Papers › Pose Transformers (POTR): Human Motion Prediction with Non-Autoregressive Transformers

Pose Transformers (POTR): Human Motion Prediction with Non-Autoregressive Transformers

15 Sep 2021arXiv:2109.07531archive 2025-07-28

Angel Martínez-González, Michael Villamizar, Jean-Marc Odobez

We propose to leverage Transformer architectures for non-autoregressive human motion prediction. Our approach decodes elements in parallel from a query sequence, instead of conditioning on previous predictions such as instate-of-the-art RNN-based approaches. In such a way our approach is less computational intensive and potentially avoids error accumulation to long term elements in the sequence. In that context, our contributions are fourfold: (i) we frame human motion prediction as a sequence-to-sequence problem and propose a non-autoregressive Transformer to infer the sequences of poses in parallel; (ii) we propose to decode sequences of 3D poses from a query sequence generated in advance with elements from the input sequence;(iii) we propose to perform skeleton-based activity classification from the encoder memory, in the hope that identifying the activity can improve predictions;(iv) we show that despite its simplicity, our approach achieves competitive results in two public datasets, although surprisingly more for short term predictions rather than for long term ones.

Paper PDF Code

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

Code

idiap/potr officialmentioned in paperpytorchGPL-3.0 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

Classification Human motion prediction motion prediction

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Classification	Full-body Parkinson’s disease dataset	Pose Transformers (POTR)	F1-score (weighted)	0.46	#4 of 7	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