Video Object Segmentation on Long-RVOS
Metric: vIoU (higher is better)
Metric: vIoU (higher is better)
| # | Model↕ | vIoU▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | ReferMo | 42.6 | No | Long-RVOS: A Comprehensive Benchmark for Long-te... | 2025-05-19 | - |
| 2 | ReferDINO | 41.2 | No | ReferDINO: Referring Video Object Segmentation w... | 2025-01-24 | - |
| 3 | MUTR | 36.2 | No | Referred by Multi-Modality: A Unified Temporal T... | 2023-05-25 | Code |
| 4 | GLUS | 34.6 | No | GLUS: Global-Local Reasoning Unified into A Sing... | 2025-04-10 | Code |
| 5 | SAMWISE | 28.6 | No | SAMWISE: Infusing Wisdom in SAM2 for Text-Driven... | 2024-11-26 | Code |
| 6 | SOC | 28.6 | No | SOC: Semantic-Assisted Object Cluster for Referr... | 2023-05-26 | Code |
| 7 | VideoLISA | 28.2 | No | One Token to Seg Them All: Language Instructed R... | 2024-09-29 | Code |