Emotion Recognition in Conversation on MELD (Per-Class Metrics)
67.29F1 ScoreVL2E
Evaluation Results
| Method | Links | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| VL2EModality=T+V2024.10 | 67.29 | 80.31 | 61.03 | 14.71 | 46.28 | 65.33 | 28.57 | 55.07 | — | — | |
| TelME*Modality=T+V, Note=Reproduced version2024.10 | 66.83 | 79.85 | 59.61 | 31.17 | 43.35 | 65.29 | 23.53 | 55 | — | — | |
| M2FNetModality=T+V+A2024.10 | 66.71 | — | — | — | — | — | — | — | — | — | |
| VL2E - w/o neutral normalizationModality=T+V2024.10 | 66.6 | — | — | — | — | — | — | — | — | — | |
| FacialMMTModality=T+V+A2024.10 | 66.58 | 80.13 | 59.63 | 19.18 | 41.99 | 64.88 | 18.18 | 56 | — | — | |
| VL2E - w/o face extractionModality=T+V2024.10 | 65.95 | — | — | — | — | — | — | — | — | — | |
| VL2E - w/o visionModality=T2024.10 | 65.56 | — | — | — | — | — | — | — | — | — | |
| UniMSEModality=T+V+A2024.10 | 65.51 | — | — | — | — | — | — | — | — | — | |
| EmoCapsModality=T+V+A2024.10 | 64 | 77.12 | 63.19 | 3.03 | 42.52 | 57.5 | 7.69 | 57.54 | — | — | |
| DAG-ERCModality=T2024.10 | 63.65 | — | — | — | — | — | — | — | — | — | |
| MM-DFNModality=T+V+A2024.10 | 59.46 | 77.76 | 50.69 | — | 22.94 | 54.78 | — | 47.82 | — | — | |
| ConGCNModality=T+A2024.10 | 59.4 | 76.7 | 50.3 | 8.7 | 28.5 | 53.1 | 10.6 | 46.8 | — | — | |
| GA2MIFModality=T+V+A2024.10 | 58.94 | 76.92 | 49.08 | — | 27.18 | 51.87 | — | 48.52 | — | — | |
| MMGCNModality=T+V+A2024.10 | 58.65 | — | — | — | — | — | — | — | — | — | |
| DialogueRNNModality=T+V+A2024.10 | 57.03 | 73.5 | 49.4 | 1.2 | 23.8 | 50.7 | 1.7 | 41.5 | — | — | |
| VL2E - w/o textModality=V2024.10 | 35.97 | — | — | — | — | — | — | — | — | — | |
| Audio Flamingo 3Size=7B2026.03 | — | — | — | — | — | — | — | — | — | 58.5 | |
| Audio-ReasonerSize=8.4B2026.03 | — | — | — | — | — | — | — | — | — | 63.2 | |
| BC-LSTM2022.03 | — | 73.8 | 47.7 | 5.4 | 25.1 | 51.3 | 5.2 | 38.4 | 55.9 | — | |
| DAG-ERC2022.03 | — | — | — | — | — | — | — | — | 63.65 | — | |
| DialogueCRN2022.03 | — | — | — | — | — | — | — | — | 58.39 | — | |
| DialogueGCN2022.03 | — | — | — | — | — | — | — | — | 58.23 | — | |
| DialogueRNN2022.03 | — | 73.5 | 49.4 | 1.2 | 23.8 | 50.7 | 1.7 | 41.5 | 57.03 | — | |
| DialogXL2022.03 | — | — | — | — | — | — | — | — | 62.41 | — | |
| EmoCaps2022.03 | — | 77.12 | 63.19 | 3.03 | 42.52 | 57.5 | 7.69 | 57.54 | 64 | — | |
| Gemini 2.5 FlashSize=-2026.03 | — | — | — | — | — | — | — | — | — | 61.5 | |
| GPT-4o AudioSize=-2026.03 | — | — | — | — | — | — | — | — | — | 62.5 | |
| MMGCN2022.03 | — | — | — | — | — | — | — | — | 58.65 | — | |
| Qwen2.5-omniSize=7B2026.03 | — | — | — | — | — | — | — | — | — | 60.3 | |
| Qwen2.5-omni + Only STASize=7B2026.03 | — | — | — | — | — | — | — | — | — | 62.8 | |
| Qwen2.5-omni + Reasoning SFTSize=7B2026.03 | — | — | — | — | — | — | — | — | — | 61.8 | |
| SALMONNSize=7B2026.03 | — | — | — | — | — | — | — | — | — | 37.2 | |
| TGSRSize=7B2026.03 | — | — | — | — | — | — | — | — | — | 64.6 |