mlsanityData to 7 Oct 2026

Personalized Pose Forecasting

arXiv 2312.03528 ↗First posted 6 Dec 2023cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Human pose forecasting is the task of predicting articulated human motion given past human motion. There exists a number of popular benchmarks that evaluate an array of different models performing human pose forecasting. These benchmarks do not reflect that a human interacting system, such as a delivery robot, observes and plans for the motion of the same individual over an extended period of time. Every individual has unique and distinct movement patterns. This is however not reflected in existing benchmarks that evaluate a model's ability to predict an average human's motion rather than a particular individual's. We reformulate the human motion forecasting problem and present a model-agnostic personalization method. Motion forecasting personalization can be performed efficiently online by utilizing a low-parametric time-series analysis model that personalizes neural network pose predictions.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 49 of its 84 references that are in the map. First posted on arXiv 6 Dec 2023.

Builds on

49 of 84 references.

References · 49

  1. 2021Action-Conditioned 3D Human Motion Synthesis with Transformer VAEcited by 497
  2. 2017On human motion prediction using recurrent neural networkscited by 336
  3. 2021BABEL: Bodies, Action and Behavior with English Labelscited by 261
  4. 2019Learning Trajectory Dependencies for Human Motion Predictioncited by 245
  5. 2016Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoderscited by 219
  6. 2017HP-GAN: Probabilistic 3D human motion prediction via GANcited by 176
  7. 2020Synthesizing Long-Term 3D Human Motion and Interaction in 3D Scenescited by 135
  8. 2021MSR-GCN: Multi-Scale Residual Graph Convolution Networks for Human Motion Predictioncited by 100
  9. 2022Back to MLP: A Simple Baseline for Human Motion Predictioncited by 99
  10. 2018MT-VAE: Learning Motion Transformations to Generate Multimodal Human Dynamicscited by 86
  11. 2021Space-Time-Separable Graph Convolutional Network for Pose Forecastingcited by 84
  12. 2022BeLFusion: Latent Diffusion for Behavior-Driven Human Motion Predictioncited by 82
37 more
  1. 2019Diverse Trajectory Forecasting with Determinantal Point Processescited by 80
  2. 2022ActFormer: A GAN-based Transformer towards General Action-Conditioned 3D Human Motion Generationcited by 77
  3. 2021Multi-Person Extreme Motion Predictioncited by 74
  4. 2021Generating Smooth Pose Sequences for Diverse Human Motion Predictioncited by 66
  5. 2022Progressively Generating Better Initial Guesses Towards Next Stages for High-Quality Human Motion Predictioncited by 66
  6. 2021Multi-Person 3D Motion Prediction with Multi-Range Transformerscited by 63
  7. 2022Implicit Neural Representations for Variable Length Human Motion Generationcited by 61
  8. 2021TRiPOD: Human Trajectory and Pose Dynamics Forecasting in the Wildcited by 52
  9. 2020Socially and Contextually Aware Human Motion and Pose Forecastingcited by 51
  10. 2023Locomotion-Action-Manipulation: Synthesizing Human-Scene Interactions in Complex 3D Environmentscited by 51
  11. 2022MultiAct: Long-Term 3D Human Motion Generation from Multiple Action Labelscited by 45
  12. 2021Multi-level Motion Attention for Human Motion Predictioncited by 35
  13. 2022A generic diffusion-based approach for 3D human pose prediction in the wildcited by 33
  14. 2021Investigating Pose Representations and Motion Contexts Modeling for 3D Motion Predictioncited by 30
  15. 20223D Human Motion Prediction: A Surveycited by 30
  16. 2022Skeleton-Parted Graph Scattering Networks for 3D Human Motion Predictioncited by 29
  17. 2022Weakly-supervised Action Transition Learning for Stochastic Human Motion Predictioncited by 26
  18. 2022Pose Forecasting in Industrial Human-Robot Collaborationcited by 24
  19. 2022SoMoFormer: Multi-Person Pose Forecasting with Transformerscited by 23
  20. 2017Human Pose Forecasting via Deep Markov Modelscited by 16
  21. 2020Forecasting Characteristic 3D Poses of Human Actionscited by 16
  22. 2022Motion Prediction via Joint Dependency Modeling in Phase Spacecited by 16
  23. 2022HiT-DVAE: Human Motion Generation via Hierarchical Transformer Dynamical VAEcited by 16
  24. 2022MotionAug: Augmentation with Physical Correction for Human Motion Predictioncited by 13
  25. 2020AirCapRL: Autonomous Aerial Human Motion Capture using Deep Reinforcement Learningcited by 11
  26. 2021Learning Human Motion Prediction via Stochastic Differential Equationscited by 11
  27. 2021Learning Multiscale Correlations for Human Motion Predictioncited by 9
  28. 2021Dyadic Human Motion Predictioncited by 9
  29. 2022VL4Pose: Active Learning Through Out-Of-Distribution Detection For Pose Estimationcited by 9
  30. 2021Human Motion Prediction Using Manifold-Aware Wasserstein GANcited by 8
  31. 2022PaCMO: Partner Dependent Human Motion Generation in Dyadic Human Activity using Neural Operatorscited by 8
  32. 2020Long Term Motion Prediction Using Keyposescited by 6
  33. 2021Uncertainty-aware Human Motion Predictioncited by 4
  34. 2017Gait Recognition from Motion Capture Datacited by 3
  35. 20223D Skeleton-based Human Motion Prediction with Manifold-Aware GANcited by 3
  36. 2021Probabilistic Human Motion Prediction via A Bayesian Neural Networkcited by 2
  37. 2022Few-shot human motion prediction for heterogeneous sensorscited by 2

Built on by

Not cited yet.