Referring Video Object Segmentation and Point-to-Mask Tracking on REVOS Reasoning
27.4F-MeasureLLaVA-OV-2-8B
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| LLaVA-OV-2-8BParameter count=8B, Conversion=point-to-mask via SAM 22026.05 | 27.4 | 22.5 | 29.2 | |
| Qwen3-VL-8BParameter count=8B2026.05 | 24.7 | 32.4 | 21.9 | |
| Keye-VL-1.52026.05 | 9.9 | 12 | 9.6 | |
| InternVL3.5-8BParameter count=8B2026.05 | 7.9 | 7.2 | 9.2 | |
| LLaVA-OV-1.52026.05 | 6.2 | 17.8 | 9.7 | |
| PLM-8BParameter count=8B2026.05 | 0.1 | 0.1 | 10.2 |