List your company
ResearchFormerly WizWand

Classification on Audiovision-MNIST (test)

98.22AccuracyUpperB
61.653671.146880.6490.1332Jul 26, 2023Dec 29, 2023Jun 3, 2024Nov 6, 2024Apr 12, 2025Sep 15, 2025Feb 19, 2026
Updated 8mo ago

Evaluation results

MethodLinks
UpperBAudio rate=5%2023.0798.22
UpperBAudio rate=10%2023.0798.22
UpperBAudio rate=15%2023.0798.22
UpperBAudio rate=20%2023.0798.22
ShaSpecAudio rate=20%2023.0794.67
SMILAudio rate=20%2023.0794.44
ShaSpecAudio rate=15%2023.0793.78
ShaSpecAudio rate=10%2023.0793.56
ShaSpecAudio rate=5%2023.0793.33
SMILAudio rate=15%2023.0793.33
SMILAudio rate=10%2023.0793.11
SMILAudio rate=5%2023.0792.89
Full2missAudio rate=20%2023.0792.67
LowerBAudio rate=5%2023.0792.35
LowerBAudio rate=10%2023.0792.35
LowerBAudio rate=15%2023.0792.35
LowerBAudio rate=20%2023.0792.35
Full2missAudio rate=15%2023.0792.23
Full2missAudio rate=10%2023.0791.11
Full2missAudio rate=5%2023.0790
AutoEncoderAudio rate=5%2023.0789.78
GANAudio rate=10%2023.0789.78
AutoEncoderAudio rate=15%2023.0789.78
GANAudio rate=20%2023.0789.56
AutoEncoderAudio rate=10%2023.0789.33
GANAudio rate=5%2023.0789.11
AutoEncoderAudio rate=20%2023.0788.89
GANAudio rate=15%2023.0788.67
Multimodal LegoGFLOPs=0.0362025.1277
Uniform AttentionGFLOPs=0.022025.1277
CLARGAGFLOPs=0.022025.1277
FuseMix2025.1275
No Residual ConnectionGFLOPs=0.022025.1275
No Contrastive AlignmentGFLOPs=0.022025.1274
Early Fusion (Mean)GFLOPs=0.022025.1273
(xo, xm)Training Modality Setup=multimodal2026.0271.14
Late FusionGFLOPs=1.2142025.1269
PRIMOTraining Modality Setup=multimodal2026.0268.17
Early FusionGFLOPs=1.2142025.1266
xoTraining Modality Setup=unimodal2026.0264.23
PRIMOTraining Modality Setup=unimodal2026.0263.06