Emotion Classification on IEMOCAP (test)
74.02Weighted-F1VowelPrompt
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| VowelPromptBackbone=LLaMA-4-Scout-17B-16E-Instruct, Training Regime=SFT & GRPO2026.02 | 74.02 | — | — | — | |
| VowelPromptBackbone=LLaMA-4-Scout-17B-16E-Instruct, Training Regime=SFT2026.02 | 73.85 | — | — | — | |
| VowelPromptBackbone=LLaMA-3-8B-Instruct, Training Regime=SFT2026.02 | 73.46 | — | — | — | |
| VowelPromptBackbone=LLaMA-3-8B-Instruct, Training Regime=SFT & GRPO2026.02 | 73.02 | — | — | — | |
| SpeechCueLLMBackbone=LLaMA-4-Scout-17B-16E-Instruct, Training Regime=SFT & GRPO2026.02 | 72.18 | — | — | — | |
| SpeechCueLLMBackbone=LLaMA-4-Scout-17B-16E-Instruct, Training Regime=SFT2026.02 | 72.02 | — | — | — | |
| SALMONNBackbone=LLaMA-4-Scout-17B-16E-Instruct, Training Regime=SFT & GRPO2026.02 | 71.85 | — | — | — | |
| InstructERCBackbone=LLaMA-4-Scout-17B-16E-Instruct, Training Regime=SFT2026.02 | 71.75 | — | — | — | |
| SpeechCueLLMBackbone=LLaMA-3-8B-Instruct, Training Regime=SFT2026.02 | 71.74 | — | — | — | |
| InstructERCBackbone=LLaMA-3-8B-Instruct, Training Regime=SFT2026.02 | 71.65 | — | — | — | |
| SpeechCueLLMBackbone=LLaMA-3-8B-Instruct, Training Regime=SFT & GRPO2026.02 | 71.55 | — | — | — | |
| InstructERCBackbone=LLaMA-4-Scout-17B-16E-Instruct, Training Regime=SFT & GRPO2026.02 | 71.52 | — | — | — | |
| SALMONNBackbone=LLaMA-4-Scout-17B-16E-Instruct, Training Regime=SFT2026.02 | 71.48 | — | — | — | |
| SALMONNBackbone=LLaMA-3-8B-Instruct, Training Regime=SFT2026.02 | 71.36 | — | — | — | |
| InstructERCBackbone=LLaMA-3-8B-Instruct, Training Regime=SFT & GRPO2026.02 | 71.32 | — | — | — | |
| SALMONNBackbone=LLaMA-3-8B-Instruct, Training Regime=SFT & GRPO2026.02 | 71.02 | — | — | — | |
| BaselineBackbone=LLaMA-4-Scout-17B-16E-Instruct, Training Regime=SFT2026.02 | 70.82 | — | — | — | |
| BaselineBackbone=LLaMA-3-8B-Instruct, Training Regime=SFT2026.02 | 70.32 | — | — | — | |
| COSMICBase=RoBERTa2020.10 | 65.28 | — | — | — | |
| COSMIC w/o Listener CSKBase=RoBERTa, Ablation=w/o Listener CSK2020.10 | 65.05 | — | — | — | |
| RoBERTa DialogueRNNBase=RoBERTa2020.10 | 64.76 | — | — | — | |
| AffectVerseAudio=true, Video=false, Text=true2026.05 | 64.32 | — | — | — | |
| AffectVerseAudio=true, Video=true, Text=true2026.05 | 63.87 | — | — | — | |
| COSMIC w/o Speaker CSKBase=RoBERTa, Ablation=w/o Speaker CSK2020.10 | 63.27 | — | — | — | |
| COSMIC w/o Speaker, Listener CSKBase=RoBERTa, Ablation=w/o Speaker, Listener CSK2020.10 | 63.05 | — | — | — | |
| DialogueRNNBase=GloVe2020.10 | 62.57 | — | — | — | |
| AffectGPTAudio=false, Video=true, Text=true2026.05 | 62.19 | — | — | — | |
| DialogueRNN2019.09 | 61.21 | — | — | — | |
| BERT_BASE2019.09 | 61.19 | — | — | — | |
| AffectVerseAudio=false, Video=true, Text=true2026.05 | 60.78 | — | — | — | |
| AffectGPTAudio=true, Video=true, Text=true2026.05 | 60.54 | — | — | — | |
| Qwen2.5-OmniAudio=true, Video=true, Text=true2026.05 | 60.51 | — | — | — | |
| KET2019.09 | 59.56 | — | — | — | |
| KETBase=GloVe2020.10 | 59.56 | — | — | — | |
| KET_StdAttn2019.09 | 58.61 | — | — | — | |
| Qwen2.5-OmniAudio=true, Video=false, Text=true2026.05 | 58.6 | — | — | — | |
| ICONBase=GloVe2020.10 | 58.54 | — | — | — | |
| Qwen2.5-OmniAudio=false, Video=true, Text=true2026.05 | 58.27 | — | — | — | |
| KET_SingleSelfAttn2019.09 | 58.1 | — | — | — | |
| Video-ChatGPTAudio=false, Video=true, Text=true2026.05 | 56.83 | — | — | — | |
| CNN+cLSTM2019.09 | 55.87 | — | — | — | |
| AffectGPTAudio=true, Video=false, Text=true2026.05 | 55.68 | — | — | — | |
| mPLUG-OwlAudio=false, Video=true, Text=true2026.05 | 55.54 | — | — | — | |
| Emotion-LLaMAAudio=true, Video=true, Text=true2026.05 | 55.47 | — | — | — | |
| RoBERTaBase=RoBERTa2020.10 | 54.55 | — | — | — | |
| Chat-UniViAudio=false, Video=true, Text=true2026.05 | 52.37 | — | — | — | |
| CNN2019.09 | 52.18 | — | — | — | |
| CNNBase=GloVe2020.10 | 52.04 | — | — | — | |
| VideoChat2Audio=false, Video=true, Text=true2026.05 | 48.7 | — | — | — | |
| VideoChatAudio=false, Video=true, Text=true2026.05 | 48.38 | — | — | — | |
| PandaGPTAudio=false, Video=true, Text=true2026.05 | 47.21 | — | — | — | |
| SALMONNAudio=true, Video=false, Text=true2026.05 | 46.84 | — | — | — | |
| LLaMA-VIDAudio=false, Video=true, Text=true2026.05 | 46.02 | — | — | — | |
| PandaGPTAudio=true, Video=true, Text=true2026.05 | 44.04 | — | — | — | |
| Video-LLaVAAudio=false, Video=true, Text=true2026.05 | 38.95 | — | — | — | |
| SECapAudio=true, Video=false, Text=true2026.05 | 36.92 | — | — | — | |
| PandaGPTAudio=true, Video=false, Text=true2026.05 | 36.55 | — | — | — | |
| Qwen-AudioAudio=true, Video=false, Text=true2026.05 | 35.47 | — | — | — | |
| cLSTM2019.09 | 34.84 | — | — | — | |
| OneLLMAudio=true, Video=false, Text=true2026.05 | 33.44 | — | — | — | |
| OtterAudio=false, Video=true, Text=true2026.05 | 29.08 | — | — | — | |
| BC-LSTM2018.02 | — | 35.9 | 34.1 | — | |
| BiDialogueRNN+attModality=Textual, Context=Trimodal Comparison2018.11 | — | — | 62.7 | — | |
| BiDialogueRNN+attModality=Trimodal (T+V+A)2018.11 | — | — | 62.9 | — | |
| c-LSTMModality=Trimodal (T+V+A)2018.11 | — | — | 58.3 | — | |
| C-MKL2018.02 | — | 34 | 31.1 | — | |
| CMNModality=Trimodal (T+V+A)2018.11 | — | — | 58.5 | — | |
| ConGCN2024.01 | — | — | 64.18 | — | |
| DAG-ERC2024.01 | — | — | 68.03 | — | |
| DF2018.02 | — | 26.1 | 20 | — | |
| DialogueRNN2024.01 | — | — | 62.75 | — | |
| DialogueTRM2024.01 | — | — | 69.23 | — | |
| EF-HCRF2018.02 | — | 32 | 20.5 | — | |
| EF-LSTM2018.02 | — | 34.1 | 32.3 | — | |
| EmoCaps2024.01 | — | — | 71.77 | — | |
| GA2MIF2024.01 | — | — | 70 | — | |
| M2FNet2024.01 | — | — | 69.86 | — | |
| Majority2018.02 | — | 21.2 | 7.4 | — | |
| MARNablation=no MAB2018.02 | — | 31.2 | 28 | — | |
| MARNablation=no A2018.02 | — | 23 | 10.9 | — | |
| MARNfull=true2018.02 | — | 37 | 35.9 | — | |
| MFNModality=Trimodal (T+V+A)2018.11 | — | — | 53.5 | — | |
| MM-DFN2024.01 | — | — | 68.18 | — | |
| MMGCN2024.01 | — | — | 66.22 | — | |
| MV-HCRF2018.02 | — | 32 | 20.5 | — | |
| MV-LSTM2018.02 | — | 31.3 | 26.7 | — | |
| RF2018.02 | — | 27.3 | 25.3 | — | |
| SVM2018.02 | — | 24.1 | 18 | — | |
| TelME2024.01 | — | — | 70.48 | — | |
| TFN2018.02 | — | 36 | 34.5 | — | |
| TFNModality=Trimodal (T+V+A)2018.11 | — | — | 56.3 | — | |
| THMM2018.02 | — | 23.5 | 10.8 | — | |
| UniMSE2024.01 | — | — | 70.66 | — |