mlsanityData to 14 Oct 2026

Capturing Uncertainty in Human Motion for Representation Learning in Soccer

arXiv 2608.11203 ↗First posted 11 Aug 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

This paper presents a self-supervised representation learning framework for understanding 3D skeleton-based human motion in soccer, using future motion prediction as the learning objective. Since human motion is inherently uncertain, accounting for multiple plausible futures is essential for capturing the underlying motion dynamics and learning effective representations. To this end, we introduce a conditioning module for motion prediction that models a probabilistic distribution over discretized future motions in 3D Euclidean space, learning multimodality with explicit supervision from future trajectories. Experiments on large-scale soccer player tracking data show that our approach substantially improves motion prediction accuracy. Moreover, the learned representations effectively transfer to multiple soccer downstream applications, demonstrating strong cross-task generalization.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 65 of its 81 references that are in the map. First posted on arXiv 11 Aug 2026.

Builds on

65 of 81 references.

References · 65

  1. 2017Neural Discrete Representation Learningcited by 4,712
  2. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
  3. 2020GLU Variants Improve Transformercited by 1,804
  4. 2019Root Mean Square Layer Normalizationcited by 1,480
  5. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,236
  6. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,209
  7. 2021How Attentive are Graph Attention Networks?cited by 835
  8. 2016NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysiscited by 686
  9. 2023T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representationscited by 588
  10. 2019NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understandingcited by 533
  11. 2023MotionGPT: Human Motion as a Foreign Languagecited by 527
  12. 2023MoMask: Generative Masked Modeling of 3D Human Motionscited by 400
38 more
  1. 2022TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Textscited by 359
  2. 2017On human motion prediction using recurrent neural networkscited by 338
  3. 2021Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognitioncited by 322
  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. 2020DLow: Diversifying Latent Flows for Diverse Human Motion Predictioncited by 185
  8. 2017HP-GAN: Probabilistic 3D human motion prediction via GANcited by 176
  9. 2020History Repeats Itself: Human Motion Prediction via Motion Attentioncited by 165
  10. 2018SoccerNet: A Scalable Dataset for Action Spotting in Soccer Videoscited by 150
  11. 2014Cross-view Action Modeling, Learning and Recognitioncited by 134
  12. 2020Dynamic Multiscale Graph Neural Networks for 3D Skeleton-Based Human Motion Predictioncited by 132
  13. 2023AttT2M: Text-Driven Human Motion Generation with Multi-Perspective Attention Mechanismcited by 117
  14. 2018Convolutional Sequence to Sequence Model for Human Dynamicscited by 115
  15. 2021MSR-GCN: Multi-Scale Residual Graph Convolution Networks for Human Motion Predictioncited by 100
  16. 2022Back to MLP: A Simple Baseline for Human Motion Predictioncited by 100
  17. 2017Deep representation learning for human motion prediction and classificationcited by 98
  18. 2023EqMotion: Equivariant Multi-agent Motion Prediction with Invariant Interaction Reasoningcited by 97
  19. 2021Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Recognitioncited by 90
  20. 2018A Neural Temporal Model for Human Motion Predictioncited by 87
  21. 2018MT-VAE: Learning Motion Transformations to Generate Multimodal Human Dynamicscited by 86
  22. 2022Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 85
  23. 2021Space-Time-Separable Graph Convolutional Network for Pose Forecastingcited by 84
  24. 2022BeLFusion: Latent Diffusion for Behavior-Driven Human Motion Predictioncited by 82
  25. 2023HumanMAC: Masked Motion Completion for Human Motion Predictioncited by 81
  26. 2019Diverse Trajectory Forecasting with Determinantal Point Processescited by 80
  27. 2023Priority-Centric Human Motion Generation in Discrete Latent Spacecited by 67
  28. 2022Progressively Generating Better Initial Guesses Towards Next Stages for High-Quality Human Motion Predictioncited by 66
  29. 2018Action-Agnostic Human Pose Forecastingcited by 56
  30. 2018BiHMP-GAN: Bidirectional 3D Human Motion Prediction GANcited by 55
  31. 2019Symbiotic Graph Neural Networks for 3D Skeleton-based Human Action Recognition and Motion Predictioncited by 50
  32. 2024The Language of Motion: Unifying Verbal and Non-verbal Language of 3D Human Motioncited by 46
  33. 2023HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representationscited by 44
  34. 2023Masked Motion Predictors are Strong 3D Action Representation Learnerscited by 41
  35. 2022CMD: Self-supervised 3D Action Representation Learning with Cross-modal Mutual Distillationcited by 38
  36. 2023Diverse Human Motion Prediction Guided by Multi-Level Spatial-Temporal Anchorscited by 34
  37. 2022Global-local Motion Transformer for Unsupervised Skeleton-based Action Learningcited by 33
  38. 2022A generic diffusion-based approach for 3D human pose prediction in the wildcited by 33

50 most cited of 65 All 65 (JSON)

Built on by

Not cited yet.