AtG-ContextNet: a temporal attention and hybrid gating architecture for facial blendshape coefficient regression
Abstract Driving facial expressions is critical for digital animation, yet resource-constrained systems still rely heavily on linear blendshape models. Existing methods struggle with feature redundancy in high-dimensional landmark prediction and numerical instability in extreme expression regions. T...
Gardado en:
| Principais autores: | , , , , |
|---|---|
| Formato: | Artigo |
| Idioma: | Inglês |
| Publicado: |
Springer
2026-04-01
|
| Series: | Journal of King Saud University: Computer and Information Sciences |
| Assuntos: | |
| Acceso en liña: | https://doi.org/10.1007/s44443-026-00699-2 |
| Tags: |
Sen Etiquetas, Sexa o primeiro en etiquetar este rexistro!
|