| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| DAVIS | SAM2-Base+ (Reference) | J&F Score88.61 | 41 | 1mo ago | |
| INRIA Instructional Videos | KNN + GMM + GT | F1 Score69.2 | 10 | 3mo ago | |
| MoRiBo Human-in-the-Wild track | SAMIV | Overlap Precision51.5 | 7 | 2mo ago | |
| MoRiBo Robotic Manipulation track | SAMIV | Overlap Precision (P)69.5 | 7 | 2mo ago | |
| YTSeg 10–<30 min duration (test) | AudioSeg | F1 Score51.4 | 5 | 3mo ago | |
| YTSeg <10 min duration (test) | AudioSeg | F1 Score50.01 | 5 | 3mo ago | |
| FLARE 2022 (test) | Temporal | Liver97.65 | 5 | 3mo ago | |
| Real-world video dataset Full Sequence iPhone 13 and Canon camera collection | ∆YNAMICS + Motion Reasoning + CMA-ES | Segmentation Map IoU65 | 4 | 13d ago | |
| Real-world video dataset First Frame iPhone 13 and Canon camera collection | ∆YNAMICS + Motion Reasoning + Best@32 | Segmentation Map IoU72 | 4 | 13d ago | |
| YTSeg 30–<60 min duration (test) | MiniSeg | F1 Score21.89 | 4 | 3mo ago | |
| 140 Gestalt videos | GenMatter | Accuracy94 | 3 | 1mo ago | |
| YTSeg ≥60 min duration (test) | MiniSeg | F1 Score15.17 | 3 | 3mo ago | |
| UniBench Dataset | UnityVideo | mIoU68.82 | 3 | 3mo ago |