In-Context Object Localization on LaSOT ICL
65.6mIoUFOCUS
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| FOCUSShots=4-shot2026.05 | 65.6 | — | |
| FOCUSShots=2-shot2026.05 | 59.9 | — | |
| IPLoc (7B)Shots=4-shot2026.05 | 59.4 | — | |
| IPLoc (7B)Shots=2-shot2026.05 | 57.1 | — | |
| FOCUSShots=1-shot2026.05 | 56.1 | — | |
| Qwen2-VL-72BShots=4-shot2026.05 | 55.4 | — | |
| InternVL2-76BShots=4-shot2026.05 | 52.5 | — | |
| Qwen2-VL-72BShots=1-shot2026.05 | 51.9 | — | |
| Qwen2-VL-72BShots=2-shot2026.05 | 50.7 | — | |
| IPLoc (7B)Shots=1-shot2026.05 | 49.7 | — | |
| InternVL2-76BShots=2-shot2026.05 | 47.3 | — | |
| InternVL2-76BShots=1-shot2026.05 | 44.2 | — | |
| Qwen2-VL-7BShots=1-shot2026.05 | 26.2 | — | |
| Qwen2-VL-7BShots=4-shot2026.05 | 25 | — | |
| Pixtral-12BShots=4-shot2026.05 | 22.4 | — | |
| Qwen2-VL-7BShots=2-shot2026.05 | 22.3 | — | |
| LLaVA-OVShots=4-shot2026.05 | 17.7 | — | |
| Idefics3Shots=4-shot2026.05 | 14.7 | — | |
| LLaVA-OVShots=2-shot2026.05 | 14.1 | — | |
| LLaVA-OVShots=1-shot2026.05 | 10.8 | — | |
| Idefics3Shots=2-shot2026.05 | 8.7 | — | |
| Pixtral-12BShots=2-shot2026.05 | 7.6 | — | |
| Pixtral-12BShots=1-shot2026.05 | 4.6 | — | |
| Idefics3Shots=1-shot2026.05 | 3.6 | — | |
| FOCUSShots=Overall2026.05 | — | 67.7 | |
| Idefics3Shots=Overall2026.05 | — | 15.2 | |
| InternVL2-76BShots=Overall2026.05 | — | 56.1 | |
| IPLoc (7B)Shots=Overall2026.05 | — | 58.8 | |
| LLaVA-OVShots=Overall2026.05 | — | 23 | |
| Pixtral-12BShots=Overall2026.05 | — | 15.5 | |
| Qwen2-VL-72BShots=Overall2026.05 | — | 55 | |
| Qwen2-VL-7BShots=Overall2026.05 | — | 31.1 |