List your company

Multimodal Action Recognition on Kinetic-Sounds ViT

74.2AccuracyDMIL
67.304869.094970.88572.6751Jun 10, 2026

Evaluation results

MethodLinks
DMILBackbone=ViT2026.0674.281.83
EnsembleBackbone=ViT2026.0671.879.03
MLBBackbone=ViT2026.0671.2277.29
MCRBackbone=ViT2026.0669.5176.33
MMMLBackbone=ViT2026.0669.1475.82
I2M2Backbone=ViT2026.0668.9373.55
FCLBackbone=ViT2026.0668.975.38
AGMBackbone=ViT2026.0668.5175.43
QMFBackbone=ViT2026.0668.172.9
OGMBackbone=ViT2026.0668.0273.42
PMRBackbone=ViT2026.0667.9973.36
JointBackbone=ViT2026.0667.8173.11
MMIBBackbone=ViT2026.0667.5773.52