Research map / Probabilistic and scientific modeling / Dynamical systems
Dynamical Deep Generative Latent Modeling of 3D Skeletal Motion
Amirreza Farnoosh, Sarah Ostadabbas
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 second-order lag (l={1,2}) instead of first-order lag (ablation) | Ours · Pendulum | NRMSE (%): 7.54 -> 5.97 | Improved |
| use nonlinear higher-order switching VAR instead of first-order linear transitions (rSLDS) | switching dynamical model · Pendulum | NRMSE (%): 25.58 -> 5.97 | Improved |
| add switching discrete states and higher-order lags (ablation) | Ours · Pendulum, Salsa, Bat, Walking, Golf | prediction accuracy | Improved |
| use proposed model instead of BTMF | Ours · Golf | NRMSE (%): 10.57 (closely following BTMF) | No clear effect |
| use nonlinear models (Ours, RKN, LSTNet) instead of linear baselines (rSLDS, SLDS, BTMF) | dynamical models · Pendulum | NRMSE (%) | Improved |
Closest papers by meaning
- LaDy: Lagrangian-Dynamic Informed Network for Skeleton-based Action Segmentation via Spatial-Temporal Modulation (CVPR 2026 · similarity 0.87)
- Neural Marionette: Unsupervised Learning of Motion Skeleton and Latent Dynamics from Volumetric Video (AAAI 2022 · similarity 0.87)
- Convolutional Sequence Generation for Skeleton-Based Action Synthesis (ICCV 2019 · similarity 0.86)
- HuMoR: 3D Human Motion Model for Robust Pose Estimation (ICCV 2021 · similarity 0.85)
- SAMoR: Motion Modelling for Articulated Objects of Any Skeleton and Topology (NeurIPS 2026 · similarity 0.84)
- Lifting Motion to the 3D World via 2D Diffusion (CVPR 2025 · similarity 0.84)
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.
