Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

MOSEI

Benchmarks

Task NameDataset NameSOTA ResultTrend
Multimodal Sentiment AnalysisMOSEI
MAE0.486
183
Multimodal Sentiment AnalysisMOSEI (test)
MAE0.523
49
Emotion RecognitionMOSEI
Accuracy (7-Class)51.88
26
Binary Sentiment ClassificationMOSEI (test)
Accuracy82.5
16
Multimodal Sentiment AnalysisMOSEI 2018b (test)
Acc2 (pos/neg)85.88
13
Active Modality AcquisitionMOSEI Text imputed by Image and Audio (test)
AUROC1.207
11
Active Modality AcquisitionMOSEI Image imputed by Text
AUROC (Gfull)99.5
11
Active Modality AcquisitionMOSEI Text imputed by Image
AUROC (G_full)1.613
11
Active Modality AcquisitionMOSEI Audio imputed by Image and Text (test)
AUROC (G_full)1.215
11
Active Modality AcquisitionMOSEI
AUROC (G_full)1.478
11
Active Modality AcquisitionMOSEI Audio imputed by Image
AUROC1.238
11
Active Modality Acquisition (Image imputed by Audio)MOSEI
AUROC1.052
11
Active Modality AcquisitionMOSEI Image imputed by Text and Audio (test)
AUROC (G_full)1.321
11
Active Modality AcquisitionMOSEI Audio imputed by Text (test)
AUROC4.955
11
Active Modality Acquisition (Text imputed by Audio)MOSEI
AUROC8.867
11
Sentiment AnalysisMOSEI (held-out)
F1 Score72.4
8
Sentiment Analysis (SEN)MOSEI S
Binary Weighted F177.5
7
Emotion Recognition (EMO)MOSEI E
Mean Weighted Accuracy61.4
7
Streaming Social Task DetectionMOSEI
Accuracy85.64
7
Sentiment ClassificationMOSEI (test)
Accuracy (2 Class)85
7
ClassificationMOSEI
Accuracy77
6
Multi-label ClassificationMOSEI
F1 (Happy)72.7
5
Binary ClassificationMOSEI
F1 (Happy)71.7
5
Cross-modal retrieval (Video)MOSEI
R@139.2
4
Cross-modal retrieval (Language)MOSEI
Recall@134.6
4
Showing 25 of 29 rows