Research map / 3D vision / 3D generation
Beyond Talking – Generating Holistic 3D Human Dyadic Motion for Communication
Mingze Sun, Chao Xu, Xinyu Jiang, Yang Liu, Baigui Sun, Ruqi Huang
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 |
|---|---|---|---|
| replace wav2vec features with decoupled audio features | TalkSHOW · SHOW | Body&Hands FGD: 2.049 -> 1.902 | Improved |
| replace wav2vec features with decoupled audio features | TalkSHOW · SHOW | Body&Hands Variation: 0.332 -> 0.328 | No clear effect |
| add text feature (ablation) | Ours · HoCo | Speaker FGD: 0.569 -> 0.558 | Improved |
| add text feature (ablation) | Ours · HoCo | Listener FGD: 0.354 -> 0.253 | Improved |
| add text feature (ablation) | Ours · HoCo | Speaker Variation: 0.514 -> 0.492 | Hurt |
| add style feature (ablation) | Ours · HoCo | Speaker FGD: 0.591 -> 0.558 | Improved |
| add style feature (ablation) | Ours · HoCo | Listener FGD: 0.305 -> 0.253 | Improved |
| add style feature (ablation) | Ours · HoCo | Listener Variation: 0.276 -> 0.261 | Hurt |
| add self and speaker-listener chain design (ablation) | Ours · HoCo | Speaker FGD: 0.864 -> 0.558 | Improved |
| add self and speaker-listener chain design (ablation) | Ours · HoCo | Listener FGD: 0.421 -> 0.253 | Improved |
| add self and speaker-listener chain design (ablation) | Ours · HoCo | Listener CCC: 0.142 -> 0.187 | Improved |
| add speaker-listener chain interaction (ablation) | Ours · HoCo | Speaker FGD: 0.761 -> 0.558 | Improved |
Closest papers by meaning
- Towards Variable and Coordinated Holistic Co-Speech Motion Generation (CVPR 2024 · similarity 0.89)
- Full-Duplex Speech-Motion Model for Dyadic Interaction (NeurIPS 2026 · similarity 0.88)
- The Language of Motion: Unifying Verbal and Non-verbal Language of 3D Human Motion (CVPR 2025 · similarity 0.87)
- DiffSHEG: A Diffusion-Based Approach for Real-Time Speech-driven Holistic 3D Expression and Gesture Generation (CVPR 2024 · similarity 0.87)
- FaceTalk: Audio-Driven Motion Diffusion for Neural Parametric Head Models (CVPR 2024 · similarity 0.87)
- Co$^{\mathbf{3}}$Gesture: Towards Coherent Concurrent Co-speech 3D Gesture Generation with Interactive Diffusion (ICLR 2025 · 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.
