.1 | 25.5 | 34.7 | |
| VD-ITYear=2024, Venue=ECCV, Backbone (L)=RoBERTa-base, Backbone (V)=Video Diffusion2026.03 | 25.2 | 25 | 25.4 | 34.4 | |
| OnlineReferYear=2023, Venue=ICCV, Backbone (L)=RoBERTa-base, Backbone (V)=Swin-L2026.03 | 25 | 24.4 | 25.6 | 34.9 | |
| ReferFormerYear=2022, Venue=CVPR, Backbone (L)=RoBERTa-base, Backbone (V)=Swin-L2026.03 | 24.9 | 24.6 | 25.2 | 34.4 | |
| R2-VOSYear=2023, Venue=ICCV, Backbone (L)=RoBERTa-base, Backbone (V)=ResNet-502026.03 | 24.9 | 25 | 24.9 | 35.3 | |
| UNINEXTYear=2023, Venue=CVPR, Backbone (L)=BERT-base, Backbone (V)=ViT-H2026.03 | 24.8 | 24.4 | 25.2 | 32.6 | |
| ReferFormerYear=2022, Venue=CVPR, Backbone (L)=RoBERTa-base, Backbone (V)=Video-Swin-B2026.03 | 24.6 | 24.3 | 24.8 | 34.5 | |
| Video LAVTYear=2024, Venue=T-PAMI, Backbone (L)=BERT-base, Backbone (V)=Video-Swin-B2026.03 | 24.5 | 23.9 | 25.2 | 33.7 | |
| InstructSegYear=2025, Venue=ICCV, Backbone (L)=Mipha-3B, Backbone (V)=Swin-B2026.03 | 24.4 | 24.1 | 24.6 | 32.6 | |
| SgMgYear=2023, Venue=ICCV, Backbone (L)=RoBERTa-base, Backbone (V)=Video-Swin-T2026.03 | 24.3 | 24.1 | 24.5 | 34.4 | |
| UNINEXTYear=2023, Venue=CVPR, Backbone (L)=BERT-base, Backbone (V)=Conv-L2026.03 | 24.2 | 23.9 | 24.5 | 32.6 | |
| SOCYear=2023, Venue=NeurIPS, Backbone (L)=RoBERTa-base, Backbone (V)=Video-Swin-B2026.03 | 24.2 | 23.8 | 24.6 | 33.6 | |
| Video LAVTYear=2024, Venue=T-PAMI, Backbone (L)=BERT-base, Backbone (V)=Video-Swin-S2026.03 | 23.9 | 23.4 | 24.5 | 33.6 | |
| SOCYear=2023, Venue=NeurIPS, Backbone (L)=RoBERTa-base, Backbone (V)=Video-Swin-T2026.03 | 23.5 | 23.2 | 23.8 | 34.4 | |
| MUTRYear=2024, Venue=AAAI, Backbone (L)=RoBERTa-base, Backbone (V)=ResNet-1012026.03 | 23.3 | 23.1 | 23.4 | 33.7 | |
| MUTRYear=2024, Venue=AAAI, Backbone (L)=RoBERTa-base, Backbone (V)=Video-Swin-T2026.03 | 23.2 | 23.1 | 23.4 | 33.5 | |
| UNINEXTYear=2023, Venue=CVPR, Backbone (L)=BERT-base, Backbone (V)=ResNet-502026.03 | 23.1 | 22.9 | 23.3 | 32.6 | |
| ReferFormerYear=2022, Venue=CVPR, Backbone (L)=RoBERTa-base, Backbone (V)=Video-Swin-T2026.03 | 23 | 22.8 | 23.1 | 33.7 | |
| ReferFormerYear=2022, Venue=CVPR, Backbone (L)=RoBERTa-base, Backbone (V)=Swin-T2026.03 | 22.6 | 22.7 | 22.6 | 34.1 | |
| OnlineReferYear=2023, Venue=ICCV, Backbone (L)=RoBERTa-base, Backbone (V)=ResNet-502026.03 | 22.5 | 22.4 | 22.5 | 33.8 | |
| MUTRYear=2024, Venue=AAAI, Backbone (L)=RoBERTa-base, Backbone (V)=ResNet-502026.03 | 22.4 | 22.3 | 22.6 | 33.3 | |
| Video LAVTYear=2024, Venue=T-PAMI, Backbone (L)=BERT-base, Backbone (V)=Video-Swin-T2026.03 | 22.4 | 22.3 | 22.5 | 33.2 | |
| ReferFormerYear=2022, Venue=CVPR, Backbone (L)=RoBERTa-base, Backbone (V)=ResNet-1012026.03 | 22.3 | 22.2 | 22.3 | 33.4 | |
| SAMWISEYear=2025, Venue=CVPR, Backbone (L)=RoBERTa-base, Backbone (V)=SAM-V2-B+2026.03 | 22.2 | 22.3 | 22.2 | 33 | |
| DEVAYear=2023, Venue=ICCV, Backbone (L)=BERT-base, Backbone (V)=Swin-L2026.03 | 21.9 | 21.6 | 22.2 | 33.6 | |
| MTTRYear=2022, Venue=CVPR, Backbone (L)=RoBERTa-base, Backbone (V)=Video-Swin-T2026.03 | 21.4 | 21.3 | 21.6 | 33.6 | |
| DsHmpYear=2024, Venue=CVPR, Backbone (L)=RoBERTa-base, Backbone (V)=Video-Swin-T2026.03 | 21 | 20.7 | 21.3 | 33.5 | |
| VideoLISAYear=2024, Venue=NeurIPS, Backbone (L)=Phi-3.8B, Backbone (V)=SAM-V1-H2026.03 | 20.9 | 20.8 | 21 | 32.7 | |
| LBDTYear=2022, Venue=CVPR, Backbone (L)=LSTM, Backbone (V)=ResNet-502026.03 | 14.6 | 14.6 | 14.5 | 32.6 | |
| LMPMYear=2023, Venue=ICCV, Backbone (L)=RoBERTa-base, Backbone (V)=Swin-T2026.03 | 13 | 12.8 | 13.3 | 21.9 | |
| ReferFormerYear=2022, Venue=CVPR, Backbone (L)=RoBERTa-base, Backbone (V)=ResNet-502026.03 | 12 | 12.1 | 11.9 | 32.2 |