Referring Video Object Segmentation and Point-to-Mask Tracking on DAVIS
52.7F-measureLLaVA-OV-2-8B
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| LLaVA-OV-2-8BParameter count=8B, Conversion=point-to-mask via SAM 22026.05 | 52.7 | 44.7 | 58.7 | |
| Qwen3-VL-8BParameter count=8B2026.05 | 39.7 | 36.6 | 41.3 | |
| Keye-VL-1.52026.05 | 14.6 | 12.2 | 5.8 | |
| InternVL3.5-8BParameter count=8B2026.05 | 12.8 | 9.4 | 4.7 | |
| LLaVA-OV-1.52026.05 | 11.9 | 8.8 | 4.1 | |
| PLM-8BParameter count=8B2026.05 | 7.8 | 32.8 | 2 |