Multimodal Emotion Recognition on IEMOCAP
75.9Weighted AccuracyMPLMM
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| MPLMMTesting Condition={AT}2025.07 | 75.9 | — | — | — | — | |
| OursTesting Condition={VT}2025.07 | 75.2 | — | — | — | 78.5 | |
| MPLMMTesting Condition={VT}2025.07 | 74.6 | — | — | — | — | |
| OursTesting Condition={AT}2025.07 | 74.1 | — | — | — | 76.6 | |
| IF-MMINTesting Condition={AT}2025.07 | 74 | — | — | — | 75.4 | |
| P-RMF*Testing Condition={VT}2025.07 | 73.6 | — | — | — | 75.4 | |
| IMDer*Testing Condition={VT}2025.07 | 73.1 | — | — | — | 73.4 | |
| MMINTesting Condition={AT}2025.07 | 72.9 | — | — | — | 75.1 | |
| MMINTesting Condition={VT}2025.07 | 72.6 | — | — | — | 73.6 | |
| IF-MMINTesting Condition={VT}2025.07 | 72.6 | — | — | — | 73.6 | |
| OursTesting Condition={AV}2025.07 | 72.1 | — | — | — | 72.9 | |
| OursTesting Condition={T}2025.07 | 71.4 | — | — | — | 74.1 | |
| IMDer*Testing Condition={AT}2025.07 | 71.2 | — | — | — | 72.3 | |
| MPLMMTesting Condition={T}2025.07 | 69.2 | — | — | — | — | |
| P-RMF*Testing Condition={AT}2025.07 | 68.9 | — | — | — | 69.9 | |
| CRATesting Condition={AT}2025.07 | 68.7 | — | — | — | 70.3 | |
| OursTesting Condition=Average2025.07 | 68.7 | — | — | — | 70.2 | |
| MCTNTesting Condition={AT}2025.07 | 68.3 | — | — | — | 69.4 | |
| P-RMF*Testing Condition={T}2025.07 | 68.3 | — | — | — | 69.6 | |
| CRATesting Condition={VT}2025.07 | 68.2 | — | — | — | 67.7 | |
| IMDer*Testing Condition={T}2025.07 | 68.2 | — | — | — | 68.5 | |
| MCTNTesting Condition={VT}2025.07 | 67.8 | — | — | — | 68.3 | |
| P-RMF*Testing Condition={AV}2025.07 | 67.8 | — | — | — | 68.7 | |
| MPLMMTesting Condition=Average2025.07 | 67.4 | — | — | — | — | |
| MPLMMTesting Condition={AV}2025.07 | 67.2 | — | — | — | — | |
| IMDer*Testing Condition={AV}2025.07 | 67.1 | — | — | — | 68.3 | |
| IF-MMINTesting Condition={T}2025.07 | 67 | — | — | — | 68.2 | |
| MMINTesting Condition={T}2025.07 | 66.5 | — | — | — | 68 | |
| IF-MMINTesting Condition={AV}2025.07 | 65.3 | — | — | — | 66.5 | |
| P-RMF*Testing Condition=Average2025.07 | 64.9 | — | — | — | 66 | |
| IMDer*Testing Condition=Average2025.07 | 64.8 | — | — | — | 65.7 | |
| IF-MMINTesting Condition=Average2025.07 | 64.5 | — | — | — | 65.3 | |
| MMINTesting Condition=Average2025.07 | 64.1 | — | — | — | 65.2 | |
| MMINTesting Condition={AV}2025.07 | 63.9 | — | — | — | 65.4 | |
| MCTNTesting Condition={T}2025.07 | 62.4 | — | — | — | 63.7 | |
| CRATesting Condition={T}2025.07 | 62.3 | — | — | — | 63.5 | |
| OursTesting Condition={V}2025.07 | 59.8 | — | — | — | 57.2 | |
| MPLMMTesting Condition={A}2025.07 | 59.7 | — | — | — | — | |
| OursTesting Condition={A}2025.07 | 59.2 | — | — | — | 61.6 | |
| MCTNTesting Condition=Average2025.07 | 58.9 | — | — | — | 59.1 | |
| CRATesting Condition=Average2025.07 | 58.7 | — | — | — | 58.8 | |
| P-RMF*Testing Condition={V}2025.07 | 58.6 | — | — | — | 55.4 | |
| MPLMMTesting Condition={V}2025.07 | 57.6 | — | — | — | — | |
| CRATesting Condition={AV}2025.07 | 57.1 | — | — | — | 54.2 | |
| MMINTesting Condition={A}2025.07 | 56.5 | — | — | — | 59 | |
| MCTNTesting Condition={AV}2025.07 | 56.3 | — | — | — | 55.8 | |
| IF-MMINTesting Condition={A}2025.07 | 56.2 | — | — | — | 58.1 | |
| IMDer*Testing Condition={V}2025.07 | 55.6 | — | — | — | 56.3 | |
| IMDer*Testing Condition={A}2025.07 | 54.1 | — | — | — | 55.2 | |
| MMINTesting Condition={V}2025.07 | 52.5 | — | — | — | 51.6 | |
| P-RMF*Testing Condition={A}2025.07 | 52.3 | — | — | — | 56.7 | |
| IF-MMINTesting Condition={V}2025.07 | 51.9 | — | — | — | 50.4 | |
| MCTNTesting Condition={A}2025.07 | 49.7 | — | — | — | 51.6 | |
| MCTNTesting Condition={V}2025.07 | 48.9 | — | — | — | 45.7 | |
| CRATesting Condition={A}2025.07 | 48.1 | — | — | — | 49.1 | |
| CRATesting Condition={V}2025.07 | 47.7 | — | — | — | 48.2 | |
| CALIBER-GText Model=nliRoBERTa, Audio Model=whisperMedium, Variant=Audio Ctx2026.04 | — | — | — | 93.27 | — | |
| CALIBER-GText Model=nliRoBERTa, Audio Model=hubertLargeFT, Variant=Audio Ctx2026.04 | — | — | — | 90.4 | — | |
| CALIBER-GText Model=nliDistilRoBERTa, Audio Model=whisperMedium, Variant=Audio Ctx2026.04 | — | — | — | 92.91 | — | |
| CALIBER-GText Model=nliDistilRoBERTa, Audio Model=hubertLargeFT, Variant=Audio Ctx2026.04 | — | — | — | 89.21 | — | |
| CALIBER-GText Model=allRoBERTaLarge, Audio Model=whisperMedium, Variant=Audio Ctx2026.04 | — | — | — | 92.48 | — | |
| CALIBER-GText Model=allRoBERTaLarge, Audio Model=hubertLargeFT, Variant=Audio Ctx2026.04 | — | — | — | 89.21 | — | |
| CALIBER-GText Model=allDistilRoBERTa, Audio Model=whisperMedium, Variant=Audio Ctx2026.04 | — | — | — | 92.56 | — | |
| CALIBER-GText Model=allDistilRoBERTa, Audio Model=hubertLargeFT, Variant=Audio Ctx2026.04 | — | — | — | 90 | — | |
| CALIBER-GText Model=allMiniLM12, Audio Model=whisperMedium, Variant=Audio Ctx2026.04 | — | — | — | 92.93 | — | |
| CALIBER-GText Model=allMiniLM12, Audio Model=hubertLargeFT, Variant=Audio Ctx2026.04 | — | — | — | 89.37 | — | |
| CALIBER-GText Model=paraTinyBERT, Audio Model=whisperMedium, Variant=Audio Ctx2026.04 | — | — | — | 91.62 | — | |
| CALIBER-GText Model=paraTinyBERT, Audio Model=hubertLargeFT, Variant=Audio Ctx2026.04 | — | — | — | 88.32 | — | |
| CALIBER-XText Model=nliRoBERTa, Audio Model=whisperMedium, Variant=Shared-KV2026.04 | — | — | — | 94.01 | — | |
| CALIBER-XText Model=nliRoBERTa, Audio Model=whisperMedium, Variant=Cross-Attn2026.04 | — | — | — | 93.05 | — | |
| CALIBER-XText Model=nliRoBERTa, Audio Model=hubertLargeFT, Variant=Shared-KV2026.04 | — | — | — | 90.2 | — | |
| CALIBER-XText Model=nliRoBERTa, Audio Model=hubertLargeFT, Variant=Cross-Attn2026.04 | — | — | — | 91.06 | — | |
| CALIBER-XText Model=nliDistilRoBERTa, Audio Model=whisperMedium, Variant=Shared-KV2026.04 | — | — | — | 93.15 | — | |
| CALIBER-XText Model=nliDistilRoBERTa, Audio Model=whisperMedium, Variant=Cross-Attn2026.04 | — | — | — | 93.99 | — | |
| CALIBER-XText Model=nliDistilRoBERTa, Audio Model=hubertLargeFT, Variant=Shared-KV2026.04 | — | — | — | 89.46 | — | |
| CALIBER-XText Model=nliDistilRoBERTa, Audio Model=hubertLargeFT, Variant=Cross-Attn2026.04 | — | — | — | 89.51 | — | |
| CALIBER-XText Model=allRoBERTaLarge, Audio Model=whisperMedium, Variant=Shared-KV2026.04 | — | — | — | 92.59 | — | |
| CALIBER-XText Model=allRoBERTaLarge, Audio Model=whisperMedium, Variant=Cross-Attn2026.04 | — | — | — | 94.05 | — | |
| CALIBER-XText Model=allRoBERTaLarge, Audio Model=hubertLargeFT, Variant=Shared-KV2026.04 | — | — | — | 88.49 | — | |
| CALIBER-XText Model=allRoBERTaLarge, Audio Model=hubertLargeFT, Variant=Cross-Attn2026.04 | — | — | — | 88.81 | — | |
| CALIBER-XText Model=allDistilRoBERTa, Audio Model=whisperMedium, Variant=Shared-KV2026.04 | — | — | — | 93.14 | — | |
| CALIBER-XText Model=allDistilRoBERTa, Audio Model=whisperMedium, Variant=Cross-Attn2026.04 | — | — | — | 94.68 | — | |
| CALIBER-XText Model=allDistilRoBERTa, Audio Model=hubertLargeFT, Variant=Shared-KV2026.04 | — | — | — | 89.62 | — | |
| CALIBER-XText Model=allDistilRoBERTa, Audio Model=hubertLargeFT, Variant=Cross-Attn2026.04 | — | — | — | 91.09 | — | |
| CALIBER-XText Model=allMiniLM12, Audio Model=whisperMedium, Variant=Shared-KV2026.04 | — | — | — | 92.84 | — | |
| CALIBER-XText Model=allMiniLM12, Audio Model=whisperMedium, Variant=Cross-Attn2026.04 | — | — | — | 92.99 | — | |
| CALIBER-XText Model=allMiniLM12, Audio Model=hubertLargeFT, Variant=Shared-KV2026.04 | — | — | — | 89.78 | — | |
| CALIBER-XText Model=allMiniLM12, Audio Model=hubertLargeFT, Variant=Cross-Attn2026.04 | — | — | — | 89.62 | — | |
| CALIBER-XText Model=paraTinyBERT, Audio Model=whisperMedium, Variant=Shared-KV2026.04 | — | — | — | 92.27 | — | |
| CALIBER-XText Model=paraTinyBERT, Audio Model=whisperMedium, Variant=Cross-Attn2026.04 | — | — | — | 93.36 | — | |
| CALIBER-XText Model=paraTinyBERT, Audio Model=hubertLargeFT, Variant=Shared-KV2026.04 | — | — | — | 89.62 | — | |
| CALIBER-XText Model=paraTinyBERT, Audio Model=hubertLargeFT, Variant=Cross-Attn2026.04 | — | — | — | 88.97 | — | |
| CHFusionModality=T2018.06 | — | 73.6 | — | — | — | |
| CHFusionModality=V2018.06 | — | 53.3 | — | — | — | |
| CHFusionModality=A2018.06 | — | 57.1 | — | — | — | |
| CHFusionModality=T+V2018.06 | — | 75.9 | 75.6 | — | — | |
| CHFusionModality=T+A2018.06 | — | 76.1 | 76 | — | — | |
| CHFusionModality=A+V2018.06 | — | 69.5 | 69.6 | — | — | |
| CHFusionModality=A+V+T2018.06 | — | 76.5 | 76.8 | — | — | |
| DF-ERCMethod Category=Fusion-based Methods2026.04 | — | 71.84 | 71.75 | — | — |