mlsanityData to 7 Oct 2026

History Repeats Itself: Human Motion Prediction via Motion Attention

arXiv 2007.11755 ↗First posted 23 Jul 2020cs.CV cs.LG eess.IVcited by 164

Not on the map. Why?

Abstract (arXiv)

Human motion prediction aims to forecast future human poses given a past motion. Whether based on recurrent or feed-forward neural networks, existing methods fail to model the observation that human motion tends to repeat itself, even for complex sports actions and cooking activities. Here, we introduce an attention-based feed-forward network that explicitly leverages this observation. In particular, instead of modeling frame-wise attention via pose similarity, we propose to extract motion attention to capture the similarity between the current motion context and the historical motion sub-sequences. Aggregating the relevant past motions and processing the result with a graph convolutional network allows us to effectively exploit motion patterns from the long-term history to predict the future poses. Our experiments on Human3.6M, AMASS and 3DPW evidence the benefits of our approach for both periodical and non-periodical actions. Thanks to our attention model, it yields state-of-the-art results on all three datasets. Our code is available at https://github.com/wei-mao-2019/HisRepItself.

Key facts. Cited by 164 papers in the map (data through 7 Oct 2026). First posted on arXiv 23 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 27; 2022: 30; 2023: 51; 2024: 27; 2025: 18; 2026: 11.

164 papers.

Sort:

By area:

  1. 2023T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representationscited by 577
  2. 2023Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Datasetcited by 220
  3. 2021GOAL: Generating 4D Whole-Body Motion for Hand-Object Graspingcited by 142
  4. 2023CG-HOI: Contact-Guided 3D Human-Object Interaction Generationcited by 137
  5. 2023Leapfrog Diffusion Model for Stochastic Trajectory Predictioncited by 129
  6. 2022Back to MLP: A Simple Baseline for Human Motion Predictioncited by 99
  7. 2023EqMotion: Equivariant Multi-agent Motion Prediction with Invariant Interaction Reasoningcited by 97
  8. 2023PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimationcited by 91
  9. 2021Space-Time-Separable Graph Convolutional Network for Pose Forecastingcited by 84
  10. 2022BeLFusion: Latent Diffusion for Behavior-Driven Human Motion Predictioncited by 82
  11. 2022GIMO: Gaze-Informed Human Motion Prediction in Contextcited by 81
  12. 2021Multi-Person Extreme Motion Predictioncited by 74
38 more
  1. 2021Generating Smooth Pose Sequences for Diverse Human Motion Predictioncited by 66
  2. 2022Progressively Generating Better Initial Guesses Towards Next Stages for High-Quality Human Motion Predictioncited by 66
  3. 2022NeMF: Neural Motion Fields for Kinematic Animationcited by 66
  4. 2024Large Motion Model for Unified Multi-Modal Motion Generationcited by 65
  5. 2021Multi-Person 3D Motion Prediction with Multi-Range Transformerscited by 63
  6. 2021The Wanderings of Odysseus in 3D Scenescited by 59
  7. 2021TRiPOD: Human Trajectory and Pose Dynamics Forecasting in the Wildcited by 52
  8. 2024ParCo: Part-Coordinating Text-to-Motion Synthesiscited by 51
  9. 2022Spatio-Temporal Gating-Adjacency GCN for Human Motion Predictioncited by 48
  10. 2021Pose Transformers (POTR): Human Motion Prediction with Non-Autoregressive Transformerscited by 46
  11. 2021View Vertically: A Hierarchical Network for Trajectory Prediction via Fourier Spectrumscited by 44
  12. 2023Hierarchical Generation of Human-Object Interactions with Diffusion Probabilistic Modelscited by 43
  13. 2022MotionMixer: MLP-based 3D Human Body Pose Forecastingcited by 42
  14. 2023Task-Oriented Human-Object Interactions Generation with Implicit Neural Representationscited by 41
  15. 2021RAIN: Reinforced Hybrid Attention Inference Network for Motion Forecastingcited by 36
  16. 2021Multiscale Spatio-Temporal Graph Neural Networks for 3D Skeleton-Based Motion Predictioncited by 36
  17. 2021Multi-level Motion Attention for Human Motion Predictioncited by 35
  18. 2023Diverse Human Motion Prediction Guided by Multi-Level Spatial-Temporal Anchorscited by 34
  19. 2022A generic diffusion-based approach for 3D human pose prediction in the wildcited by 33
  20. 2022Diverse Human Motion Prediction via Gumbel-Softmax Sampling from an Auxiliary Spacecited by 32
  21. 20223D Human Motion Prediction: A Surveycited by 30
  22. 2022Motron: Multimodal Probabilistic Human Motion Forecastingcited by 30
  23. 2022Skeleton-Parted Graph Scattering Networks for 3D Human Motion Predictioncited by 29
  24. 2022Human Joint Kinematics Diffusion-Refinement for Stochastic Motion Predictioncited by 28
  25. 2022Contact-aware Human Motion Forecastingcited by 27
  26. 2024Towards Open Domain Text-Driven Synthesis of Multi-Person Motionscited by 27
  27. 2022Weakly-supervised Action Transition Learning for Stochastic Human Motion Predictioncited by 26
  28. 2023Skeleton-in-Context: Unified Skeleton Sequence Modeling with In-Context Learningcited by 26
  29. 2023Trajectory-Aware Body Interaction Transformer for Multi-Person Pose Forecastingcited by 25
  30. 2023AI-Generated Content (AIGC) for Various Data Modalities: A Surveycited by 25
  31. 2022Pose Forecasting in Industrial Human-Robot Collaborationcited by 24
  32. 2022SoMoFormer: Multi-Person Pose Forecasting with Transformerscited by 23
  33. 2024M2D2M: Multi-Motion Generation from Text with Discrete Diffusion Modelscited by 23
  34. 2021Pose2Room: Understanding 3D Scenes from Human Activitiescited by 22
  35. 2023Robots That Can See: Leveraging Human Pose for Trajectory Predictioncited by 22
  36. 20223D Vision with Transformers: A Surveycited by 21
  37. 2023CoMusion: Towards Consistent Stochastic Human Motion Prediction via Motion Diffusioncited by 21
  38. 2024Multi-Transmotion: Pre-trained Model for Human Motion Predictioncited by 21

50 most cited of 164 All 164 (JSON)