Multi-sound source localization on MUSIC-Duet (test)
82.7CIoU@0.3Generation-Analysis-Refinement
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| Generation-Analysis-RefinementModel category=MLLMs, N iterations=52026.04 | 82.7 | 56.7 | — | 53.2 | |
| Generation-Analysis-RefinementModel category=MLLMs, N iterations=32026.04 | 80.8 | 54.7 | — | 51.4 | |
| Qwen2.5-OmniModel category=MLLMs2026.04 | 50.6 | 47.2 | — | 40.8 | |
| OA-SSLModel category=Vision Model2026.04 | 45.9 | 61.4 | — | 36.1 | |
| T-VSLEncoders=AudioCLIP (ResNet-50 + ESResNeXt)2024.04 | 43.2 | 62.9 | — | 35.9 | |
| AVGNEncoders=AudioCLIP pre-trained2024.04 | 39.3 | 59.2 | — | 32.4 | |
| DSOLEncoders=AudioCLIP pre-trained2024.04 | 38.8 | — | — | 31.3 | |
| Proposed Method2024.03 | 38.6 | 52.1 | 72.5 | 30.1 | |
| NoPriorModel category=Vision Model2026.04 | 38.6 | 52.1 | — | 30.1 | |
| AlignmentEncoders=AudioCLIP pre-trained2024.04 | 38.3 | 57.8 | — | 30.9 | |
| Mix-and-LocalizeEncoders=AudioCLIP pre-trained2024.04 | 38.1 | 57.4 | — | 30.7 | |
| FNACEncoders=AudioCLIP pre-trained2024.04 | 37.9 | 57.3 | — | 30.6 | |
| AudioCLIPEncoders=AudioCLIP pre-trained2024.04 | 36.9 | 56.1 | — | 29.2 | |
| MarginNCEEncoders=AudioCLIP pre-trained2024.04 | 36.1 | 55.1 | — | 28.5 | |
| EZ-VSLEncoders=AudioCLIP pre-trained2024.04 | 34.3 | — | — | 26.7 | |
| LVSEncoders=AudioCLIP pre-trained2024.04 | 33.1 | — | — | 26.9 | |
| AVGN2024.03 | 32.5 | 50.6 | 57.2 | 24.6 | |
| AVGNModel category=Vision Model2026.04 | 32.5 | 50.6 | — | 24.6 | |
| Wav2CLIPEncoders=AudioCLIP pre-trained2024.04 | 32.2 | 52.6 | — | 27.2 | |
| CoarsetoFineEncoders=AudioCLIP pre-trained2024.04 | 31.8 | — | — | 24.1 | |
| DSOL2024.03 | 30.1 | — | — | 22.3 | |
| OTSEncoders=AudioCLIP pre-trained2024.04 | 29.4 | 51.2 | — | 24.3 | |
| MiniCPM-oModel category=MLLMs2026.04 | 27.7 | 29.3 | — | 23.6 | |
| Mix-and-Localize2024.03 | 26.5 | 47.5 | 54.1 | 21.5 | |
| Mix-and-LocalizeModel category=Vision Model2026.04 | 26.5 | 47.5 | — | 21.5 | |
| EZ-VSL2024.03 | 24.3 | — | — | 21.3 | |
| EZ-VSLModel category=Vision Model2026.04 | 24.3 | — | — | 21.3 | |
| LVS2024.03 | 22.5 | — | — | 20.9 | |
| Attention10k2024.03 | 21.6 | — | — | 19.6 | |
| Attention 10kModel category=Vision Model2026.04 | 21.6 | — | — | 19.6 | |
| InteractiveOmniModel category=MLLMs2026.04 | 20 | 28.8 | — | 17 | |
| CoarseToFIne2024.03 | 17.6 | — | — | 20.6 | |
| CoarseToFineModel category=Vision Model2026.04 | 17.6 | — | — | 20.6 | |
| DMC2024.03 | 17.5 | — | — | 21.1 | |
| DMCModel category=Vision Model2026.04 | 17.5 | — | — | 21.1 | |
| OTS2024.03 | 13.3 | 11.6 | 17.7 | 18.5 | |
| OTSModel category=Vision Model2026.04 | 13.3 | 11.6 | — | 18.5 |