Metric: Precision@0.9 (higher is better)
| # | Model↕ | Precision@0.9▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | HINet | 0.4 | No | - | - | - |
| 2 | VLIDE | 0.3 | No | Deeply Interleaved Two-Stream Encoder for Referr... | 2022-03-30 | - |
| 3 | SgMg (Video-Swin-B) | 0.003 | Yes | Spectrum-guided Multi-granularity Referring Vide... | 2023-07-25 | Code |
| 4 | ClawCraneNet | 0.002 | No | ClawCraneNet: Leveraging Object-level Relation f... | 2021-03-19 | - |
| 5 | SOC (Video-Swin-B) | 0.001 | Yes | SOC: Semantic-Assisted Object Cluster for Referr... | 2023-05-26 | Code |
| 6 | SOC (Video-Swin-T) | 0.001 | No | SOC: Semantic-Assisted Object Cluster for Referr... | 2023-05-26 | Code |
| 7 | MTTR (w=10) | 0.001 | No | End-to-End Referring Video Object Segmentation w... | 2021-11-29 | Code |
| 8 | MTTR (w=8) | 0.001 | No | End-to-End Referring Video Object Segmentation w... | 2021-11-29 | Code |
| 9 | PRPE | 0.001 | No | - | - | - |
| 10 | CMSA+CFSA | 0.001 | No | Referring Segmentation in Images and Videos with... | 2021-02-09 | - |
| 11 | CMPC-V | 0 | No | - | - | Code |
| 12 | Hui et al. | 0 | No | - | - | - |
| 13 | AAMN | 0 | No | - | - | - |
| 14 | CMDy | 0 | No | - | - | - |
| 15 | ACGA | 0 | No | - | - | Code |
| 16 | Gavrilyuk et al. (Optical flow) | 0 | No | - | - | Code |
| 17 | VT-Capsule | 0 | No | - | - | - |
| 18 | Gavrilyuk et al. | 0 | No | - | - | Code |
| 19 | Hu et al. | 0 | No | - | - | Code |
| 20 | Li et al. | 0 | No | - | - | - |
| 21 | RefVOS | 0 | No | - | - | - |