mlsanityData to 7 Oct 2026

Motron: Multimodal Probabilistic Human Motion Forecasting

arXiv 2203.04132 ↗First posted 8 Mar 2022cs.CV cs.HC cs.LGcited by 30

Not on the map. Why?

Abstract (arXiv)

Autonomous systems and humans are increasingly sharing the same space. Robots work side by side or even hand in hand with humans to balance each other's limitations. Such cooperative interactions are ever more sophisticated. Thus, the ability to reason not just about a human's center of gravity position, but also its granular motion is an important prerequisite for human-robot interaction. Though, many algorithms ignore the multimodal nature of humans or neglect uncertainty in their motion forecasts. We present Motron, a multimodal, probabilistic, graph-structured model, that captures human's multimodality using probabilistic methods while being able to output deterministic maximum-likelihood motions and corresponding confidence values for each mode. Our model aims to be tightly integrated with the robotic planning-control-interaction loop; outputting physically feasible human motions and being computationally efficient. We demonstrate the performance of our model on several challenging real-world motion forecasting datasets, outperforming a wide array of generative/variational methods while providing state-of-the-art single-output motions if required. Both using significantly less computational power than state-of-the art algorithms.

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). Builds on 32 of its 56 references that are in the map. First posted on arXiv 8 Mar 2022.

Builds on

32 of 56 references.

References · 32

  1. 2017Attention Is All You Needcited by 59,932
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2017Graph Attention Networkscited by 8,854
  4. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  5. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,571
  6. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,208
  7. 2018Pyro: Deep Universal Probabilistic Programmingcited by 379
  8. 2017On human motion prediction using recurrent neural networkscited by 336
  9. 2019Learning Trajectory Dependencies for Human Motion Predictioncited by 245
  10. 2015Structural-RNN: Deep Learning on Spatio-Temporal Graphscited by 234
  11. 2019Social-BiGAT: Multimodal Trajectory Forecasting using Bicycle-GAN and Graph Attention Networkscited by 228
  12. 2016Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoderscited by 219
20 more
  1. 2020DLow: Diversifying Latent Flows for Diverse Human Motion Predictioncited by 184
  2. 2019Multiple Futures Predictioncited by 178
  3. 2017HP-GAN: Probabilistic 3D human motion prediction via GANcited by 176
  4. 2020History Repeats Itself: Human Motion Prediction via Motion Attentioncited by 164
  5. 2020A Spatio-temporal Transformer for 3D Human Motion Predictioncited by 133
  6. 2020Dynamic Multiscale Graph Neural Networks for 3D Skeleton-Based Human Motion Predictioncited by 132
  7. 2020We are More than Our Joints: Predicting how 3D Bodies Movecited by 115
  8. 2017The Pose Knows: Video Forecasting by Generating Pose Futurescited by 88
  9. 2018MT-VAE: Learning Motion Transformations to Generate Multimodal Human Dynamicscited by 86
  10. 2019Diverse Trajectory Forecasting with Determinantal Point Processescited by 80
  11. 2017DeLiGAN : Generative Adversarial Networks for Diverse and Limited Datacited by 77
  12. 2017Learning Human Motion Models for Long-term Predictionscited by 67
  13. 2018Accurate and Diverse Sampling of Sequences based on a "Best of Many" Sample Objectivecited by 56
  14. 2018BiHMP-GAN: Bidirectional 3D Human Motion Prediction GANcited by 55
  15. 2019Modeling Human Motion with Quaternion-based Neural Networkscited by 45
  16. 2018Long-Term Human Motion Prediction by Modeling Motion Context and Enhancing Motion Dynamiccited by 41
  17. 2020A Smooth Representation of Belief over SO(3) for Deep Rotation Learning with Uncertaintycited by 29
  18. 2018Generative Modeling of Multimodal Multi-Human Behaviorcited by 24
  19. 2014Efficient Evaluation of the Probability Density Function of a Wrapped Normal Distributioncited by 3
  20. 2017Approximation of probability density functions on the Euclidean group parametrized by dual quaternionscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 11; 2024: 6; 2025: 7; 2026: 3.

30 papers.

Sort:

By area:

  1. 2022BeLFusion: Latent Diffusion for Behavior-Driven Human Motion Predictioncited by 82
  2. 2023HumanMAC: Masked Motion Completion for Human Motion Predictioncited by 81
  3. 2024Seamless Human Motion Composition with Blended Positional Encodingscited by 77
  4. 2023SINC: Spatial Composition of 3D Human Motions for Simultaneous Action Generationcited by 62
  5. 2023Emotional Speech-driven 3D Body Animation via Disentangled Latent Diffusioncited by 39
  6. 2023Diverse Human Motion Prediction Guided by Multi-Level Spatial-Temporal Anchorscited by 34
  7. 2022A generic diffusion-based approach for 3D human pose prediction in the wildcited by 33
  8. 2024AnySkill: Learning Open-Vocabulary Physical Skill for Interactive Agentscited by 32
  9. 2024Multi-agent Long-term 3D Human Pose Forecasting via Interaction-aware Trajectory Conditioningcited by 29
  10. 2023Interactive Humanoid: Online Full-Body Motion Reaction Synthesis with Social Affordance Canonicalization and Forecastingcited by 27
  11. 2023Robots That Can See: Leveraging Human Pose for Trajectory Predictioncited by 22
  12. 2023CoMusion: Towards Consistent Stochastic Human Motion Prediction via Motion Diffusioncited by 21
18 more
  1. 2023Auxiliary Tasks Benefit 3D Skeleton-based Human Motion Predictioncited by 20
  2. 2025Nonisotropic Gaussian Diffusion for Realistic 3D Human Motion Predictioncited by 12
  3. 2023Toward Reliable Human Pose Forecasting with Uncertaintycited by 11
  4. 2024MotionWavelet: Human Motion Prediction via Wavelet Manifold Learningcited by 8
  5. 2024Normalizing Flows on the Product Space of SO(3) Manifolds for Probabilistic Human Pose Modelingcited by 7
  6. 2024MotionMap: Representing Multimodality in Human Pose Forecastingcited by 7
  7. 2022FutureHuman3D: Forecasting Complex Long-Term 3D Human Behavior from Video Observationscited by 5
  8. 2023DeFeeNet: Consecutive 3D Human Motion Prediction with Deviation Feedbackcited by 4
  9. 2025CacheFlow: Fast Human Motion Prediction by Cached Normalizing Flowcited by 4
  10. 2025Uncertainty-aware Probabilistic 3D Human Motion Forecasting via Invertible Networkscited by 2
  11. 2025MMCM: Multimodality-aware Metric using Clustering-based Modes for Probabilistic Human Motion Predictioncited by 1
  12. 20233D Pose Nowcasting: Forecast the Future to Improve the Presentcited by 0
  13. 2025Stochastic Human Motion Prediction with Memory of Action Transition and Action Characteristiccited by 0
  14. 2025Cross-Modal Alignment via Variational Copula Modellingcited by 0
  15. 2025SMamDiff: Spatial Mamba for Stochastic Human Motion Predictioncited by 0
  16. 2026Capturing Uncertainty in Human Motion for Representation Learning in Soccercited by 0
  17. 2026Gaussian-Mixture Latent Flow for Stochastic 3D Human Motion Predictioncited by 0
  18. 2026Probabilistic electrical power demand forecasting with uncertainty quantificationcited by 0