Papers › Graph-Guided MLP-Mixer for Skeleton-Based Human Motion Prediction

Graph-Guided MLP-Mixer for Skeleton-Based Human Motion Prediction

7 Apr 2023arXiv:2304.03532archive 2025-07-28

Xinshun Wang, Qiongjie Cui, Chen Chen, Shen Zhao, Mengyuan Liu

In recent years, Graph Convolutional Networks (GCNs) have been widely used in human motion prediction, but their performance remains unsatisfactory. Recently, MLP-Mixer, initially developed for vision tasks, has been leveraged into human motion prediction as a promising alternative to GCNs, which achieves both better performance and better efficiency than GCNs. Unlike GCNs, which can explicitly capture human skeleton's bone-joint structure by representing it as a graph with edges and nodes, MLP-Mixer relies on fully connected layers and thus cannot explicitly model such graph-like structure of human's. To break this limitation of MLP-Mixer's, we propose \textit{Graph-Guided Mixer}, a novel approach that equips the original MLP-Mixer architecture with the capability to model graph structure. By incorporating graph guidance, our \textit{Graph-Guided Mixer} can effectively capture and utilize the specific connectivity patterns within human skeleton's graph representation. In this paper, first we uncover a theoretical connection between MLP-Mixer and GCN that is unexplored in existing research. Building on this theoretical connection, next we present our proposed \textit{Graph-Guided Mixer}, explaining how the original MLP-Mixer architecture is reinvented to incorporate guidance from graph structure. Then we conduct an extensive evaluation on the Human3.6M, AMASS, and 3DPW datasets, which shows that our method achieves state-of-the-art performance.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Human Pose ForecastingHuman motion predictionmotion prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Human Pose Forecasting Human3.6M GraphMixer Average MPJPE (mm) @ 1000 ms 108.6 #8 of 33 Archive leaderboard report
Human Pose Forecasting Human3.6M GraphMixer Average MPJPE (mm) @ 400ms 56.7 #8 of 33 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Average PoolingDense ConnectionsDropoutGCNGlobal Average PoolingLayer NormalizationMLP-MixerMixer LayerResidual Connection

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections