mlsanityData to 14 Oct 2026

MotionMixer: MLP-based 3D Human Body Pose Forecasting

arXiv 2207.00499 ↗First posted 1 Jul 2022cs.CV cs.LGcited by 42

Not on the map. Why?

Abstract (arXiv)

In this work, we present MotionMixer, an efficient 3D human body pose forecasting model based solely on multi-layer perceptrons (MLPs). MotionMixer learns the spatial-temporal 3D body pose dependencies by sequentially mixing both modalities. Given a stacked sequence of 3D body poses, a spatial-MLP extracts fine grained spatial dependencies of the body joints. The interaction of the body joints over time is then modelled by a temporal MLP. The spatial-temporal mixed features are finally aggregated and decoded to obtain the future motion. To calibrate the influence of each time step in the pose sequence, we make use of squeeze-and-excitation (SE) blocks. We evaluate our approach on Human3.6M, AMASS, and 3DPW datasets using the standard evaluation protocols. For all evaluations, we demonstrate state-of-the-art performance, while having a model with a smaller number of parameters. Our code is available at: https://github.com/MotionMLP/MotionMixer

Key facts. Cited by 42 papers in the map (data through 14 Oct 2026). Builds on 19 of its 34 references that are in the map. First posted on arXiv 1 Jul 2022.

Builds on

19 of 34 references.

References · 19

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2016Layer Normalizationcited by 5,669
  4. 2017Squeeze-and-Excitation Networkscited by 4,789
  5. 2016Gaussian Error Linear Units (GELUs)cited by 3,502
  6. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,446
  7. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,236
  8. 2017On human motion prediction using recurrent neural networkscited by 338
  9. 2019Learning Trajectory Dependencies for Human Motion Predictioncited by 246
  10. 2020History Repeats Itself: Human Motion Prediction via Motion Attentioncited by 165
  11. 2020A Spatio-temporal Transformer for 3D Human Motion Predictioncited by 133
  12. 2018Convolutional Sequence to Sequence Model for Human Dynamicscited by 115
7 more
  1. 2021MSR-GCN: Multi-Scale Residual Graph Convolution Networks for Human Motion Predictioncited by 100
  2. 2021Space-Time-Separable Graph Convolutional Network for Pose Forecastingcited by 84
  3. 2022Spatio-Temporal Gating-Adjacency GCN for Human Motion Predictioncited by 48
  4. 2018Long-Term Human Motion Prediction by Modeling Motion Context and Enhancing Motion Dynamiccited by 41
  5. 2021Multi-level Motion Attention for Human Motion Predictioncited by 35
  6. 2020Traffic Control Gesture Recognition for Autonomous Vehiclescited by 24
  7. 2021Self-Supervised 3D Human Pose Estimation with Multiple-View Geometrycited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 3; 2023: 19; 2024: 7; 2025: 8; 2026: 5.

42 papers.

Sort:

By area:

  1. 2023T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representationscited by 588
  2. 2022Back to MLP: A Simple Baseline for Human Motion Predictioncited by 100
  3. 2023HumanMAC: Masked Motion Completion for Human Motion Predictioncited by 81
  4. 2024Multi-agent Long-term 3D Human Pose Forecasting via Interaction-aware Trajectory Conditioningcited by 30
  5. 2022Human Joint Kinematics Diffusion-Refinement for Stochastic Motion Predictioncited by 28
  6. 2023Interactive Humanoid: Online Full-Body Motion Reaction Synthesis with Social Affordance Canonicalization and Forecastingcited by 27
  7. 2023CoMusion: Towards Consistent Stochastic Human Motion Prediction via Motion Diffusioncited by 21
  8. 2023Diverse 3D Hand Gesture Prediction from Body Dynamics by Bilateral Hand Disentanglementcited by 18
  9. 2023TransFusion: A Practical and Effective Transformer-based Diffusion Model for 3D Human Motion Predictioncited by 17
  10. 2024EgoCast: Forecasting Egocentric Human Pose in the Wildcited by 11
  11. 2023T2M-HiFiGPT: Generating High Quality Human Motion from Textual Descriptions with Residual Discrete Representationscited by 10
  12. 2024MotionRL: Align Text-to-Motion Generation to Human Preferences with Multi-Reward Reinforcement Learningcited by 10
30 more
  1. 2023Best Practices for 2-Body Pose Forecastingcited by 8
  2. 2023Weakly Supervised Multi-Modal 3D Human Body Pose Estimation for Autonomous Drivingcited by 8
  3. 2024Learning Generalizable Human Motion Generator with Reinforcement Learningcited by 7
  4. 2024Context-based Interpretable Spatio-Temporal Graph Convolutional Network for Human Motion Forecastingcited by 6
  5. 2022FutureHuman3D: Forecasting Complex Long-Term 3D Human Behavior from Video Observationscited by 5
  6. 2023DeFeeNet: Consecutive 3D Human Motion Prediction with Deviation Feedbackcited by 4
  7. 2023Towards Accurate Human Motion Prediction via Iterative Refinementcited by 4
  8. 2023A Unified Masked Autoencoder with Patchified Skeletons for Motion Synthesiscited by 4
  9. 2025CacheFlow: Fast Human Motion Prediction by Cached Normalizing Flowcited by 4
  10. 2025Efficient Multi-Person Motion Prediction by Lightweight Spatial and Temporal Interactionscited by 4
  11. 2023Physics-constrained Attack against Convolution-based Human Motion Predictioncited by 2
  12. 2023Graph-Guided MLP-Mixer for Skeleton-Based Human Motion Predictioncited by 1
  13. 2023Persistent-Transient Duality: A Multi-mechanism Approach for Modeling Human-Object Interactioncited by 1
  14. 2023Spatio-temporal MLP-graph network for 3D human pose estimationcited by 1
  15. 2023Recent Advances in Deterministic Human Motion Prediction: A Reviewcited by 1
  16. 2024Fooling Neural Networks for Motion Forecasting via Adversarial Attackscited by 1
  17. 2025Towards Efficient Large Scale Spatial-Temporal Time Series Forecasting via Improved Inverted Transformerscited by 1
  18. 2025Temporal Continual Learning with Prior Compensation for Human Motion Predictioncited by 1
  19. 2025MotionFlux: Efficient Text-Guided Motion Generation through Rectified Flow Matching and Preference Alignmentcited by 1
  20. 2026Ego-Human Motion Prediction with 3D-Aware LLMcited by 1
  21. 2023Data-Free Backbone Fine-Tuning for Pruned Neural Networkscited by 0
  22. 2023Pedestrian Environment Model for Automated Drivingcited by 0
  23. 2024Multi-Scale Incremental Modeling for Enhanced Human Motion Prediction in Human-Robot Collaborationcited by 0
  24. 2025Stochastic Human Motion Prediction with Memory of Action Transition and Action Characteristiccited by 0
  25. 2025LuKAN: A Kolmogorov-Arnold Network Framework for 3D Human Motion Predictioncited by 0
  26. 2025Scriboora: Rethinking Human Pose Forecastingcited by 0
  27. 2026A Self-Supervised Approach on Motion Calibration for Enhancing Physical Plausibility in Text-to-Motioncited by 0
  28. 2026Real-time body pose non-verbal communication with a consistency-based reliability measurecited by 0
  29. 2026Learning When to Listen: Gated Affect Fusion for Human Motion Predictioncited by 0
  30. 2026Multi-Person Human Motion Forecasting in Complex Scenescited by 0