Papers › Multi-Graph Convolution Network for Pose Forecasting

Multi-Graph Convolution Network for Pose Forecasting

11 Apr 2023arXiv:2304.04956archive 2025-07-28

Hongwei Ren, Yuhong Shi, Kewei Liang

Recently, there has been a growing interest in predicting human motion, which involves forecasting future body poses based on observed pose sequences. This task is complex due to modeling spatial and temporal relationships. The most commonly used models for this task are autoregressive models, such as recurrent neural networks (RNNs) or variants, and Transformer Networks. However, RNNs have several drawbacks, such as vanishing or exploding gradients. Other researchers have attempted to solve the communication problem in the spatial dimension by integrating Graph Convolutional Networks (GCN) and Long Short-Term Memory (LSTM) models. These works deal with temporal and spatial information separately, which limits the effectiveness. To fix this problem, we propose a novel approach called the multi-graph convolution network (MGCN) for 3D human pose forecasting. This model simultaneously captures spatial and temporal information by introducing an augmented graph for pose sequences. Multiple frames give multiple parts, joined together in a single graph instance. Furthermore, we also explore the influence of natural structure and sequence-aware attention to our model. In our experimental evaluation of the large-scale benchmark datasets, Human3.6M, AMSS and 3DPW, MGCN outperforms the state-of-the-art in pose prediction.

Paper PDF

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 Forecasting Pose Prediction

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Human Pose Forecasting	Human3.6M	MGCN	Average MPJPE (mm) @ 1000 ms	72.9	#2 of 33	Archive leaderboard	report
Human Pose Forecasting	Human3.6M	MGCN	Average MPJPE (mm) @ 400ms	34.4	#2 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

Absolute Position Encodings Adam Attention BPE Convolution Dense Connections Dropout Label Smoothing Layer Normalization Linear Layer Multi-Head Attention Position-Wise Feed-Forward Layer Residual Connection Softmax Transformer

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