Papers › PGformer: Proxy-Bridged Game Transformer for Multi-Person Highly Interactive Extreme...

PGformer: Proxy-Bridged Game Transformer for Multi-Person Highly Interactive Extreme Motion Prediction

6 Jun 2023arXiv:2306.03374archive 2025-07-28

Yanwen Fang, Jintai Chen, Peng-Tao Jiang, Chao Li, Yifeng Geng, Eddy K. F. LAM, Guodong Li

Multi-person motion prediction is a challenging task, especially for real-world scenarios of highly interacted persons. Most previous works have been devoted to studying the case of weak interactions (e.g., walking together), in which typically forecasting each human pose in isolation can still achieve good performances. This paper focuses on collaborative motion prediction for multiple persons with extreme motions and attempts to explore the relationships between the highly interactive persons' pose trajectories. Specifically, a novel cross-query attention (XQA) module is proposed to bilaterally learn the cross-dependencies between the two pose sequences tailored for this situation. A proxy unit is additionally introduced to bridge the involved persons, which cooperates with our proposed XQA module and subtly controls the bidirectional spatial information flows. These designs are then integrated into a Transformer-based architecture and the resulting model is called Proxy-bridged Game Transformer (PGformer) for multi-person interactive motion prediction. Its effectiveness has been evaluated on the challenging ExPI dataset, which involves highly interactive actions. Our PGformer consistently outperforms the state-of-the-art methods in both short- and long-term predictions by a large margin. Besides, our approach can also be compatible with the weakly interacted CMU-Mocap and MuPoTS-3D datasets and extended to the case of more than 2 individuals with encouraging results.

Paper PDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

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

Multi-Person Pose forecasting motion prediction

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Multi-Person Pose forecasting	Expi - common actions split	PGformer	Average MPJPE (mm) @ 1000 ms	231	#2 of 6	Archive leaderboard	report
Multi-Person Pose forecasting	Expi - common actions split	PGformer	Average MPJPE (mm) @ 200 ms	53	#2 of 6	Archive leaderboard	report
Multi-Person Pose forecasting	Expi - common actions split	PGformer	Average MPJPE (mm) @ 400 ms	108	#2 of 6	Archive leaderboard	report
Multi-Person Pose forecasting	Expi - common actions split	PGformer	Average MPJPE (mm) @ 600 ms	156	#2 of 6	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 Dense Connections Dropout Focus 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