Papers › Multi-Person 3D Motion Prediction with Multi-Range Transformers

Multi-Person 3D Motion Prediction with Multi-Range Transformers

23 Nov 2021NeurIPS 2021 12arXiv:2111.12073archive 2025-07-28

Jiashun Wang, Huazhe Xu, Medhini Narasimhan, Xiaolong Wang

We propose a novel framework for multi-person 3D motion trajectory prediction. Our key observation is that a human's action and behaviors may highly depend on the other persons around. Thus, instead of predicting each human pose trajectory in isolation, we introduce a Multi-Range Transformers model which contains of a local-range encoder for individual motion and a global-range encoder for social interactions. The Transformer decoder then performs prediction for each person by taking a corresponding pose as a query which attends to both local and global-range encoder features. Our model not only outperforms state-of-the-art methods on long-term 3D motion prediction, but also generates diverse social interactions. More interestingly, our model can even predict 15-person motion simultaneously by automatically dividing the persons into different interaction groups. Project page with code is available at https://jiashunwang.github.io/MRT/.

Paper PDF Conference PDF Code

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

Code

jiashunwang/MRT officialmentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

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

Tasks

Decoder Multi-Person Pose forecasting Prediction Trajectory Prediction 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	MRT	Average MPJPE (mm) @ 1000 ms	238	#4 of 6	Archive leaderboard	report
Multi-Person Pose forecasting	Expi - common actions split	MRT	Average MPJPE (mm) @ 200 ms	58	#4 of 6	Archive leaderboard	report
Multi-Person Pose forecasting	Expi - common actions split	MRT	Average MPJPE (mm) @ 400 ms	116	#4 of 6	Archive leaderboard	report
Multi-Person Pose forecasting	Expi - common actions split	MRT	Average MPJPE (mm) @ 600 ms	163	#4 of 6	Archive leaderboard	report
Multi-Person Pose forecasting	Expi - unseen actions split	MRT	Average MPJPE (mm) @ 400 ms	146	#4 of 5	Archive leaderboard	report
Multi-Person Pose forecasting	Expi - unseen actions split	MRT	Average MPJPE (mm) @ 600 ms	205	#4 of 5	Archive leaderboard	report
Multi-Person Pose forecasting	Expi - unseen actions split	MRT	Average MPJPE (mm) @ 800 ms	291	#4 of 5	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 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