List your company

Audio-Visual Classification on CREMA-D (test)

79.7AccuracyMLA
14.845631.682848.5265.3572Nov 14, 2022Jun 17, 2023Jan 19, 2024Aug 22, 2024Mar 26, 2025Oct 28, 2025Jun 1, 2026

Evaluation results

MethodLinks
MLAModality=Multi2023.1179.7———
MLAModality=Multi2023.1179.7———
OGM-GEModality=Multi2023.1168.14———
OGM-GEModality=Multi2023.1168.14———
Late FusionModality=Multi2023.1166.32———
Late FusionModality=Multi2023.1166.32———
MLAModality=Video2023.1164.91———
MLAModality=Video2023.1164.91———
QMFModality=Multi2023.1163.71———
QMFModality=Multi2023.1163.71———
PMRFusion strategy=Film2022.1161.8———
ConcatModality=Multi2023.1161.56———
ConcatModality=Multi2023.1161.56———
PMR w/o PERFusion strategy=Film2022.1161.3———
PMRFusion strategy=Concat2022.1161.1———
SumModality=Multi2023.1160.32———
SumModality=Multi2023.1160.32———
PMR w/o PERFusion strategy=Concat2022.1160.3———
FiLMModality=Multi2023.1160.07———
FiLMModality=Multi2023.1160.07———
QMFModality=Audio2023.1159.41———
QMFModality=Audio2023.1159.41———
MLAModality=Audio2023.1159.27———
MLAModality=Audio2023.1159.27———
BiGatedModality=Multi2023.1159.21———
BiGatedModality=Multi2023.1159.21———
Grad-BlendingFusion strategy=Film2022.1158.7———
Modality-dropFusion strategy=Film2022.1158.3———
OGM-GEFusion strategy=Film2022.1158———
VGMRBackbone=Concatenation2026.0657.8——57.82
OGM-GEFusion strategy=Concat2022.1157.7———
ARLBackbone=Concatenation2026.0657.53——57.94
NaiveFusion strategy=Film2022.1157.2———
Grad-BlendingFusion strategy=Concat2022.1156.7———
Modality-dropFusion strategy=Concat2022.1155.8———
ConcatModality=Audio2023.1155.65———
ConcatModality=Audio2023.1155.65———
Late FusionModality=Video2023.1155.48———
Late FusionModality=Video2023.1155.48———
SumModality=Audio2023.1154.14———
SumModality=Audio2023.1154.14———
FiLMModality=Audio2023.1153.89———
FiLMModality=Audio2023.1153.89———
OGM-GEModality=Audio2023.1153.76———
OGM-GEModality=Audio2023.1153.76———
NaiveFusion strategy=Concat2022.1153.2———
Late FusionModality=Audio2023.1152.17———
Late FusionModality=Audio2023.1152.17———
Grad-BlendingBackbone=Concatenation2026.0651.75——51.65
PMRBackbone=Concatenation2026.0651.75——51.55
BiGatedModality=Audio2023.1151.49———
BiGatedModality=Audio2023.1151.49———
OGM-GEBackbone=Concatenation2026.0651.48——50.96
MLABackbone=Concatenation2026.0651.08——50.81
BaselineBackbone=Concatenation2026.0650.54——50.3
MMParetoBackbone=Concatenation2026.0649.73——49.63
AGMBackbone=Concatenation2026.0649.6——49.34
D&RBackbone=Concatenation2026.0648.52——46.78
QMFModality=Video2023.1139.11———
QMFModality=Video2023.1139.11———
OGM-GEModality=Video2023.1128.09———
OGM-GEModality=Video2023.1128.09———
ConcatModality=Video2023.1118.68———
ConcatModality=Video2023.1118.68———
FiLMModality=Video2023.1118.67———
FiLMModality=Video2023.1118.67———
SumModality=Video2023.1118.45———
SumModality=Video2023.1118.45———
BiGatedModality=Video2023.1117.34———
BiGatedModality=Video2023.1117.34———