List your company

Audio-Visual Event Classification on VGGSound (test)

69.1Fusion Top-1 AccMIMO
37.06845.38453.762.016Jul 29, 2022Mar 1, 2023Oct 3, 2023May 6, 2024Dec 8, 2024Jul 12, 2025Feb 13, 2026

Evaluation results

MethodLinks
MIMOt(s)=0.019±0.0042025.1169.141.4738.2—
MMParetot(s)=0.389±0.0532025.1166.0748.0728.87—
UAVMmodality-missing results=false2022.0765.8———
Modal-Independent Modeltrained independently=false2022.0765.7———
MBTtrained independently=false2022.0764.1———
EWt(s)=0.006±0.0012025.1163.948.7725.2—
Cross-Modal Attention Model2022.0762.9———
OGM-GEt(s)=0.121±0.0072025.1162.1332.522—
MSLt(s)=0.011±0.0012025.1160.842.8315.43—
TCMaxFusion Head=Concat2026.0247.633.922—
TCMaxFusion Head=Share Head2026.0247.536.324.3—
Unimodal Ensemble2026.0246.334.826.7—
MMPareto2026.0246.235.527.5—
OPM2026.0245.931.223.5—
QMF2026.0245.834.626.1—
OGM-GE + OPM2026.0245.531.623.5—
AGM2026.0244.730.514.7—
MLA2026.0244.535.325.8—
OGM-GE2026.0242.528.713.2—
Share Head2026.0241.830.913—
Concat2026.0241.129.510.3—
FiLM2026.0238.3———
BiGated2026.0238.3———
AudioSlowFast2022.07—50.1——
Chen et al.2022.07—48.8——
MAVILInput Modalities=Audio + Video2023.11———67.1
MBTtrained independently=true2022.07—52.351.2—
Mirasol3BInput Modalities=Audio + Video2023.11———69.8
Mirasol3B TTMInput Modalities=Audio + Video, Module Configuration=TTM2023.11———66.4
MMTInput Modalities=Audio + Video2023.11———66.2
Modal-Independent Modeltrained independently=true2022.07—56.549.7—
ONE-PEACEInput Modalities=Audio + Video2023.11———68.2
UAVMmodality-missing results=true2022.07—56.549.9—
UAVMInput Modalities=Audio + Video2023.11———65.8