Multimodal Emotion Recognition in Conversation on IEMOCAP 6-class (test)
72.81Weighted F1 Score (WF1)GraphSmile
Evaluation Results
| Method | Links | |||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| GraphSmile2024.07 | 72.81 | 63.09 | 83.16 | 71.07 | 71.38 | 79.66 | 66.84 | 72.77 | — | — | — | — | — | — | — | |
| M3NetResult Source=Original Paper2024.07 | 71.07 | 60.93 | 78.84 | 70.14 | 68.06 | 77.11 | 67.42 | 70.92 | — | — | — | — | — | — | — | |
| JoyfulResult Source=Original Paper2024.07 | 71.03 | 60.94 | 84.42 | 68.24 | 69.95 | 73.54 | 67.55 | 70.55 | — | — | — | — | — | — | — | |
| MiSTER-EModality=speech-text2026.03 | 70.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| UniMSE2024.07 | 70.66 | — | — | — | — | — | — | 70.56 | — | — | — | — | — | — | — | |
| SACL-LSTMResult Source=Original Paper, Multimodal Feature Fusion Strategy=Direct Concatenation2024.07 | 70.6 | 51.3 | 82.25 | 71.39 | 67.78 | 75.26 | 66.94 | 70.55 | — | — | — | — | — | — | — | |
| SMINModality=speech-text, External Emotional Data=Not used2026.03 | 70.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| HCAMModality=speech-text2026.03 | 70.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| LSDGNN+ICL2025.07 | 70.24 | 47.2 | 81.53 | 71 | 69.74 | 73.19 | 68.58 | 70.35 | 68.54 | — | — | — | — | — | — | |
| Mamba-like-modelModality=speech-text2026.03 | 70.2 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MetaDrop2024.07 | 69.59 | — | — | — | — | — | — | 69.38 | — | — | — | — | — | — | — | |
| DF-ERCModality=speech-text2026.03 | 69.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DER-GCNResult Source=Original Paper2024.07 | 69.4 | 58.8 | 79.8 | 61.5 | 72.1 | 73.3 | 67.8 | 69.7 | — | — | — | — | — | — | — | |
| DER-GCN2025.07 | 69.4 | 58.8 | 79.8 | 61.5 | 72.1 | 73.3 | 67.8 | 69.7 | — | — | — | — | — | — | — | |
| TelMEModality=speech-text2026.03 | 69.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| CBERL2025.07 | 69.27 | 67.34 | 72.84 | 60.75 | 73.51 | 70.77 | 71.19 | 69.36 | — | — | — | — | — | — | — | |
| MultiDAG+CL2025.07 | 69.08 | 45.26 | 81.4 | 69.53 | 70.33 | 71.61 | 66.94 | 69.11 | — | — | — | — | — | — | — | |
| MM-DFNResult Source=Original Paper2024.07 | 68.83 | 43.36 | 83.23 | 70.03 | 70.19 | 73.11 | 64.01 | 69.44 | — | — | — | — | — | — | — | |
| DialogueCRNResult Source=Original Paper, Multimodal Feature Fusion Strategy=Direct Concatenation2024.07 | 68.82 | 53.85 | 82.66 | 71.03 | 62.33 | 77.64 | 58.81 | 68.7 | — | — | — | — | — | — | — | |
| CFN-ESAModality=speech-text2026.03 | 68.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DCGCNResult Source=Original Paper2024.07 | 68.31 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| LR-GCN2025.07 | 68.3 | 55.5 | 79.1 | 63.8 | 69 | 74 | 68.9 | 68.5 | — | — | — | — | — | — | — | |
| EmoLRResult Source=Original Paper2024.07 | 68.12 | — | — | — | — | — | — | 68.53 | — | — | — | — | — | — | — | |
| DAG-ERC2025.07 | 68.03 | 47.59 | 79.83 | 69.36 | 66.67 | 66.79 | 68.66 | 67.53 | — | — | — | — | — | — | — | |
| COGMENResult Source=Original Paper2024.07 | 67.6 | 51.9 | 81.7 | 68.6 | 66 | 75.3 | 58.2 | 68.2 | — | — | — | — | — | — | — | |
| MultiEmoModality=speech-text, Implementation=authors' public implementation (re-run)2026.03 | 66.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MMGCNResult Source=Original Paper2024.07 | 66.81 | 47.1 | 81.91 | 66.44 | 63.51 | 76.17 | 59.06 | 67.1 | — | — | — | — | — | — | — | |
| MMGCN2025.07 | 66.22 | 42.34 | 78.67 | 61.73 | 69 | 74.33 | 62.32 | — | — | — | — | — | — | — | — | |
| MMGAT-EMOModality=speech-text, Implementation=authors' public implementation (re-run)2026.03 | 65.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DER-GCNModality=speech-text2026.03 | 64.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ELR-GNNModality=speech-text2026.03 | 64.4 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| DialogueGCN2025.07 | 64.18 | 42.75 | 84.54 | 63.54 | 64.19 | 63.08 | 66.99 | 65.25 | — | — | — | — | — | — | — | |
| ICON2025.07 | 63.5 | 32.8 | 74.4 | 60.6 | 68.2 | 68.4 | 66.2 | 64 | — | — | — | — | — | — | — | |
| DialogueRNN2025.07 | 62.75 | 33.18 | 78.8 | 59.21 | 65.28 | 71.86 | 58.91 | 63.4 | — | — | — | — | — | — | — | |
| BiDialogueRNN+Attbidirectional=true, attention=true2018.11 | 62.75 | 25.69 | 75.1 | 58.59 | 64.71 | 80.27 | 61.15 | 63.4 | — | 33.18 | 78.8 | 59.21 | 65.28 | 71.86 | 58.91 | |
| DialogueRNN+Attattention=true2018.11 | 61.51 | 28.47 | 65.31 | 62.5 | 67.65 | 70.9 | 61.68 | 61.8 | — | 36.61 | 72.4 | 57.21 | 65.71 | 68.61 | 60.8 | |
| BiDialogueRNNbidirectional=true2018.11 | 60.28 | 32.64 | 71.02 | 60.47 | 62.94 | 56.52 | 65.62 | 60.32 | — | 36.15 | 74.04 | 56.16 | 63.88 | 62.02 | 61.73 | |
| DialogueRNNvariant=12018.11 | 59.89 | 31.25 | 66.12 | 63.02 | 61.76 | 61.54 | 59.58 | 59.33 | — | 33.83 | 69.83 | 57.76 | 62.5 | 64.45 | 59.46 | |
| DialogueRNNvariant=22018.11 | 58.76 | 35.42 | 65.71 | 55.73 | 62.94 | 59.2 | 63.52 | 58.66 | — | 35.54 | 69.85 | 55.3 | 61.85 | 62.21 | 59.38 | |
| c-LSTM+attattention=true2018.11 | 56.19 | 30.56 | 56.73 | 57.55 | 59.41 | 52.84 | 65.88 | 56.32 | — | 35.63 | 62.9 | 53 | 59.24 | 58.85 | 59.41 | |
| CMNstatus=SOTA2018.11 | 56.13 | 25 | 55.92 | 52.86 | 61.76 | 55.52 | 71.13 | 56.56 | — | 30.38 | 62.41 | 52.39 | 59.83 | 60.25 | 60.69 | |
| memnet2018.11 | 55.1 | 25.72 | 55.53 | 58.12 | 59.32 | 51.5 | 67.2 | 55.72 | — | 33.53 | 61.77 | 52.84 | 55.39 | 58.3 | 59 | |
| c-LSTM2018.11 | 54.95 | 29.17 | 57.14 | 54.17 | 57.06 | 51.17 | 67.19 | 55.21 | — | 34.43 | 60.87 | 51.81 | 56.73 | 57.95 | 58.92 | |
| CNN2018.11 | 48.18 | 27.77 | 57.14 | 34.33 | 61.17 | 46.15 | 62.99 | 48.92 | — | 29.86 | 53.83 | 40.14 | 52.44 | 50.09 | 55.75 |