Multimodal Emotion Recognition On Iemocap 4
Metrics
Accuracy
F1
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Accuracy | F1 |
|---|---|---|
| speech-emotion-recognition-based-on-self | 76.8 | 76.85 |
| hcam-hierarchical-cross-attention-model-for | - | 70.5 |
| combining-deep-and-unsupervised-features-for | 80.4 | 78 |
| multimae-der-multimodal-masked-autoencoder | - | - |
| mmer-multimodal-multi-task-learning-for | 81.7 | - |
| cogmen-contextualized-gnn-based-multimodal | - | - |
| 2407-21536 | 86.53 | - |
| 0-1-deep-neural-networks-via-block-coordinate | - | - |
| context-dependent-domain-adversarial-neural | 82.7 | - |
| multimodal-sentiment-analysis-using | 76.5 | 76.8 |