List your company

Sound Source Localization on Flickr-SoundNet (test)

89.84CIoUDMT
23.446440.683257.9275.1568Mar 5, 2024Jul 7, 2024Nov 9, 2024Mar 14, 2025Jul 17, 2025Nov 19, 2025Mar 24, 2026

Evaluation results

MethodLinks
DMTTrainset=VGG-Sound 144k, Annotated samples size (|Dl|)=4k2024.0389.8468.64
MEERKATGeneralist=true2024.0788.3567.88
DMTTrainset=VGG-Sound 144k, Annotated samples size (|Dl|)=2k2024.0388.3267.78
DMTTrainset=VGG-Sound 10k, Annotated samples size (|Dl|)=4k2024.0388.267.56
DMTTrainset=VGG-Sound 10k, Annotated samples size (|Dl|)=2k2024.0387.3667.38
DMTTrainset=VGG-Sound 144k, Annotated samples size (|Dl|)=2562024.0387.0464.72
SLAVCGeneralist=false2024.0786—
SLAVCObject-Guided Refinement (OGL)=true2026.0386—
MarginNCEGeneralist=false2024.0785.1464.55
FNACGeneralist=false2024.0785.1464.3
MarginNCEObject-Guided Refinement (OGL)=true2026.0385.1464.55
FNACObject-Guided Refinement (OGL)=true2026.0385.1464.3
DMTTrainset=VGG-Sound 10k, Annotated samples size (|Dl|)=2562024.0385.0465.06
HearTheFlowGeneralist=false2024.0784.864
HearTheFlow2026.0384.864
SOUPLEObject-Guided Refinement (OGL)=false, Training Epochs=202026.0384.867.64
FNACObject-Guided Refinement (OGL)=false2026.0384.7363.76
EZ-VSLGeneralist=false2024.0783.9463.6
EZ-VSLObject-Guided Refinement (OGL)=true2026.0383.9463.6
MarginNCEObject-Guided Refinement (OGL)=false2026.0383.9463.2
SLAVCObject-Guided Refinement (OGL)=false2026.0383.6—
SOUPLEObject-Guided Refinement (OGL)=false, Training Epochs=502026.0383.665.76
AlignmentGeneralist=false2024.0782.464.6
AlignmentObject-Guided Refinement (OGL)=true2026.0382.464.6
BuboGPTGeneralist=true2024.0781.1762.29
ACL-SSLObject-Guided Refinement (OGL)=false2026.0380.864.62
SLAVCTrainset=VGG-Sound 144k2024.038061.68
AlignmentObject-Guided Refinement (OGL)=false2026.0379.663.44
EZVSLTrainset=VGG-Sound 144k2024.0379.5161.17
SSL-TIETrainset=VGG-Sound 144k2024.0379.561.2
SSL-TIEGeneralist=false2024.0779.561.2
SSL-TIE2026.0379.561.2
EZ-VSLObject-Guided Refinement (OGL)=false2026.0378.3161.74
SSL-TIETrainset=VGG-Sound 10k2024.0377.0460.36
HardPos2026.0376.859.2
SSPLTrainset=VGG-Sound 144k2024.0376.760.5
SSPLGeneralist=false2024.0776.760.5
SSPL2026.0376.760.5
SSPLTrainset=VGG-Sound 10k2024.0376.359.1
SLAVCTrainset=VGG-Sound 10k2024.037457.74
LVSTrainset=VGG-Sound 144k2024.0371.958.2
LVS2026.0371.958.2
attention 10kTrainset=VGG-Sound 144k2024.036655.8
Attention2026.036655.8
EZVSLTrainset=VGG-Sound 10k2024.0365.4654.57
LVSTrainset=VGG-Sound 10k2024.0361.853.6
attention 10kTrainset=VGG-Sound 10k2024.0352.250.2
AudioCLIP2026.0347.245.22
WAV2CLIP2026.032629.6