List your company

Single-source sound localization on VGGSound single-source (test)

60.2IoU@0.5Generation-Analysis-Refinement
17.5628.6339.750.77Mar 26, 2024Jul 27, 2024Nov 28, 2024Apr 1, 2025Aug 3, 2025Dec 5, 2025Apr 8, 2026

Evaluation results

MethodLinks
Generation-Analysis-RefinementN (Number of iterations in Stage 2)=52026.0460.260.555.2
Generation-Analysis-RefinementN (Number of iterations in Stage 2)=32026.0460.160.255
T-VSLMethod Category=Ours2024.0453.748.152.9
AlignmentMethod Category=Current SOTA Based Methods, Pre-trained Encoders=AudioCLIP2024.0450.845.350.2
AVGNMethod Category=Current SOTA Based Methods, Pre-trained Encoders=AudioCLIP2024.0449.644.149.5
FNACMethod Category=Current SOTA Based Methods, Pre-trained Encoders=AudioCLIP2024.0448.443.349.1
AudioCLIPMethod Category=CLIP-Based Baseline Methods, Pre-trained Encoders=AudioCLIP2024.0447.442.848.5
OA-SSL2026.0447.351.744.9
MarginNCEMethod Category=Current SOTA Based Methods, Pre-trained Encoders=AudioCLIP2024.0446.942.548.3
DSOLMethod Category=Current SOTA Based Methods, Pre-trained Encoders=AudioCLIP2024.0446.8—47.9
Mix-and-LocalizeMethod Category=Current SOTA Based Methods, Pre-trained Encoders=AudioCLIP2024.0445.641.847.4
EZ-VSLMethod Category=Current SOTA Based Methods, Pre-trained Encoders=AudioCLIP2024.0445.140.647.2
LVSMethod Category=Current SOTA Based Methods, Pre-trained Encoders=AudioCLIP2024.0444.639.745.3
Wav2CLIPMethod Category=CLIP-Based Baseline Methods, Pre-trained Encoders=AudioCLIP2024.0443.639.344.7
OTSMethod Category=Current SOTA Based Methods, Pre-trained Encoders=AudioCLIP2024.0443.238.943.7
CoarsetoFineMethod Category=Current SOTA Based Methods, Pre-trained Encoders=AudioCLIP2024.0443.139.444.8
Proposed MethodVisual Backbone=ResNet-18, Audio Backbone=ResNet-182024.0341.446.241.2
NoPrior2026.0441.446.241.2
AVGN2024.0340.835.342.3
AVGN2026.0440.833.242.3
Qwen2.5-Omni2026.0439.443.641.8
EZ-VSL2024.0338.931.339.5
EZ-VSL2026.0438.931.339.5
Mix-and-Localize2024.0336.332.538.9
Mix-and-Localize2026.0436.332.538.9
DSOL2024.0335.7—37.2
DSOL2026.0435.7—37.2
LVS2024.0334.429.638.2
LVS2026.0434.429.638.2
OTS2024.0332.829.835.7
OTS2026.0432.829.835.7
CoarseToFine2024.0329.128.234.8
CoarseToFIne2026.0429.128.234.8
MiniCPM-o2026.0424.940.932.1
DMC2024.0323.9—27.6
DMC2026.0423.9—27.6
InteractiveOmni2026.042136.416.4
Attention10k2024.0319.2—30.6
Attention 10k2026.0419.2—30.6