mlsanityData to 14 Oct 2026

Human Motion Prediction under Unexpected Perturbation

arXiv 2403.15891 ↗First posted 23 Mar 2024cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

We investigate a new task in human motion prediction, which is predicting motions under unexpected physical perturbation potentially involving multiple people. Compared with existing research, this task involves predicting less controlled, unpremeditated and pure reactive motions in response to external impact and how such motions can propagate through people. It brings new challenges such as data scarcity and predicting complex interactions. To this end, we propose a new method capitalizing differential physics and deep neural networks, leading to an explicit Latent Differential Physics (LDP) model. Through experiments, we demonstrate that LDP has high data efficiency, outstanding prediction accuracy, strong generalizability and good explainability. Since there is no similar research, a comprehensive comparison with 11 adapted baselines from several relevant domains is conducted, showing LDP outperforming existing research both quantitatively and qualitatively, improving prediction accuracy by as much as 70%, and demonstrating significantly stronger generalization.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 34 of its 78 references that are in the map. First posted on arXiv 23 Mar 2024.

Builds on

34 of 78 references.

References · 34

  1. 2022Human Motion Diffusion Modelcited by 1,080
  2. 2021Action-Conditioned 3D Human Motion Synthesis with Transformer VAEcited by 501
  3. 2020Action2Motion: Conditioned Generation of 3D Human Motionscited by 441
  4. 2023ReMoDiffuse: Retrieval-Augmented Motion Diffusion Modelcited by 287
  5. 2015Structural-RNN: Deep Learning on Spatio-Temporal Graphscited by 234
  6. 2023Perpetual Humanoid Control for Real-time Simulated Avatarscited by 218
  7. 2021Character Controllers Using Motion VAEscited by 184
  8. 2020A Spatio-temporal Transformer for 3D Human Motion Predictioncited by 133
  9. 2020Dynamic Multiscale Graph Neural Networks for 3D Skeleton-Based Human Motion Predictioncited by 132
  10. 2018QuaterNet: A Quaternion-based Recurrent Model for Human Motioncited by 109
  11. 2021MSR-GCN: Multi-Scale Residual Graph Convolution Networks for Human Motion Predictioncited by 100
  12. 2022Back to MLP: A Simple Baseline for Human Motion Predictioncited by 100
22 more
  1. 2018Latent-space Physics: Towards Learning the Temporal Evolution of Fluid Flowcited by 97
  2. 2023EqMotion: Equivariant Multi-agent Motion Prediction with Invariant Interaction Reasoningcited by 97
  3. 2021Physics-based Human Motion Estimation and Synthesis from Videoscited by 66
  4. 2022Human Trajectory Prediction via Neural Social Physicscited by 66
  5. 2021Multi-Person 3D Motion Prediction with Multi-Range Transformerscited by 63
  6. 2021Dynamic Visual Reasoning by Learning Differentiable Physics Models from Video and Languagecited by 55
  7. 2021Fast and Feature-Complete Differentiable Physics for Articulated Rigid Bodies with Contactcited by 52
  8. 2022Differentiable Physics Simulation of Dynamics-Augmented Neural Objectscited by 45
  9. 2022Differentiable Dynamics for Articulated 3d Human Motion Reconstructioncited by 39
  10. 2021Multiscale Spatio-Temporal Graph Neural Networks for 3D Skeleton-Based Motion Predictioncited by 37
  11. 2019Spatio-temporal Manifold Learning for Human Motions via Long-horizon Modelingcited by 32
  12. 2021High-order Differentiable Autoencoder for Nonlinear Model Reductioncited by 32
  13. 2022Real-time Controllable Motion Transition for Characterscited by 29
  14. 2023Stochastic Multi-Person 3D Motion Forecastingcited by 28
  15. 2023Trajectory-Aware Body Interaction Transformer for Multi-Person Pose Forecastingcited by 26
  16. 2023RSMT: Real-time Stylized Motion Transition for Characterscited by 19
  17. 2023Joint-Relation Transformer for Multi-Person Motion Predictioncited by 16
  18. 2020Dynamic Future Net: Diversified Human Motion Generationcited by 14
  19. 2022Fine-grained differentiable physics: a yarn-level model for fabricscited by 9
  20. 2023Human Trajectory Forecasting with Explainable Behavioral Uncertaintycited by 7
  21. 2020Sim2Sim Evaluation of a Novel Data-Efficient Differentiable Physics Engine for Tensegrity Robotscited by 6
  22. 2022Imitation Learning via Differentiable Physicscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 2.

5 papers.

  1. 2025Large-Scale Multi-Character Interaction Synthesiscited by 4
  2. 2025Human Motion Prediction, Reconstruction, and Generationcited by 1
  3. 2026Ego-Human Motion Prediction with 3D-Aware LLMcited by 1
  4. 2025Wearable-informed generative digital avatars predict task-conditioned post-stroke locomotioncited by 0
  5. 2026Encore: Conditioning Trajectory Forecasting via Biased Ego Rehearsalscited by 0