List your company

Audio-driven Talking Head Generation on RAVDESS (cross-identity)

1.885FADDSM
1.583443.618975.65457.69003Jan 19, 2026Feb 3, 2026Feb 19, 2026Mar 6, 2026Mar 22, 2026Apr 6, 2026Apr 22, 2026

Evaluation results

MethodLinks
DSMEmotion=Neutral2026.011.8858.1080.848
DSM+EATEmotion=Neutral2026.011.8858.240.876
DSM+EATEmotion=Surprised2026.012.7278.1770.77
Ours_VDBackbone=DICE-Talk2026.042.9737.4970.795
Ours_CMBackbone=DICE-Talk2026.043.0347.4990.801
NED+EATEmotion=Neutral2026.013.0738.050.838
ASCCLBackbone=DICE-Talk2026.043.1067.6380.785
BaselineBackbone=DICE-Talk2026.043.2417.7780.775
DSMEmotion=Surprised2026.013.2928.0080.763
DSM+EAMMEmotion=Neutral2026.013.3538.3740.845
DSM+EATEmotion=Happy2026.013.5037.9770.8
NEDEmotion=Neutral2026.013.5597.9060.82
DSMEmotion=Happy2026.013.8188.2590.801
DSM+EATEmotion=Avg.2026.013.8798.0530.775
DSMEmotion=Avg.2026.014.2568.1650.756
DSM+EATEmotion=Sad2026.014.3958.060.76
DSMEmotion=Sad2026.014.4267.980.745
DSM+EATEmotion=Angry2026.014.4828.0770.747
DSM+EATEmotion=Fear2026.014.4898.0440.748
DSM+EAMMEmotion=Sad2026.014.5468.2760.787
DSM+EAMMEmotion=Angry2026.014.5588.4260.727
NED+EATEmotion=Surprised2026.014.6147.830.736
DSM+EAMMEmotion=Avg.2026.014.6248.3720.778
NED+EAMMEmotion=Neutral2026.014.6638.2250.803
DSM+EAMMEmotion=Happy2026.014.6948.4040.805
DSMEmotion=Angry2026.014.7078.330.706
Ours_VDBackbone=NED2026.044.7747.8030.767
DSMEmotion=Fear2026.014.7928.2070.732
Ours_CMBackbone=NED2026.044.7947.8040.772
ASCCLBackbone=NED2026.044.8087.820.761
NED+EATEmotion=Fear2026.014.8367.9740.74
DSM+EAMMEmotion=Disgusted2026.014.948.2720.809
DSM+EAMMEmotion=Surprised2026.014.948.3360.741
NEDEmotion=Fear2026.015.0068.1530.749
NED+EATEmotion=Avg.2026.015.1267.8740.777
NEDEmotion=Surprised2026.015.1357.9930.716
Ours_VDBackbone=EAT2026.045.1897.440.732
Ours_CMBackbone=EAT2026.045.267.4490.74
NED+EATEmotion=Angry2026.015.2718.0910.723
DSM+EAMMEmotion=Fear2026.015.3368.5140.731
NED+EATEmotion=Sad2026.015.377.7670.765
NED+EAMMEmotion=Angry2026.015.3758.3190.759
NEDEmotion=Avg.2026.015.4028.0570.76
BaselineBackbone=NED2026.045.4128.0340.76
NED+EAMMEmotion=Sad2026.015.4178.1060.769
ASCCLBackbone=EAT2026.045.5417.6820.716
NEDEmotion=Angry2026.015.5468.0770.766
NED+EAMMEmotion=Fear2026.015.5498.2090.759
NEDEmotion=Sad2026.015.5838.0340.726
NEDEmotion=Happy2026.015.6448.0870.804
NED+EAMMEmotion=Avg.2026.015.6758.1620.779
NED+EATEmotion=Happy2026.015.7877.9320.833
BaselineBackbone=EAT2026.045.8897.9210.7
NED+EAMMEmotion=Disgusted2026.016.1258.0910.845
NED+EAMMEmotion=Surprised2026.016.1878.3480.697
NED+EAMMEmotion=Happy2026.016.4157.8360.82
DSM+EATEmotion=Disgusted2026.016.8017.7940.727
DSMEmotion=Disgusted2026.016.878.2620.694
NED+EATEmotion=Disgusted2026.016.9297.4640.803
NEDEmotion=Disgusted2026.017.3428.1510.741
Ours_VDBackbone=ICface2026.048.910.3150.687
Ours_CMBackbone=ICface2026.048.90210.3120.691
ASCCLBackbone=ICface2026.049.08610.3130.682
BaselineBackbone=ICface2026.049.42411.5390.677