# History Repeats Itself: Human Motion Prediction via Motion Attention

arXiv: https://arxiv.org/abs/2007.11755 · HTML: https://mlsanity.com/paper/2007.11755/

## Key facts

- Cited by 165 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Jul 2020.

## Built on by (most cited first, 30 of 165)

- [T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations](https://mlsanity.com/paper/2301.06052/) (2023)
- [Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset](https://mlsanity.com/paper/2307.00818/) (2023)
- [GOAL: Generating 4D Whole-Body Motion for Hand-Object Grasping](https://mlsanity.com/paper/2112.11454/) (2021)
- [CG-HOI: Contact-Guided 3D Human-Object Interaction Generation](https://mlsanity.com/paper/2311.16097/) (2023)
- [Leapfrog Diffusion Model for Stochastic Trajectory Prediction](https://mlsanity.com/paper/2303.10895/) (2023)
- [Back to MLP: A Simple Baseline for Human Motion Prediction](https://mlsanity.com/paper/2207.01567/) (2022)
- [EqMotion: Equivariant Multi-agent Motion Prediction with Invariant Interaction Reasoning](https://mlsanity.com/paper/2303.10876/) (2023)
- [PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimation](https://mlsanity.com/paper/2303.17472/) (2023)
- [Space-Time-Separable Graph Convolutional Network for Pose Forecasting](https://mlsanity.com/paper/2110.04573/) (2021)
- [BeLFusion: Latent Diffusion for Behavior-Driven Human Motion Prediction](https://mlsanity.com/paper/2211.14304/) (2022)
- [GIMO: Gaze-Informed Human Motion Prediction in Context](https://mlsanity.com/paper/2204.09443/) (2022)
- [Multi-Person Extreme Motion Prediction](https://mlsanity.com/paper/2105.08825/) (2021)
- [NeMF: Neural Motion Fields for Kinematic Animation](https://mlsanity.com/paper/2206.03287/) (2022)
- [Generating Smooth Pose Sequences for Diverse Human Motion Prediction](https://mlsanity.com/paper/2108.08422/) (2021)
- [Progressively Generating Better Initial Guesses Towards Next Stages for High-Quality Human Motion Prediction](https://mlsanity.com/paper/2203.16051/) (2022)
- [Large Motion Model for Unified Multi-Modal Motion Generation](https://mlsanity.com/paper/2404.01284/) (2024)
- [Multi-Person 3D Motion Prediction with Multi-Range Transformers](https://mlsanity.com/paper/2111.12073/) (2021)
- [The Wanderings of Odysseus in 3D Scenes](https://mlsanity.com/paper/2112.09251/) (2021)
- [ParCo: Part-Coordinating Text-to-Motion Synthesis](https://mlsanity.com/paper/2403.18512/) (2024)
- [TRiPOD: Human Trajectory and Pose Dynamics Forecasting in the Wild](https://mlsanity.com/paper/2104.04029/) (2021)
- [Spatio-Temporal Gating-Adjacency GCN for Human Motion Prediction](https://mlsanity.com/paper/2203.01474/) (2022)
- [Pose Transformers (POTR): Human Motion Prediction with Non-Autoregressive Transformers](https://mlsanity.com/paper/2109.07531/) (2021)
- [View Vertically: A Hierarchical Network for Trajectory Prediction via Fourier Spectrums](https://mlsanity.com/paper/2110.07288/) (2021)
- [Hierarchical Generation of Human-Object Interactions with Diffusion Probabilistic Models](https://mlsanity.com/paper/2310.02242/) (2023)
- [MotionMixer: MLP-based 3D Human Body Pose Forecasting](https://mlsanity.com/paper/2207.00499/) (2022)
- [Task-Oriented Human-Object Interactions Generation with Implicit Neural Representations](https://mlsanity.com/paper/2303.13129/) (2023)
- [Multiscale Spatio-Temporal Graph Neural Networks for 3D Skeleton-Based Motion Prediction](https://mlsanity.com/paper/2108.11244/) (2021)
- [RAIN: Reinforced Hybrid Attention Inference Network for Motion Forecasting](https://mlsanity.com/paper/2108.01316/) (2021)
- [Multi-level Motion Attention for Human Motion Prediction](https://mlsanity.com/paper/2106.09300/) (2021)
- [Diverse Human Motion Prediction Guided by Multi-Level Spatial-Temporal Anchors](https://mlsanity.com/paper/2302.04860/) (2023)

## 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.