# Efficient Multi-Person Motion Prediction by Lightweight Spatial and Temporal Interactions

arXiv: https://arxiv.org/abs/2507.09446 · HTML: https://mlsanity.com/paper/2507.09446/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 51 references that are in the map.
- First posted on arXiv 13 Jul 2025.

## Builds on (most cited first, 27 of 27)

- [Generating Long Sequences with Sparse Transformers](https://mlsanity.com/paper/1904.10509/) (2019)
- [MLP-Mixer: An all-MLP Architecture for Vision](https://mlsanity.com/paper/2105.01601/) (2021)
- [AMASS: Archive of Motion Capture as Surface Shapes](https://mlsanity.com/paper/1904.03278/) (2019)
- [MetaFormer Is Actually What You Need for Vision](https://mlsanity.com/paper/2111.11418/) (2021)
- [Learning Trajectory Dependencies for Human Motion Prediction](https://mlsanity.com/paper/1908.05436/) (2019)
- [Single-Shot Multi-Person 3D Pose Estimation From Monocular RGB](https://mlsanity.com/paper/1712.03453/) (2017)
- [History Repeats Itself: Human Motion Prediction via Motion Attention](https://mlsanity.com/paper/2007.11755/) (2020)
- [CycleMLP: A MLP-like Architecture for Dense Prediction](https://mlsanity.com/paper/2107.10224/) (2021)
- [MSR-GCN: Multi-Scale Residual Graph Convolution Networks for Human Motion Prediction](https://mlsanity.com/paper/2108.07152/) (2021)
- [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)
- [Progressively Generating Better Initial Guesses Towards Next Stages for High-Quality Human Motion Prediction](https://mlsanity.com/paper/2203.16051/) (2022)
- [Multi-Person 3D Motion Prediction with Multi-Range Transformers](https://mlsanity.com/paper/2111.12073/) (2021)
- [Action-Agnostic Human Pose Forecasting](https://mlsanity.com/paper/1810.09676/) (2018)
- [TRiPOD: Human Trajectory and Pose Dynamics Forecasting in the Wild](https://mlsanity.com/paper/2104.04029/) (2021)
- [Socially and Contextually Aware Human Motion and Pose Forecasting](https://mlsanity.com/paper/2007.06843/) (2020)
- [MotionMixer: MLP-based 3D Human Body Pose Forecasting](https://mlsanity.com/paper/2207.00499/) (2022)
- [Multi-agent Long-term 3D Human Pose Forecasting via Interaction-aware Trajectory Conditioning](https://mlsanity.com/paper/2404.05218/) (2024)
- [Trajectory-Aware Body Interaction Transformer for Multi-Person Pose Forecasting](https://mlsanity.com/paper/2303.05095/) (2023)
- [SoMoFormer: Multi-Person Pose Forecasting with Transformers](https://mlsanity.com/paper/2208.14023/) (2022)
- [GraphMLP: A Graph MLP-Like Architecture for 3D Human Pose Estimation](https://mlsanity.com/paper/2206.06420/) (2022)
- [MART: MultiscAle Relational Transformer Networks for Multi-agent Trajectory Prediction](https://mlsanity.com/paper/2407.21635/) (2024)
- [PVRED: A Position-Velocity Recurrent Encoder-Decoder for Human Motion Prediction](https://mlsanity.com/paper/1906.06514/) (2019)
- [LatentFormer: Multi-Agent Transformer-Based Interaction Modeling and Trajectory Prediction](https://mlsanity.com/paper/2203.01880/) (2022)
- [TransKD: Transformer Knowledge Distillation for Efficient Semantic Segmentation](https://mlsanity.com/paper/2202.13393/) (2022)
- [Joint-Relation Transformer for Multi-Person Motion Prediction](https://mlsanity.com/paper/2308.04808/) (2023)
- [Layer-wise Pruning of Transformer Attention Heads for Efficient Language Modeling](https://mlsanity.com/paper/2110.03252/) (2021)

## Built on by (most cited first, 4 of 4)

- [Scriboora: Rethinking Human Pose Forecasting](https://mlsanity.com/paper/2511.15565/) (2025)
- [SimpliHuMoN: Simplifying Human Motion Prediction](https://mlsanity.com/paper/2603.04399/) (2026)
- [Residual Flow Matching with Dynamic Cross-Interaction for 3D Multi-Person Motion Prediction](https://mlsanity.com/paper/2608.03379/) (2026)
- [Multi-Person Human Motion Forecasting in Complex Scenes](https://mlsanity.com/paper/2608.27039/) (2026)

## Abstract (arXiv)

3D multi-person motion prediction is a highly complex task, primarily due to the dependencies on both individual past movements and the interactions between agents. Moreover, effectively modeling these interactions often incurs substantial computational costs. In this work, we propose a computationally efficient model for multi-person motion prediction by simplifying spatial and temporal interactions. Our approach begins with the design of lightweight dual branches that learn local and global representations for individual and multiple persons separately. Additionally, we introduce a novel cross-level interaction block to integrate the spatial and temporal representations from both branches. To further enhance interaction modeling, we explicitly incorporate the spatial inter-person distance embedding. With above efficient temporal and spatial design, we achieve state-of-the-art performance for multiple metrics on standard datasets of CMU-Mocap, MuPoTS-3D, and 3DPW, while significantly reducing the computational cost. Code is available at https://github.com/Yuanhong-Zheng/EMPMP.