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

• URL: http://arxiv.org/abs/2507.09446v1
• Date: Sun, 13 Jul 2025 02:16:37 GMT
• Title: Efficient Multi-Person Motion Prediction by Lightweight Spatial and Temporal Interactions
• Authors: Yuanhong Zheng, Ruixuan Yu, Jian Sun,
• Abstract summary: We propose a computationally efficient model for multi-person motion prediction by simplifying spatial and temporal interactions.<n>We achieve state-of-the-art performance for multiple metrics on standard datasets of CMU-Mocap, MuPoTS-3D, and 3DPW.
• Score: 45.51160285910023
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Relation Learning and Aggregate-attention for Multi-person Motion Prediction [13.052342503276936]
  Multi-person motion prediction considers not just the skeleton structures or human trajectories but also the interactions between others. Previous methods often overlook that the joints relations within an individual (intra-relation) and interactions among groups (inter-relation) are distinct types of representations. We introduce a new collaborative framework for multi-person motion prediction that explicitly modeling these relations.
  arXiv  Detail & Related papers  (2024-11-06T07:48:30Z)
• Sports-Traj: A Unified Trajectory Generation Model for Multi-Agent Movement in Sports [53.637837706712794]
  We propose a Unified Trajectory Generation model, UniTraj, that processes arbitrary trajectories as masked inputs.<n>Specifically, we introduce a Ghost Spatial Masking (GSM) module, embedded within a Transformer encoder, for spatial feature extraction.<n>We benchmark three practical sports datasets, Basketball-U, Football-U, and Soccer-U, for evaluation.
  arXiv  Detail & Related papers  (2024-05-27T22:15:23Z)
• Multi-agent Long-term 3D Human Pose Forecasting via Interaction-aware Trajectory Conditioning [41.09061877498741]
  We propose an interaction-aware trajectory-conditioned long-term multi-agent human pose forecasting model. Our model effectively handles the multi-modality of human motion and the complexity of long-term multi-agent interactions.
  arXiv  Detail & Related papers  (2024-04-08T06:15:13Z)
• A Decoupled Spatio-Temporal Framework for Skeleton-based Action Segmentation [89.86345494602642]
  Existing methods are limited in weak-temporal modeling capability. We propose a Decoupled Scoupled Framework (DeST) to address the issues. DeST significantly outperforms current state-of-the-art methods with less computational complexity.
  arXiv  Detail & Related papers  (2023-12-10T09:11:39Z)
• PGformer: Proxy-Bridged Game Transformer for Multi-Person Highly Interactive Extreme Motion Prediction [22.209454616479505]
  This paper focuses on collaborative motion prediction for multiple persons with extreme motions. A proxy unit is introduced to bridge the involved persons, which cooperates with our proposed XQA module. Our approach can also be compatible with the weakly interacted CMU-Mocap and MuPoTS-3D datasets.
  arXiv  Detail & Related papers  (2023-06-06T03:25:09Z)
• Ret3D: Rethinking Object Relations for Efficient 3D Object Detection in Driving Scenes [82.4186966781934]
  We introduce a simple, efficient, and effective two-stage detector, termed as Ret3D. At the core of Ret3D is the utilization of novel intra-frame and inter-frame relation modules. With negligible extra overhead, Ret3D achieves the state-of-the-art performance.
  arXiv  Detail & Related papers  (2022-08-18T03:48:58Z)
• Interaction Transformer for Human Reaction Generation [61.22481606720487]
  We propose a novel interaction Transformer (InterFormer) consisting of a Transformer network with both temporal and spatial attentions. Our method is general and can be used to generate more complex and long-term interactions.
  arXiv  Detail & Related papers  (2022-07-04T19:30:41Z)
• Dynamic and Static Context-aware LSTM for Multi-agent Motion Prediction [40.20696709103593]
  This paper designs a new mechanism, textiti.e., Dynamic and Static Context-aware Motion Predictor (DSCMP) It integrates rich information into the long-short-term-memory (LSTM) It models the dynamic interactions between agents by learning both their spatial positions and temporal coherence. It captures the context of scene by inferring latent variable, which enables multimodal predictions with meaningful semantic scene layout.
  arXiv  Detail & Related papers  (2020-08-03T11:03:57Z)
• A Spatial-Temporal Attentive Network with Spatial Continuity for Trajectory Prediction [74.00750936752418]
  We propose a novel model named spatial-temporal attentive network with spatial continuity (STAN-SC) First, spatial-temporal attention mechanism is presented to explore the most useful and important information. Second, we conduct a joint feature sequence based on the sequence and instant state information to make the generative trajectories keep spatial continuity.
  arXiv  Detail & Related papers  (2020-03-13T04:35:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.