Multimodal Emotion Recognition
This is a leaderboard for multimodal emotion recognition on the IEMOCAP dataset. The modality abbreviations are A: Acoustic T: Text V: Visual
Please include the modality in the bracket after the model name.
All models must use standard five emotion categories and are evaluated in standard leave-one-session-out (LOSO). See the papers for references.
Papers
Showing 1–10 of 180 papers
All datasetsIEMOCAP-4MELDIEMOCAPCMU-MOSEI-SentimentCMU-MOSEI-Sentiment-3Expressive hands and faces dataset (EHF).MELD-Sentiment
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | GraphSmile | Weighted F1 | 86.52 | — | Unverified |
| 2 | Joyful | Weighted F1 | 85.7 | — | Unverified |
| 3 | COGMEN | Weighted F1 | 84.5 | — | Unverified |
| 4 | DANN | Accuracy | 82.7 | — | Unverified |
| 5 | MMER | Accuracy | 81.7 | — | Unverified |
| 6 | PATHOSnet v2 | Accuracy | 80.4 | — | Unverified |
| 7 | Self-attention weight correction (A+T) | Accuracy | 76.8 | — | Unverified |
| 8 | CHFusion | Accuracy | 76.5 | — | Unverified |
| 9 | bc-LSTM | Weighted F1 | 74.1 | — | Unverified |
| 10 | Audio + Text (Stage III) | F1 | 70.5 | — | Unverified |