mlsanityData to 14 Oct 2026

Multi-Person Extreme Motion Prediction

arXiv 2105.08825 ↗First posted 18 May 2021cs.CVcited by 75

Not on the map. Why?

Abstract (arXiv)

Human motion prediction aims to forecast future poses given a sequence of past 3D skeletons. While this problem has recently received increasing attention, it has mostly been tackled for single humans in isolation. In this paper, we explore this problem when dealing with humans performing collaborative tasks, we seek to predict the future motion of two interacted persons given two sequences of their past skeletons. We propose a novel cross interaction attention mechanism that exploits historical information of both persons, and learns to predict cross dependencies between the two pose sequences. Since no dataset to train such interactive situations is available, we collected ExPI (Extreme Pose Interaction), a new lab-based person interaction dataset of professional dancers performing Lindy-hop dancing actions, which contains 115 sequences with 30K frames annotated with 3D body poses and shapes. We thoroughly evaluate our cross interaction network on ExPI and show that both in short- and long-term predictions, it consistently outperforms state-of-the-art methods for single-person motion prediction.

Key facts. Cited by 75 papers in the map (data through 14 Oct 2026). Builds on 40 of its 83 references that are in the map. First posted on arXiv 18 May 2021.

Builds on

40 of 83 references.

References · 40

  1. 2017Attention Is All You Needcited by 60,361
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2017Graph Attention Networkscited by 8,923
  4. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,236
  5. 2016NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysiscited by 686
  6. 2019NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understandingcited by 533
  7. 2021Action-Conditioned 3D Human Motion Synthesis with Transformer VAEcited by 501
  8. 2017On human motion prediction using recurrent neural networkscited by 338
  9. 2019Resolving 3D Human Pose Ambiguities with 3D Scene Constraintscited by 295
  10. 2019Learning Trajectory Dependencies for Human Motion Predictioncited by 246
  11. 2015Structural-RNN: Deep Learning on Spatio-Temporal Graphscited by 234
  12. 2019Social-BiGAT: Multimodal Trajectory Forecasting using Bicycle-GAN and Graph Attention Networkscited by 229
28 more
  1. 2017Single-Shot Multi-Person 3D Pose Estimation From Monocular RGBcited by 195
  2. 2020Long-term Human Motion Prediction with Scene Contextcited by 192
  3. 2017Social Attention: Modeling Attention in Human Crowdscited by 186
  4. 2020DLow: Diversifying Latent Flows for Diverse Human Motion Predictioncited by 185
  5. 2017HP-GAN: Probabilistic 3D human motion prediction via GANcited by 176
  6. 2017PoseTrack: A Benchmark for Human Pose Estimation and Trackingcited by 173
  7. 2020History Repeats Itself: Human Motion Prediction via Motion Attentioncited by 165
  8. 2020Coherent Reconstruction of Multiple Humans from a Single Imagecited by 136
  9. 2020A Spatio-temporal Transformer for 3D Human Motion Predictioncited by 133
  10. 2019Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Imagecited by 132
  11. 2018Convolutional Sequence to Sequence Model for Human Dynamicscited by 115
  12. 2018Human Motion Prediction via Spatio-Temporal Inpaintingcited by 114
  13. 2017Deep representation learning for human motion prediction and classificationcited by 98
  14. 2018LCR-Net++: Multi-person 2D and 3D Pose Detection in Natural Imagescited by 88
  15. 2018MT-VAE: Learning Motion Transformations to Generate Multimodal Human Dynamicscited by 86
  16. 2019Context-aware Human Motion Predictioncited by 84
  17. 20163D Human Pose Estimation from a Single Image via Distance Matrix Regressioncited by 73
  18. 2017Learning Human Motion Models for Long-term Predictionscited by 67
  19. 2018Action-Agnostic Human Pose Forecastingcited by 56
  20. 2021TRiPOD: Human Trajectory and Pose Dynamics Forecasting in the Wildcited by 52
  21. 2020Socially and Contextually Aware Human Motion and Pose Forecastingcited by 51
  22. 2020HMOR: Hierarchical Multi-Person Ordinal Relations for Monocular Multi-Person 3D Pose Estimationcited by 44
  23. 2021Spatio-Temporal Graph Dual-Attention Network for Multi-Agent Prediction and Trackingcited by 35
  24. 2019Multi-Person 3D Human Pose Estimation from Monocular Imagescited by 19
  25. 2020PI-Net: Pose Interacting Network for Multi-Person Monocular 3D Pose Estimationcited by 15
  26. 2018Transferable Interactiveness Knowledge for Human-Object Interaction Detectioncited by 12
  27. 2020AnimePose: Multi-person 3D pose estimation and animationcited by 10
  28. 2019Instance- and Category-level 6D Object Pose Estimationcited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 4; 2023: 20; 2024: 24; 2025: 21; 2026: 5.

75 papers.

Sort:

By area:

  1. 2023InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactionscited by 206
  2. 2022Back to MLP: A Simple Baseline for Human Motion Predictioncited by 100
  3. 2023Inter-X: Towards Versatile Human-Human Interaction Analysiscited by 98
  4. 2023Hi4D: 4D Instance Segmentation of Close Human Interactioncited by 87
  5. 2024Seamless Human Motion Composition with Blended Positional Encodingscited by 80
  6. 2023ReMoS: 3D Motion-Conditioned Reaction Synthesis for Two-Person Interactionscited by 62
  7. 2024ReGenNet: Towards Human Action-Reaction Synthesiscited by 53
  8. 2024CORE4D: A 4D Human-Object-Human Interaction Dataset for Collaborative Object REarrangementcited by 44
  9. 2024FreeMotion: A Unified Framework for Number-free Text-to-Motion Synthesiscited by 42
  10. 2024Harmony4D: A Video Dataset for In-The-Wild Close Human Interactionscited by 31
  11. 2024Multi-agent Long-term 3D Human Pose Forecasting via Interaction-aware Trajectory Conditioningcited by 30
  12. 2024in2IN: Leveraging individual Information to Generate Human INteractionscited by 29
38 more
  1. 2024Towards Open Domain Text-Driven Synthesis of Multi-Person Motionscited by 29
  2. 2023Stochastic Multi-Person 3D Motion Forecastingcited by 28
  3. 2023Trajectory-Aware Body Interaction Transformer for Multi-Person Pose Forecastingcited by 26
  4. 2025A Survey on Human Interaction Motion Generationcited by 25
  5. 2023InterControl: Zero-shot Human Interaction Generation by Controlling Every Jointcited by 23
  6. 2023CoMusion: Towards Consistent Stochastic Human Motion Prediction via Motion Diffusioncited by 21
  7. 2024Closely Interactive Human Reconstruction with Proxemics and Physics-Guided Adaptioncited by 19
  8. 2024MultiPhys: Multi-Person Physics-aware 3D Motion Estimationcited by 18
  9. 2025UniEgoMotion: A Unified Model for Egocentric Motion Reconstruction, Forecasting, and Generationcited by 17
  10. 2023Joint-Relation Transformer for Multi-Person Motion Predictioncited by 16
  11. 2024Dense Hand-Object(HO) GraspNet with Full Grasping Taxonomy and Dynamicscited by 15
  12. 2025HERO: Human Reaction Generation from Videoscited by 15
  13. 2023Reconstructing Three-Dimensional Models of Interacting Humanscited by 14
  14. 2024MEGA: Masked Generative Autoencoder for Human Mesh Recoverycited by 14
  15. 2024MotionBank: A Large-scale Video Motion Benchmark with Disentangled Rule-based Annotationscited by 14
  16. 2025WorldPose: A World Cup Dataset for Global 3D Human Pose Estimationcited by 14
  17. 2025SocialGen: Modeling Multi-Human Social Interaction with Language Modelscited by 14
  18. 2023VQ-HPS: Human Pose and Shape Estimation in a Vector-Quantized Latent Spacecited by 13
  19. 20223D Pose Based Feedback for Physical Exercisescited by 11
  20. 2021Dyadic Human Motion Predictioncited by 9
  21. 2023Social Motion Prediction with Cognitive Hierarchiescited by 9
  22. 2024Synergy and Synchrony in Couple Dancescited by 9
  23. 2025MVHumanNet++: A Large-scale Dataset of Multi-view Daily Dressing Human Captures with Richer Annotations for 3D Human Digitizationcited by 9
  24. 2023Best Practices for 2-Body Pose Forecastingcited by 8
  25. 2025Perceiving and Acting in First-Person: A Dataset and Benchmark for Egocentric Human-Object-Human Interactionscited by 8
  26. 2024Robot Interaction Behavior Generation based on Social Motion Forecasting for Human-Robot Interactioncited by 7
  27. 2024AvatarPose: Avatar-guided 3D Pose Estimation of Close Human Interaction from Sparse Multi-view Videoscited by 7
  28. 20253D Human Interaction Generation: A Surveycited by 7
  29. 2025Ponimator: Unfolding Interactive Pose for Versatile Human-human Interaction Animationcited by 7
  30. 2022Interaction Mix and Match: Synthesizing Close Interaction using Conditional Hierarchical GAN with Multi-Hot Class Embeddingcited by 6
  31. 2022SoMoFormer: Social-Aware Motion Transformer for Multi-Person Motion Predictioncited by 6
  32. 2023Staged Contact-Aware Global Human Motion Forecastingcited by 6
  33. 2024Context-based Interpretable Spatio-Temporal Graph Convolutional Network for Human Motion Forecastingcited by 6
  34. 2024Multi-Condition Latent Diffusion Network for Scene-Aware Neural Human Motion Predictioncited by 6
  35. 2025Interact2Ar: Full-Body Human-Human Interaction Generation via Autoregressive Diffusion Modelscited by 6
  36. 2024Two-Person Interaction Augmentation with Skeleton Priorscited by 5
  37. 2023Towards Accurate Human Motion Prediction via Iterative Refinementcited by 4
  38. 2025Reconstructing Close Human Interaction with Appearance and Proxemics Reasoningcited by 4

50 most cited of 75 All 75 (JSON)