mlsanityData to 7 Oct 2026

Dyadic Human Motion Prediction

arXiv 2112.00396 ↗First posted 1 Dec 2021cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

Prior work on human motion forecasting has mostly focused on predicting the future motion of single subjects in isolation from their past pose sequence. In the presence of closely interacting people, however, this strategy fails to account for the dependencies between the different subject's motions. In this paper, we therefore introduce a motion prediction framework that explicitly reasons about the interactions of two observed subjects. Specifically, we achieve this by introducing a pairwise attention mechanism that models the mutual dependencies in the motion history of the two subjects. This allows us to preserve the long-term motion dynamics in a more realistic way and more robustly predict unusual and fast-paced movements, such as the ones occurring in a dance scenario. To evaluate this, and because no existing motion prediction datasets depict two closely-interacting subjects, we introduce the LindyHop600K dance dataset. Our results evidence that our approach outperforms the state-of-the-art single person motion prediction techniques.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 52 of its 72 references that are in the map. First posted on arXiv 1 Dec 2021.

Builds on

52 of 72 references.

References · 52

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  4. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  5. 2015Show, Attend and Tell: Neural Image Caption Generation with Visual Attentioncited by 1,421
  6. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,061
  7. 2018Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networkscited by 687
  8. 2017A simple neural network module for relational reasoningcited by 345
  9. 2017On human motion prediction using recurrent neural networkscited by 336
  10. 2017DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agentscited by 310
  11. 2018SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraintscited by 296
  12. 2019Learning Trajectory Dependencies for Human Motion Predictioncited by 245
38 more
  1. 2015Structural-RNN: Deep Learning on Spatio-Temporal Graphscited by 234
  2. 2019Social-BiGAT: Multimodal Trajectory Forecasting using Bicycle-GAN and Graph Attention Networkscited by 228
  3. 2018Convolutional Social Pooling for Vehicle Trajectory Predictioncited by 221
  4. 2021Multimodal Motion Prediction with Stacked Transformerscited by 207
  5. 2020Long-term Human Motion Prediction with Scene Contextcited by 191
  6. 2020DLow: Diversifying Latent Flows for Diverse Human Motion Predictioncited by 184
  7. 2017HP-GAN: Probabilistic 3D human motion prediction via GANcited by 176
  8. 2020History Repeats Itself: Human Motion Prediction via Motion Attentioncited by 164
  9. 2018Convolutional Sequence to Sequence Model for Human Dynamicscited by 115
  10. 2018Human Motion Prediction via Spatio-Temporal Inpaintingcited by 114
  11. 2019Spatially-Aware Graph Neural Networks for Relational Behavior Forecasting from Sensor Datacited by 104
  12. 2021MSR-GCN: Multi-Scale Residual Graph Convolution Networks for Human Motion Predictioncited by 100
  13. 2020Spatially Conditioned Graphs for Detecting Human-Object Interactionscited by 93
  14. 2018Actor-Centric Relation Networkcited by 87
  15. 2018A Neural Temporal Model for Human Motion Predictioncited by 87
  16. 2018MT-VAE: Learning Motion Transformations to Generate Multimodal Human Dynamicscited by 86
  17. 2019Context-aware Human Motion Predictioncited by 83
  18. 2019You2Me: Inferring Body Pose in Egocentric Video via First and Second Person Interactionscited by 82
  19. 2021Multi-Person Extreme Motion Predictioncited by 74
  20. 2021Scene-aware Generative Network for Human Motion Synthesiscited by 70
  21. 2017Learning Human Motion Models for Long-term Predictionscited by 67
  22. 2021Generating Smooth Pose Sequences for Diverse Human Motion Predictioncited by 66
  23. 2020Social NCE: Contrastive Learning of Socially-aware Motion Representationscited by 58
  24. 2018Action-Agnostic Human Pose Forecastingcited by 56
  25. 2018BiHMP-GAN: Bidirectional 3D Human Motion Prediction GANcited by 55
  26. 2020End-to-end Contextual Perception and Prediction with Interaction Transformercited by 54
  27. 2020Socially and Contextually Aware Human Motion and Pose Forecastingcited by 51
  28. 2019Symbiotic Graph Neural Networks for 3D Skeleton-based Human Action Recognition and Motion Predictioncited by 50
  29. 2019Spatiotemporal Co-attention Recurrent Neural Networks for Human-Skeleton Motion Predictioncited by 46
  30. 2021Pose Transformers (POTR): Human Motion Prediction with Non-Autoregressive Transformerscited by 46
  31. 2019Imitation Learning for Human Pose Predictioncited by 44
  32. 2020HMOR: Hierarchical Multi-Person Ordinal Relations for Monocular Multi-Person 3D Pose Estimationcited by 44
  33. 2018Long-Term Human Motion Prediction by Modeling Motion Context and Enhancing Motion Dynamiccited by 41
  34. 2021RAIN: Reinforced Hybrid Attention Inference Network for Motion Forecastingcited by 36
  35. 2021Multi-level Motion Attention for Human Motion Predictioncited by 35
  36. 2019Relational Action Forecastingcited by 27
  37. 2020PI-Net: Pose Interacting Network for Multi-Person Monocular 3D Pose Estimationcited by 15
  38. 2020Motion Prediction Using Temporal Inception Modulecited by 10

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 2; 2024: 2; 2025: 2.

9 papers.

  1. 2022Didn't see that coming: a survey on non-verbal social human behavior forecastingcited by 12
  2. 20223D Pose Based Feedback for Physical Exercisescited by 11
  3. 2022Comparison of Spatio-Temporal Models for Human Motion and Pose Forecasting in Face-to-Face Interaction Scenarioscited by 8
  4. 2024Reconstructing Close Human Interactions from Multiple Viewscited by 7
  5. 2023The MI-Motion Dataset and Benchmark for 3D Multi-Person Motion Predictioncited by 3
  6. 2023Personalized Pose Forecastingcited by 0
  7. 2024Towards a large-scale fused and labeled dataset of human pose while interacting with robots in shared urban areascited by 0
  8. 2025Dyads: Artist-Centric, AI-Generated Dance Duetscited by 0
  9. 2025Motion In-Betweening for Densely Interacting Characterscited by 0