Single Object Tracking on LaSOT (test)
75.3mIoUQwen3-VL-235B + IPLoc-ID
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Qwen3-VL-235B + IPLoc-IDN-shot=82026.07 | 75.3 | 98.6 | |
| Qwen3-VL-235B + IPLocN-shot=82026.07 | 74.2 | 66.7 | |
| Qwen3-VL-32B + IPLoc-IDN-shot=82026.07 | 72.9 | 99.6 | |
| Qwen3-VL-32B + IPLocN-shot=82026.07 | 72.8 | 66.7 | |
| Qwen3-VL-32B + IPLoc-IDN-shot=42026.07 | 72.3 | 98.5 | |
| Qwen3-VL-235B + IPLoc-IDN-shot=42026.07 | 71.8 | 98.2 | |
| Qwen3-VL-32B + IPLocN-shot=42026.07 | 71.6 | 66.7 | |
| Qwen3-VL-8B + IPLoc-IDN-shot=82026.07 | 71.4 | 99.3 | |
| Qwen3-VL-8B + IPLocN-shot=82026.07 | 71.1 | 66.7 | |
| Qwen3-VL-235B + IPLocN-shot=42026.07 | 70.4 | 66.7 | |
| Qwen3-VL-32B + IPLocN-shot=22026.07 | 70.2 | 66.7 | |
| Qwen3-VL-32B + IPLoc-IDN-shot=22026.07 | 70.1 | 96.8 | |
| Qwen3-VL-8B + IPLoc-IDN-shot=42026.07 | 69.8 | 98.2 | |
| Qwen3-VL-8B + IPLocN-shot=42026.07 | 69.4 | 66.7 | |
| Qwen3-VL-235B + IPLocN-shot=22026.07 | 69.1 | 66.7 | |
| Qwen3-VL-235B + IPLoc-IDN-shot=22026.07 | 68.6 | 96.7 | |
| Qwen3-VL-8B + IPLocN-shot=22026.07 | 67.5 | 66.7 | |
| Qwen3-VL-8B + IPLoc-IDN-shot=22026.07 | 67.3 | 97.3 | |
| Qwen3-VL-235B + IPLoc-IDN-shot=12026.07 | 65.2 | 95.6 | |
| Qwen3-VL-32B + IPLocN-shot=12026.07 | 65 | 66.8 | |
| Qwen3-VL-235B + IPLocN-shot=12026.07 | 64.6 | 66.5 | |
| (FSOD) No-Time-To-TrainN-shot=12026.07 | 64.4 | 66.3 | |
| Qwen3-VL-32B + IPLoc-IDN-shot=12026.07 | 63.9 | 95 | |
| Qwen3-VL-8B + IPLoc-IDN-shot=12026.07 | 63.7 | 92.4 | |
| Qwen3-VL-8B + IPLocN-shot=12026.07 | 63.2 | 66.7 | |
| (FSOD) No-Time-To-TrainN-shot=22026.07 | 62.7 | 65.7 | |
| (FSOD) No-Time-To-TrainN-shot=42026.07 | 61.8 | 66 | |
| (FSOD) VFMN-shot=42026.07 | 61.7 | 66.2 | |
| (FSOD) No-Time-To-TrainN-shot=82026.07 | 61.7 | 65.7 | |
| (FSOD) VFMN-shot=12026.07 | 60.5 | 65.6 | |
| (FSOD) VFMN-shot=82026.07 | 60.1 | 66.5 | |
| (FSOD) VFMN-shot=22026.07 | 59.3 | 66.5 | |
| Qwen3-VL-235BN-shot=82026.07 | 58.8 | 93.5 | |
| Qwen3-VL-32BN-shot=82026.07 | 58.5 | 92.7 | |
| Qwen3-VL-235BN-shot=42026.07 | 58.4 | 88.4 | |
| Qwen2-VL-7B + IPLocN-shot=82026.07 | 58 | 66.7 | |
| Qwen2-VL-7B + IPLoc-IDN-shot=82026.07 | 58 | 98.5 | |
| Qwen3-VL-32BN-shot=42026.07 | 57.2 | 88.3 | |
| Qwen2-VL-7B + IPLoc-IDN-shot=42026.07 | 57.1 | 97.3 | |
| Qwen2-VL-7B + IPLocN-shot=42026.07 | 56.1 | 66.7 | |
| Qwen3-VL-32BN-shot=22026.07 | 56.1 | 88.9 | |
| Qwen3-VL-235BN-shot=22026.07 | 56.1 | 84 | |
| Qwen3-VL-8BN-shot=82026.07 | 55.9 | 77.1 | |
| Qwen3-VL-8BN-shot=22026.07 | 55.8 | 77.9 | |
| Qwen3-VL-8BN-shot=42026.07 | 55.2 | 81 | |
| IPLoc 7B (official)N-shot=42026.07 | 54.1 | 66.3 | |
| Qwen3-VL-32BN-shot=12026.07 | 54.1 | 83.5 | |
| Qwen2-VL-7B + IPLocN-shot=22026.07 | 53.6 | 66.6 | |
| Qwen2-VL-7B + IPLoc-IDN-shot=22026.07 | 53.5 | 96.3 | |
| IPLoc 7B (official)N-shot=22026.07 | 52.9 | 66.3 | |
| IPLoc 7B (official)N-shot=82026.07 | 52.7 | 65.9 | |
| IPLoc 7B (official)N-shot=12026.07 | 51.5 | 65.2 | |
| Qwen3-VL-8BN-shot=12026.07 | 51.1 | 74.6 | |
| Qwen2-VL-7B + IPLoc-IDN-shot=12026.07 | 50.3 | 94.3 | |
| Qwen2-VL-7B + IPLocN-shot=12026.07 | 50.1 | 66.7 | |
| Gemma3-12B + IPLoc-IDN-shot=82026.07 | 45 | 94.6 | |
| Gemma3-12B + IPLocN-shot=82026.07 | 44.4 | 66.6 | |
| Gemma3-12B + IPLoc-IDN-shot=22026.07 | 44.2 | 93.9 | |
| Qwen3-VL-235BN-shot=12026.07 | 43 | 86.6 | |
| Gemma3-12B + IPLoc-IDN-shot=42026.07 | 42.2 | 92 | |
| Gemma3-12B + IPLocN-shot=42026.07 | 40.6 | 66.6 | |
| Gemma3-12B + IPLocN-shot=22026.07 | 39.5 | 66.6 | |
| Gemma3-12B + IPLoc-IDN-shot=12026.07 | 38.2 | 92.9 | |
| Gemma3-12B + IPLocN-shot=12026.07 | 37.7 | 66.7 | |
| Qwen2-VL-7BN-shot=82026.07 | 31.9 | 48.8 | |
| (OD) Florence-2N-shot=12026.07 | 30.6 | 51.1 | |
| Qwen2-VL-7BN-shot=22026.07 | 30.6 | 48.9 | |
| Qwen2-VL-7BN-shot=42026.07 | 29.7 | 42.6 | |
| Qwen2-VL-7BN-shot=12026.07 | 24.7 | 58.4 | |
| (OD) Grounding-DINON-shot=12026.07 | 22.2 | 41.6 | |
| Gemma3-12B (+ prompt)N-shot=42026.07 | 20.9 | 79.5 | |
| Gemma3-12B (+ prompt)N-shot=22026.07 | 18.5 | 84.3 | |
| LLaVA1.5-7B + promptN-shot=22026.07 | 15.9 | 62.4 | |
| Gemma3-12B (+ prompt)N-shot=82026.07 | 14 | 53.5 | |
| Gemma3-12B (+ prompt)N-shot=12026.07 | 13.9 | 86.9 | |
| LLaVA1.5-7B + promptN-shot=42026.07 | 11.1 | 52.4 | |
| LLaVA1.5-7B + promptN-shot=12026.07 | 0.5 | 6.5 | |
| LLaVA1.5-7B + promptN-shot=82026.07 | 0 | 1.4 |