Pith. sign in

REVIEW 4 cited by

MotionMixer: MLP-based 3D Human Body Pose Forecasting

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2207.00499 v1 pith:5LHJR7UH submitted 2022-07-01 cs.CV cs.LG

Arij Bouazizi , Adrian Holzbock , Ulrich Kressel , Klaus Dietmayer , Vasileios Belagiannis This is my paper · ORCID
classification cs.CVcs.LG
keywords bodymotionmixerposedependenciesforecastinghumanjointsmodel
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

In this work, we present MotionMixer, an efficient 3D human body pose forecasting model based solely on multi-layer perceptrons (MLPs). MotionMixer learns the spatial-temporal 3D body pose dependencies by sequentially mixing both modalities. Given a stacked sequence of 3D body poses, a spatial-MLP extracts fine grained spatial dependencies of the body joints. The interaction of the body joints over time is then modelled by a temporal MLP. The spatial-temporal mixed features are finally aggregated and decoded to obtain the future motion. To calibrate the influence of each time step in the pose sequence, we make use of squeeze-and-excitation (SE) blocks. We evaluate our approach on Human3.6M, AMASS, and 3DPW datasets using the standard evaluation protocols. For all evaluations, we demonstrate state-of-the-art performance, while having a model with a smaller number of parameters. Our code is available at: https://github.com/MotionMLP/MotionMixer

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Ego-Human Motion Prediction with 3D-Aware LLM

    cs.CV 2026-07 conditional novelty 6.0 of 10

    Ego3DLM jointly predicts past and future 3D body pose and motion descriptions in a single autoregressive pass, conditioned on egocentric video, 3D scene features, and three-point tracking, achieving state-of-the-art o...

  2. Efficient Multi-Person Motion Prediction by Lightweight Spatial and Temporal Interactions

    cs.CV 2025-07 conditional novelty 5.0 of 10

    A lightweight MLP-based architecture with cross-level interaction and hip-distance embedding reports state-of-the-art multi-person motion prediction errors with 1-10 percent of transformer baseline parameters.

  3. Temporal Continual Learning with Prior Compensation for Human Motion Prediction

    cs.CV 2025-07 conditional novelty 5.0 of 10

    A multi-stage temporal continual learning method with a learned prior compensation factor improves human motion prediction across several backbones and four datasets.

  4. Multi-Scale Incremental Modeling for Enhanced Human Motion Prediction in Human-Robot Collaboration

    cs.RO 2024-12 reject novelty 5.0 of 10

    A multi-scale incremental model for human motion prediction is claimed to outperform prior state-of-the-art, but its reported gains are selective and its evaluation protocol is questionable.

Pith tools