Research map / Video / Video generation
MindFlow: Harmonizing Cognitive Semantics and Acoustic Dynamics for Facial Animation Generation in Dyadic Conversations
Hejia Chen, Haoxian Zhang, Xu He, Xiaoqiang Liu, Pengfei Wan, Shoulong Zhang, Shuai Li
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 |
|---|---|---|---|
| use Ventral evolving emotion state instead of random guidance (ablation) | MindFlow Dorsal · VICO listening | FD expression: 15.21 -> 13.86 | Improved |
| use Ventral state instead of fixed sentence-level GT guidance (ablation) | MindFlow Dorsal · VICO listening | FD expression: 14.15 -> 13.86 | Improved |
| use Chunk-State instead of Sentence-Action reasoning (ablation) | MindFlow · VICO listening | FD expression: 14.39 -> 13.86 | Improved |
| add Selective Acoustic Injector (ablation) | MindFlow · HDTF talking | SyncC: 0.424 -> 0.520 | Improved |
| add Selective Acoustic Injector to A2P (ablation) | A2P · HDTF talking | SyncD: 0.341 -> 0.331 | Improved |
| increase chunk size (ablation) | Ventral module · user study | emotion accuracy vs perceptual synchronicity | Mixed |
| MindFlow vs A2P on listening | MindFlow · VICO listening | MSE expression: 0.34 -> 0.30 | Improved |
| MindFlow vs EmoTalk on lip vertex error | MindFlow · HDTF test set | LVE: 6.212 -> 6.305 | Hurt |
Closest papers by meaning
- INFP: Audio-Driven Interactive Head Generation in Dyadic Conversations (CVPR 2025 · similarity 0.90)
- DEEPTalk: Dynamic Emotion Embedding for Probabilistic Speech-Driven 3D Face Animation (AAAI 2025 · similarity 0.88)
- EmotiveTalk: Expressive Talking Head Generation through Audio Information Decoupling and Emotional Video Diffusion (CVPR 2025 · similarity 0.87)
- Full-Duplex Speech-Motion Model for Dyadic Interaction (NeurIPS 2026 · similarity 0.87)
- FaceTalk: Audio-Driven Motion Diffusion for Neural Parametric Head Models (CVPR 2024 · similarity 0.87)
- Style2Talker: High-Resolution Talking Head Generation with Emotion Style and Art Style (AAAI 2024 · similarity 0.87)
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.
