Learning Adaptive Spatial Coherent Correlations for Speech-Preserving Facial Expression Manipulation
Published in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024 — Highlight (top 2.8%) · CCF-A, 2024
ASCCL formulates learnable spatial-coherent correlation metrics and a DAAS module to reduce reliance on large paired emotion datasets, improving fine-grained mouth motion for speech-preserving facial expression editing.
Recommended citation: Tianshui Chen, Jianman Lin, Zhijing Yang, Chunmei Qing, Liang Lin. Learning Adaptive Spatial Coherent Correlations for Speech-Preserving Facial Expression Manipulation. CVPR, 2024.
Download Paper