Research map / Video / Video generation
Learning Spatial-Temporal Coherent Correlations for Speech-Preserving Facial Expression Manipulation
Tianshui Chen, Jianman Lin, Zhijing Yang, Chunmei Qing, Guangrun Wang, Liang Lin
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add STCCL supervision (VD) | NED · MEAD Cross-ID | FAD: 4.448 -> 4.169 | Improved |
| add STCCL supervision (VD) | NED · MEAD Cross-ID | LSE-D: 9.906 -> 9.216 | Improved |
| add STCCL supervision (VD) | EAT · MEAD Cross-ID | LSE-D: 10.023 to 9.381 | Improved |
| add STCCL supervision (VD) | DICE-Talk · MEAD Cross-ID | FAD: 2.666 to 2.470 | Improved |
| add STCCL supervision (VD) | ICface · MEAD Intra-ID | FAD: 6.795 -> 6.634 | Improved |
| replace preliminary ASCCL with extended STCCL (VD) | NED · MEAD Intra-ID | FAD: 1.234 to 1.077 | Improved |
| train STCCL metric with paired data instead of untrained (ablation) | NED + STCCL (VD) · MEAD Cross-ID | FAD: 4.301 to 4.169 | Improved |
| train STCCL metric with paired data instead of untrained (ablation) | NED + STCCL (CM) · MEAD Cross-ID | FAD: 4.320 to 4.253 | Improved |
| add temporal TCC metric to SCC-only (ablation) | NED + STCCL · MEAD Intra-ID | FAD: 1.229 -> 1.077 | Improved |
| add spatial SCC metric to TCC-only (ablation) | NED + STCCL · MEAD Intra-ID | FAD: 1.342 -> 1.077 | Improved |
| add correlation-aware adaptive weighting (CAAS) (ablation) | NED + STCCL · MEAD Cross-ID | FAD: 4.228 -> 4.169 | Improved |
| add correlation-aware adaptive weighting (CAAS) (ablation) | NED + STCCL (CM) · MEAD Cross-ID | FAD: 4.255 -> 4.253 | No clear effect |
Closest papers by meaning
- Learning Adaptive Spatial Coherent Correlations for Speech-Preserving Facial Expression Manipulation (CVPR 2024 · similarity 0.98)
- DEEPTalk: Dynamic Emotion Embedding for Probabilistic Speech-Driven 3D Face Animation (AAAI 2025 · similarity 0.88)
- Cafe-Talk: Generating 3D Talking Face Animation with Multimodal Coarse- and Fine-grained Control (ICLR 2025 · similarity 0.87)
- ProsodyTalker: 3D Visual Speech Animation via Prosody Decomposition (AAAI 2025 · similarity 0.87)
- KeyFace: Expressive Audio-Driven Facial Animation for Long Sequences via KeyFrame Interpolation (CVPR 2025 · similarity 0.86)
- Seeing Speech: Learning Visible Articulatory Dynamics for Speech-Driven 3D Facial Animation (NeurIPS 2026 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
