Generic Object Tracking on GOT-10K (mIoU/F1)
86.9mIoUQwen3-VL-235B + IPLoc-ID
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Qwen3-VL-235B + IPLoc-IDN-shot=82026.07 | 86.9 | 100 | |
| Qwen3-VL-235B + IPLocN-shot=82026.07 | 86 | 66.7 | |
| Qwen3-VL-32B + IPLoc-IDN-shot=82026.07 | 85.4 | 99.7 | |
| Qwen3-VL-32B + IPLocN-shot=82026.07 | 84.2 | 66.7 | |
| Qwen3-VL-8B + IPLocN-shot=82026.07 | 83.6 | 66.7 | |
| Qwen3-VL-8B + IPLoc-IDN-shot=82026.07 | 82.8 | 99.7 | |
| Qwen3-VL-235B + IPLocN-shot=42026.07 | 80.6 | 66.8 | |
| Qwen3-VL-32B + IPLocN-shot=42026.07 | 79.6 | 66.7 | |
| Qwen3-VL-235B + IPLoc-IDN-shot=22026.07 | 79.5 | 97.4 | |
| Qwen3-VL-235B + IPLoc-IDN-shot=42026.07 | 79.5 | 93.5 | |
| Qwen3-VL-8B + IPLocN-shot=42026.07 | 78.6 | 66.7 | |
| Qwen3-VL-8B + IPLoc-IDN-shot=42026.07 | 78.5 | 97.3 | |
| Qwen3-VL-235B + IPLocN-shot=22026.07 | 78.5 | 66.7 | |
| Qwen3-VL-32B + IPLoc-IDN-shot=42026.07 | 77.7 | 98.2 | |
| Qwen3-VL-8B + IPLoc-IDN-shot=22026.07 | 77.2 | 96.7 | |
| Qwen3-VL-8B + IPLocN-shot=22026.07 | 77.1 | 66.7 | |
| (FSOD) No-Time-To-TrainN-shot=42026.07 | 76.9 | 67.2 | |
| (FSOD) No-Time-To-TrainN-shot=82026.07 | 76.9 | 67 | |
| (FSOD) No-Time-To-TrainN-shot=22026.07 | 76.8 | 67 | |
| (FSOD) VFMN-shot=82026.07 | 76.4 | 96 | |
| Qwen3-VL-235B + IPLoc-IDN-shot=12026.07 | 76.4 | 100 | |
| Qwen3-VL-8B + IPLocN-shot=12026.07 | 76.3 | 66.7 | |
| (FSOD) No-Time-To-TrainN-shot=12026.07 | 76.2 | 67.2 | |
| Qwen3-VL-32B + IPLocN-shot=22026.07 | 75.6 | 66.4 | |
| Qwen3-VL-8B + IPLoc-IDN-shot=12026.07 | 74.7 | 94.3 | |
| Qwen3-VL-32B + IPLoc-IDN-shot=22026.07 | 74.2 | 98.6 | |
| Qwen3-VL-32B + IPLocN-shot=12026.07 | 73.8 | 66.8 | |
| Qwen3-VL-32B + IPLoc-IDN-shot=12026.07 | 73.8 | 99.3 | |
| Qwen3-VL-235BN-shot=82026.07 | 73.7 | 92.9 | |
| (FSOD) VFMN-shot=42026.07 | 73.6 | 94.6 | |
| Qwen3-VL-235B + IPLocN-shot=12026.07 | 73.6 | 66.7 | |
| (FSOD) VFMN-shot=22026.07 | 71.7 | 94.6 | |
| Qwen3-VL-32BN-shot=22026.07 | 69.3 | 94.9 | |
| Qwen3-VL-8BN-shot=22026.07 | 69 | 98.3 | |
| Qwen3-VL-32BN-shot=12026.07 | 68.6 | 94.7 | |
| (FSOD) VFMN-shot=12026.07 | 68 | 94.2 | |
| Qwen3-VL-8BN-shot=82026.07 | 67.6 | 98.5 | |
| Qwen3-VL-32BN-shot=42026.07 | 67.1 | 95.6 | |
| Qwen3-VL-235BN-shot=22026.07 | 67.1 | 91.6 | |
| Qwen3-VL-32BN-shot=82026.07 | 66.8 | 98.3 | |
| Qwen3-VL-8BN-shot=12026.07 | 66.7 | 96.7 | |
| Qwen3-VL-8BN-shot=42026.07 | 64.9 | 98.9 | |
| Qwen2-VL-7B + IPLoc-IDN-shot=82026.07 | 64.3 | 99.7 | |
| Qwen2-VL-7B + IPLocN-shot=82026.07 | 63.4 | 66.7 | |
| Qwen3-VL-235BN-shot=42026.07 | 62.5 | 91.5 | |
| Qwen3-VL-235BN-shot=12026.07 | 61.6 | 95.1 | |
| Gemma3-12B + IPLoc-IDN-shot=82026.07 | 60.7 | 97.2 | |
| IPLoc 7B (official)N-shot=82026.07 | 58.7 | 66.8 | |
| Gemma3-12B + IPLocN-shot=82026.07 | 57.2 | 66.7 | |
| Qwen2-VL-7B + IPLoc-IDN-shot=42026.07 | 57 | 94.4 | |
| Qwen2-VL-7B + IPLocN-shot=42026.07 | 55.8 | 66.7 | |
| Gemma3-12B + IPLoc-IDN-shot=22026.07 | 53.4 | 94 | |
| Qwen2-VL-7B + IPLoc-IDN-shot=22026.07 | 53.2 | 94.9 | |
| Qwen2-VL-7B + IPLocN-shot=22026.07 | 52.7 | 66.7 | |
| IPLoc 7B (official)N-shot=42026.07 | 51.6 | 66.8 | |
| Gemma3-12B + IPLocN-shot=42026.07 | 51.1 | 66.6 | |
| Gemma3-12B + IPLocN-shot=12026.07 | 50.4 | 66.7 | |
| Gemma3-12B + IPLoc-IDN-shot=12026.07 | 50.4 | 94.2 | |
| Gemma3-12B + IPLoc-IDN-shot=42026.07 | 50.4 | 91 | |
| IPLoc 7B (official)N-shot=22026.07 | 50.1 | 67.7 | |
| Qwen2-VL-7B + IPLocN-shot=12026.07 | 49.7 | 66.7 | |
| Qwen2-VL-7B + IPLoc-IDN-shot=12026.07 | 49.6 | 97 | |
| Gemma3-12B + IPLocN-shot=22026.07 | 48.5 | 66.7 | |
| IPLoc 7B (official)N-shot=12026.07 | 48.1 | 67.5 | |
| Qwen2-VL-7BN-shot=82026.07 | 43.4 | 66.9 | |
| Gemma3-12B (+ prompt)N-shot=82026.07 | 29.5 | 75.1 | |
| Qwen2-VL-7BN-shot=42026.07 | 27.4 | 41.4 | |
| Qwen2-VL-7BN-shot=22026.07 | 23.5 | 60.2 | |
| Gemma3-12B (+ prompt)N-shot=42026.07 | 23.4 | 89.9 | |
| Qwen2-VL-7BN-shot=12026.07 | 23.1 | 73.1 | |
| Gemma3-12B (+ prompt)N-shot=12026.07 | 20.1 | 96.6 | |
| Gemma3-12B (+ prompt)N-shot=22026.07 | 19.8 | 92.2 | |
| LLaVA1.5-7B + promptN-shot=22026.07 | 13.9 | 52.9 | |
| LLaVA1.5-7B + promptN-shot=42026.07 | 8.2 | 41 | |
| (OD) Florence-2N-shot=12026.07 | 3.9 | 11.5 | |
| (OD) Grounding-DINON-shot=12026.07 | 1.2 | 5.4 | |
| LLaVA1.5-7B + promptN-shot=12026.07 | 0 | 0 | |
| LLaVA1.5-7B + promptN-shot=82026.07 | 0 | 4.3 |