Research map / Video / Video generation
Learning Diverse Stochastic Human-Action Generators by Learning Smooth Latent Transitions
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 latent-space and action-space smoothness regularizers (ablation) | Ours · Human3.6M | MMD_avg: 0.798 -> 0.195 | Helped |
| add latent-space and action-space smoothness regularizers (ablation) | Ours · Human3.6M | MMD_seq: 1.254 -> 0.218 | Helped |
| include both smoothness regularizers rather than only the action-space regularizer (ablation) | Ours · Human3.6M | MMD_avg: 0.396 -> 0.195 | Helped |
| include both smoothness regularizers rather than only the latent-space regularizer (ablation) | Ours · Human3.6M | MMD_avg: 0.214 -> 0.195 | Helped |
| include both smoothness regularizers rather than only the action-space regularizer (ablation) | Ours · Human3.6M | MMD_seq: 0.566 -> 0.218 | Helped |
| include both smoothness regularizers rather than only the latent-space regularizer (ablation) | Ours · Human3.6M | MMD_seq: 0.259 -> 0.218 | Helped |
| predict residual latent transitions instead of direct latent transitions (ablation) | Ours · Human3.6M | MMD_avg: 0.975 -> 0.195 | Helped |
| predict residual latent transitions instead of direct latent transitions (ablation) | Ours · Human3.6M | MMD_seq: 0.829 -> 0.218 | Helped |
| generate without seed motion using the proposed method rather than the no-seed baselines | Ours · Human3.6M, without seed motion | MMD_avg: 0.419 -> 0.195 | Helped |
| generate without seed motion using the proposed method rather than the no-seed baselines | Ours · Human3.6M, without seed motion | MMD_seq: 0.436 -> 0.218 | Helped |
Closest papers by meaning
- Stochastic Human Motion Prediction with Memory of Action Transition and Action Characteristic (CVPR 2025 · similarity 0.88)
- Motion Diversification Networks (CVPR 2024 · similarity 0.87)
- FutureHuman3D: Forecasting Complex Long-Term 3D Human Behavior from Video Observations (CVPR 2024 · similarity 0.87)
- Deterministic-to-Stochastic Diverse Latent Feature Mapping for Human Motion Synthesis (CVPR 2025 · similarity 0.87)
- HumanDreamer: Generating Controllable Human-Motion Videos via Decoupled Generation (CVPR 2025 · similarity 0.86)
- Recovering Complete Actions for Cross-dataset Skeleton Action Recognition (NeurIPS 2024 · 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.