List your company

Emotional Mimicry Intensity Estimation on Hume-Vidmimic2 (val)

0.5851Average Pearson Correlation (p-bar)EmoViT+HuBERT+ChatGLM3
0.0701960.2038730.337550.471227Mar 14, 2026

Evaluation results

MethodLinks
EmoViT+HuBERT+ChatGLM3Modality=Audio+Video, Features=-2026.030.58510.71550.61590.63030.34880.61740.5793
ChatGLM3 + WavLM-Large + ViTModality=Text + Audio + Face, Fusion Strategy=concat2026.030.47860.52420.47090.44150.58460.45310.3971
ChatGLM3 + WavLM-Large + ViTModality=Text + Audio + Face, Fusion Strategy=blending2026.030.46730.51250.4630.43380.55990.4350.3995
GigaChat + MT-EmotiMobileViT + HuBERTModality=Text + Video + Audio, Fusion=blending2026.030.4460.51970.44910.39160.49810.41920.3983
OpenAI + MT-EmotiMobileViT + HuBERTModality=Text + Video + Audio, Fusion=blending2026.030.44510.52030.44610.39380.50540.40150.4036
GigaChat + MT-EmotiMobileFaceNet + HuBERTModality=Text + Video + Audio, Fusion=blending2026.030.43380.49550.43320.39230.4640.42820.3863
GigaChat + MT-EmotiMobileFaceNetModality=Text + Video, Fusion=blending2026.030.42310.48970.41070.38060.48240.41310.3618
OpenAI + MT-EmotiMobileFaceNet + HuBERTModality=Text + Video + Audio, Fusion=blending2026.030.42250.50730.40440.36960.48010.38220.3912
RoBERTa + MT-EmotiMobileFaceNet + HuBERTModality=Text + Video + Audio, Fusion=blending2026.030.42230.4620.40950.38480.49360.38760.3965
GigaChat + MT-EmotiMobileFaceNet + HuBERTModality=Text + Video + Audio, Fusion=early2026.030.42040.48230.40130.42670.44960.37650.3983
GigaChat + MT-EmotiMobileFaceNetModality=Text + Video, Fusion=early2026.030.41990.49060.39880.41210.4420.38760.393
RoBERTa + MT-EmotiMobileViT + HuBERTModality=Text + Video + Audio, Fusion=blending2026.030.41920.46030.41040.38440.49350.38020.3864
OpenAI + HuBERTModality=Text + Audio, Fusion=blending2026.030.41250.51140.40060.37760.48630.36450.3344
GigaChat + HuBERTModality=Text + Audio, Fusion=blending2026.030.41060.49550.39120.38810.46190.39220.3348
OpenAI + MT-EmotiMobileViTModality=Text + Video, Fusion=blending2026.030.41030.49320.4090.33270.45710.37710.393
GigaChat + MT-EmotiMobileViTModality=Text + Video, Fusion=blending2026.030.41030.49320.4090.33270.45710.37110.393
RoBERTa + MT-EmotiMobileFaceNetModality=Text + Video, Fusion=blending2026.030.40740.44080.38770.36320.50640.3650.3814
RoBERTa + MT-EmotiMobileViTModality=Text + Video, Fusion=blending2026.030.40280.43790.39110.3580.48020.36560.384
OpenAI (small)Modality=Text, Features=Embeddings (mean)2026.030.40110.51130.38250.36870.48470.33630.3233
GigaChat + HuBERTModality=Text + Audio, Fusion=early2026.030.40110.47940.37330.41820.44490.35160.3395
GigaChatModality=Text, Features=Embeddings (mean)2026.030.40010.48880.36480.37320.48620.37260.3151
RoBERTa + HuBERTModality=Text + Audio, Fusion=blending2026.030.39740.46440.37270.38140.47550.34770.343
Wav2Vec2.0+VADModality=Audio, Features=-2026.030.389——————
OpenAI + MT-EmotiMobileFaceNetModality=Text + Video, Fusion=blending2026.030.38870.47790.35930.33690.43730.34520.3758
SentenceE5Modality=Text, Features=Embeddings (mean)2026.030.37770.47190.34970.34170.45530.32930.3184
RoBERTa (emotional)Modality=Text, Features=Embeddings (mean)2026.030.37630.45580.33280.34270.49640.32010.3099
SentenceBERTModality=Text, Features=Embeddings (mean)2026.030.37560.4710.35850.35890.43470.31860.3119
RoBERTa (emotional)Modality=Text, Features=Embeddings (STAT)2026.030.36970.45010.33260.31730.48430.33310.3008
Sentence all-MiniLMModality=Text, Features=Embeddings (mean)2026.030.35370.45520.30760.33710.41110.30930.3023
ResNet18+AUs+Wav2Vec2.0Modality=Audio+Video, Features=-2026.030.3288——————
HuBERTModality=Audio, Features=Embeddings (mean)2026.030.30450.36440.31790.29870.31110.28480.2499
wav2vec 2.0 + MT-EmotiMobileFaceNetModality=Audio + Video2026.030.28980.30410.30040.25840.31480.3160.2452
wav2vec 2.0 + MT-EmotiMobileViTModality=Audio + Video2026.030.28290.30110.29680.25950.30740.31710.2152
HuBERTModality=Audio, Features=Embeddings (STAT)2026.030.27290.35850.24540.24320.30650.25660.2275
ViT+wav2Vec2Modality=Audio+Video, Features=-2026.030.25——————
wav2Vec2Modality=Audio, Features=-2026.030.24——————
wav2vec 2.0Modality=Audio, Features=Embeddings (STAT)2026.030.23110.30060.16590.25590.31980.18440.1602
MT-EmotiMobileViTModality=Faces, Features=Scores (STAT)2026.030.17760.06190.26230.12470.07730.25440.2849
MT-EmotiMobileFaceNetModality=Faces, Features=Scores (STAT)2026.030.17320.02850.24980.13180.0970.25430.2776
MT-EmotiMobileViTModality=Faces, Features=Embeddings (STAT)2026.030.16830.04330.24590.13470.07790.23820.2699
MT-EmotiMobileFaceNetModality=Faces, Features=Scores (mean)2026.030.16670.02760.23670.13360.08070.25160.2699
MT-EmotiMobileFaceNetModality=Faces, Features=Embeddings (STAT)2026.030.16460.05570.2380.13030.07030.23250.2605
MT-EmotiMobileViTModality=Faces, Features=Embeddings (mean)2026.030.16440.03790.23140.13870.07810.23340.2672
MT-EmotiMobileViTModality=Faces, Features=Scores (mean)2026.030.16420.03210.24840.1490.06740.23990.2481
MT-EmotiMobileFaceNetModality=Faces, Features=Embeddings (mean)2026.030.15180.02150.22880.1140.06920.22990.2476
wav2vec 2.0Modality=Audio, Features=Embeddings (mean)2026.030.15140.21530.11760.18340.14260.12750.1219
Baseline ViTModality=Faces, Features=-2026.030.09——————