Author

Yongkang Xia

h-index 0 View on Semantic Scholar

We have 1 of 1 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

ETHead: Generating Expressive 3D Facial Animation and Head Movement from Speech

A self-distillation framework that leverages large-scale 2D talking videos to pre-train a specialized speech encoder that aligns speech representations with expressive visual dynamics, allowing the encoder to extract features highly correlated with facial and head motions directly from audio.

Jiu-Cheng Xie, Ji-Wang Zheng, Yongkang Xia et al. · 0 citations