mlsanityData to 7 Oct 2026

Imitation Learning for Human Pose Prediction

arXiv 1909.03449 ↗First posted 8 Sep 2019cs.CVcited by 44

On the map: Offline RL and imitation learning from data → Imitation learning methods

Abstract (arXiv)

Modeling and prediction of human motion dynamics has long been a challenging problem in computer vision, and most existing methods rely on the end-to-end supervised training of various architectures of recurrent neural networks. Inspired by the recent success of deep reinforcement learning methods, in this paper we propose a new reinforcement learning formulation for the problem of human pose prediction, and develop an imitation learning algorithm for predicting future poses under this formulation through a combination of behavioral cloning and generative adversarial imitation learning. Our experiments show that our proposed method outperforms all existing state-of-the-art baseline models by large margins on the task of human pose prediction in both short-term predictions and long-term predictions, while also enjoying huge advantage in training speed.

Key facts. Cited by 44 papers in the map (data through 7 Oct 2026). Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data. Builds on 29 of its 54 references that are in the map. First posted on arXiv 8 Sep 2019.

Builds on

29 of 54 references.

References · 29

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2015Continuous control with deep reinforcement learningcited by 3,279
  3. 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
  4. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  5. 2015Trust Region Policy Optimizationcited by 2,503
  6. 2017Improved Training of Wasserstein GANscited by 2,223
  7. 2016Generative Adversarial Imitation Learningcited by 1,576
  8. 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,303
  9. 2017Wasserstein GANcited by 635
  10. 2016Generating Videos with Scene Dynamicscited by 376
  11. 2017On human motion prediction using recurrent neural networkscited by 336
  12. 2015Structural-RNN: Deep Learning on Spatio-Temporal Graphscited by 234
17 more
  1. 2017HP-GAN: Probabilistic 3D human motion prediction via GANcited by 176
  2. 2017VNect: Real-time 3D Human Pose Estimation with a Single RGB Cameracited by 129
  3. 2019Peeking into the Future: Predicting Future Person Activities and Locations in Videoscited by 112
  4. 2019Procedure Planning in Instructional Videoscited by 92
  5. 2017The Pose Knows: Video Forecasting by Generating Pose Futurescited by 88
  6. 2016An Uncertain Future: Forecasting from Static Images using Variational Autoencoderscited by 86
  7. 2018MT-VAE: Learning Motion Transformations to Generate Multimodal Human Dynamicscited by 86
  8. 2017Learning Human Motion Models for Long-term Predictionscited by 67
  9. 2018Learning Plannable Representations with Causal InfoGANcited by 56
  10. 2018Action-Agnostic Human Pose Forecastingcited by 56
  11. 2017Predicting Deeper into the Future of Semantic Segmentationcited by 51
  12. 2017Socially Compliant Navigation through Raw Depth Inputs with Generative Adversarial Imitation Learningcited by 50
  13. 2015Dense Optical Flow Prediction from a Static Imagecited by 36
  14. 2017Wasserstein Divergence for GANscited by 22
  15. 2017Forecasting Human Dynamics from Static Imagescited by 17
  16. 2017Visual Forecasting by Imitating Dynamics in Natural Sequencescited by 14
  17. 2016Geometry-Based Next Frame Prediction from Monocular Videocited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 14; 2022: 11; 2023: 9; 2024: 4; 2025: 4; 2026: 1.

44 papers.

Sort:

By area:

  1. 2021AI Choreographer: Music Conditioned 3D Dance Generation with AIST++cited by 479
  2. 2022PhysDiff: Physics-Guided Human Motion Diffusion Modelcited by 365
  3. 2021SAGA: Stochastic Whole-Body Grasping with Contactcited by 89
  4. 2021Space-Time-Separable Graph Convolutional Network for Pose Forecastingcited by 84
  5. 2021Generating Smooth Pose Sequences for Diverse Human Motion Predictioncited by 66
  6. 2021TRiPOD: Human Trajectory and Pose Dynamics Forecasting in the Wildcited by 52
  7. 2022Spatio-Temporal Gating-Adjacency GCN for Human Motion Predictioncited by 48
  8. 2023Diverse Human Motion Prediction Guided by Multi-Level Spatial-Temporal Anchorscited by 34
  9. 2022The Boltzmann Policy Distribution: Accounting for Systematic Suboptimality in Human Modelscited by 31
  10. 2021Conditional Neural Relational Inference for Interacting Systemscited by 28
  11. 2022Contact-aware Human Motion Forecastingcited by 27
  12. 2022Weakly-supervised Action Transition Learning for Stochastic Human Motion Predictioncited by 26
32 more
  1. 2022MoCapAct: A Multi-Task Dataset for Simulated Humanoid Controlcited by 24
  2. 2025UniEgoMotion: A Unified Model for Egocentric Motion Reconstruction, Forecasting, and Generationcited by 17
  3. 2022MotionAug: Augmentation with Physical Correction for Human Motion Predictioncited by 13
  4. 20223D Pose Based Feedback for Physical Exercisescited by 11
  5. 2024MaIL: Improving Imitation Learning with Mambacited by 11
  6. 2021Learning Multiscale Correlations for Human Motion Predictioncited by 9
  7. 2021Conditional Temporal Variational AutoEncoder for Action Video Predictioncited by 9
  8. 2021Dyadic Human Motion Predictioncited by 9
  9. 2023Best Practices for 2-Body Pose Forecastingcited by 8
  10. 2023Social Motion Prediction with Cognitive Hierarchiescited by 8
  11. 2023Scene-aware Human Motion Forecasting via Mutual Distance Predictioncited by 7
  12. 2020On the Guaranteed Almost Equivalence between Imitation Learning from Observation and Demonstrationcited by 6
  13. 2022SoMoFormer: Social-Aware Motion Transformer for Multi-Person Motion Predictioncited by 6
  14. 2021Review of Video Predictive Understanding: Early Action Recognition and Future Action Predictioncited by 5
  15. 2022FutureHuman3D: Forecasting Complex Long-Term 3D Human Behavior from Video Observationscited by 5
  16. 2025RoboSSM: Scalable In-context Imitation Learning via State-Space Modelscited by 5
  17. 2021Uncertainty-aware Human Motion Predictioncited by 4
  18. 2023SPOTR: Spatio-temporal Pose Transformers for Human Motion Predictioncited by 4
  19. 2023AnyPose: Anytime 3D Human Pose Forecasting via Neural Ordinary Differential Equationscited by 4
  20. 2024Towards more realistic human motion prediction with attention to motion coordinationcited by 4
  21. 2024Few-Shot Task Learning through Inverse Generative Modelingcited by 4
  22. 2021Learning to Predict Diverse Human Motions from a Single Image via Mixture Density Networkscited by 3
  23. 2023Data-Driven Stochastic Motion Evaluation and Optimization with Image by Spatially-Aligned Temporal Encodingcited by 3
  24. 2023Dance Generation by Sound Symbolic Wordscited by 2
  25. 2021Make Bipedal Robots Learn How to Imitatecited by 0
  26. 2021An Attractor-Guided Neural Networks for Skeleton-Based Human Motion Predictioncited by 0
  27. 2022Unified Simulation, Perception, and Generation of Human Behaviorcited by 0
  28. 2023All by Myself: Learning Individualized Competitive Behaviour with a Contrastive Reinforcement Learning optimizationcited by 0
  29. 2024CrowdTransfer: Enabling Crowd Knowledge Transfer in AIoT Communitycited by 0
  30. 2025Stochastic Human Motion Prediction with Memory of Action Transition and Action Characteristiccited by 0
  31. 2025GGMotion: Group Graph Dynamics-Kinematics Networks for Human Motion Predictioncited by 0
  32. 2026Online Intention Prediction via Control-Informed Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2019Model-based Behavioral Cloning with Future Image Similarity Learning
  2. 2023One-Shot Imitation Learning: A Pose Estimation Perspective
  3. 2022Resolving Copycat Problems in Visual Imitation Learning via Residual Action Prediction
  4. 2025Imitation Learning in the Deep Learning Era: A Novel Taxonomy and Recent Advances
  5. 2024Deep Generative Models in Robotics: A Survey on Learning from Multimodal Demonstrations
  6. 2023Sample-efficient Adversarial Imitation Learning
  7. 2023Adversarial Imitation Learning from Visual Observations using Latent Information
  8. 2022A generic diffusion-based approach for 3D human pose prediction in the wild