mlsanityData to 14 Oct 2026

Human Motion Prediction Using Manifold-Aware Wasserstein GAN

arXiv 2105.08715 ↗First posted 18 May 2021cs.CV cs.AIcited by 8

Not on the map. Why?

Abstract (arXiv)

Human motion prediction aims to forecast future human poses given a prior pose sequence. The discontinuity of the predicted motion and the performance deterioration in long-term horizons are still the main challenges encountered in current literature. In this work, we tackle these issues by using a compact manifold-valued representation of human motion. Specifically, we model the temporal evolution of the 3D human poses as trajectory, what allows us to map human motions to single points on a sphere manifold. To learn these non-Euclidean representations, we build a manifold-aware Wasserstein generative adversarial model that captures the temporal and spatial dependencies of human motion through different losses. Extensive experiments show that our approach outperforms the state-of-the-art on CMU MoCap and Human 3.6M datasets. Our qualitative results show the smoothness of the predicted motions.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 12 of its 27 references that are in the map. First posted on arXiv 18 May 2021.

Builds on

12 of 27 references.

References · 12

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2017Improved Training of Wasserstein GANscited by 2,235
  3. 2017On human motion prediction using recurrent neural networkscited by 338
  4. 2016A Survey of Motion Planning and Control Techniques for Self-driving Urban Vehiclescited by 254
  5. 2019Learning Trajectory Dependencies for Human Motion Predictioncited by 246
  6. 2015Structural-RNN: Deep Learning on Spatio-Temporal Graphscited by 234
  7. 2017HP-GAN: Probabilistic 3D human motion prediction via GANcited by 176
  8. 2018Convolutional Sequence to Sequence Model for Human Dynamicscited by 115
  9. 2017Deep representation learning for human motion prediction and classificationcited by 98
  10. 2017Learning Human Motion Models for Long-term Predictionscited by 67
  11. 2018A Novel Geometric Framework on Gram Matrix Trajectories for Human Behavior Understandingcited by 21
  12. 2019Dynamic Facial Expression Generation on Hilbert Hypersphere with Conditional Wasserstein Generative Adversarial Netscited by 19

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 1; 2024: 4; 2025: 2.

8 papers.

  1. 2024Multi-Track Timeline Control for Text-Driven 3D Human Motion Generationcited by 91
  2. 2025GENMO: A GENeralist Model for Human MOtioncited by 49
  3. 2024Generation of Complex 3D Human Motion by Temporal and Spatial Composition of Diffusion Modelscited by 7
  4. 20223D Skeleton-based Human Motion Prediction with Manifold-Aware GANcited by 3
  5. 2024Motion Generation Review: Exploring Deep Learning for Lifelike Animation with Manifoldcited by 1
  6. 2025No MoCap Needed: Post-Training Motion Diffusion Models with Reinforcement Learning using Only Textual Promptscited by 1
  7. 2023Personalized Pose Forecastingcited by 0
  8. 2024AdvMT: Adversarial Motion Transformer for Long-term Human Motion Predictioncited by 0