mlsanityData to 14 Oct 2026

HUMOF: Human Motion Forecasting in Interactive Social Scenes

arXiv 2506.03753 ↗First posted 4 Jun 2025cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

Complex scenes present significant challenges for predicting human behaviour due to the abundance of interaction information, such as human-human and humanenvironment interactions. These factors complicate the analysis and understanding of human behaviour, thereby increasing the uncertainty in forecasting human motions. Existing motion prediction methods thus struggle in these complex scenarios. In this paper, we propose an effective method for human motion forecasting in interactive scenes. To achieve a comprehensive representation of interactions, we design a hierarchical interaction feature representation so that high-level features capture the overall context of the interactions, while low-level features focus on fine-grained details. Besides, we propose a coarse-to-fine interaction reasoning module that leverages both spatial and frequency perspectives to efficiently utilize hierarchical features, thereby enhancing the accuracy of motion predictions. Our method achieves state-of-the-art performance across four public datasets. The source code will be available at https://github.com/scy639/HUMOF.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 42 of its 52 references that are in the map. First posted on arXiv 4 Jun 2025.

Builds on

42 of 52 references.

References · 42

  1. 2017Attention Is All You Needcited by 60,361
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  3. 2020Simple and Deep Graph Convolutional Networkscited by 860
  4. 2017On human motion prediction using recurrent neural networkscited by 338
  5. 2019Learning Trajectory Dependencies for Human Motion Predictioncited by 246
  6. 2015Structural-RNN: Deep Learning on Spatio-Temporal Graphscited by 234
  7. 2020Long-term Human Motion Prediction with Scene Contextcited by 192
  8. 2020History Repeats Itself: Human Motion Prediction via Motion Attentioncited by 165
  9. 2022HUMANISE: Language-conditioned Human Motion Generation in 3D Scenescited by 158
  10. 2020A Spatio-temporal Transformer for 3D Human Motion Predictioncited by 133
  11. 2020Dynamic Multiscale Graph Neural Networks for 3D Skeleton-Based Human Motion Predictioncited by 132
  12. 2021MSR-GCN: Multi-Scale Residual Graph Convolution Networks for Human Motion Predictioncited by 100
30 more
  1. 2023Inter-X: Towards Versatile Human-Human Interaction Analysiscited by 98
  2. 2023EqMotion: Equivariant Multi-agent Motion Prediction with Invariant Interaction Reasoningcited by 97
  3. 2018A Neural Temporal Model for Human Motion Predictioncited by 87
  4. 2021Space-Time-Separable Graph Convolutional Network for Pose Forecastingcited by 84
  5. 2022GIMO: Gaze-Informed Human Motion Prediction in Contextcited by 81
  6. 2023GTA: A Geometry-Aware Attention Mechanism for Multi-View Transformerscited by 79
  7. 2021Multi-Person Extreme Motion Predictioncited by 75
  8. 2022Progressively Generating Better Initial Guesses Towards Next Stages for High-Quality Human Motion Predictioncited by 66
  9. 2021Multi-Person 3D Motion Prediction with Multi-Range Transformerscited by 63
  10. 2024HOI-M3:Capture Multiple Humans and Objects Interaction within Contextual Environmentcited by 53
  11. 2021TRiPOD: Human Trajectory and Pose Dynamics Forecasting in the Wildcited by 52
  12. 2020Socially and Contextually Aware Human Motion and Pose Forecastingcited by 51
  13. 2023Social-Transmotion: Promptable Human Trajectory Predictioncited by 33
  14. 2021Investigating Pose Representations and Motion Contexts Modeling for 3D Motion Predictioncited by 31
  15. 2024Multi-agent Long-term 3D Human Pose Forecasting via Interaction-aware Trajectory Conditioningcited by 30
  16. 2022Skeleton-Parted Graph Scattering Networks for 3D Human Motion Predictioncited by 29
  17. 2022Contact-aware Human Motion Forecastingcited by 27
  18. 2023Trajectory-Aware Body Interaction Transformer for Multi-Person Pose Forecastingcited by 26
  19. 2023Spherical Mask: Coarse-to-Fine 3D Point Cloud Instance Segmentation with Spherical Representationcited by 24
  20. 2022SoMoFormer: Multi-Person Pose Forecasting with Transformerscited by 23
  21. 2024Multi-Transmotion: Pre-trained Model for Human Motion Predictioncited by 21
  22. 2023Auxiliary Tasks Benefit 3D Skeleton-based Human Motion Predictioncited by 20
  23. 2022Motion Prediction via Joint Dependency Modeling in Phase Spacecited by 16
  24. 2023Joint-Relation Transformer for Multi-Person Motion Predictioncited by 16
  25. 2023Scene-aware Human Motion Forecasting via Mutual Distance Predictioncited by 8
  26. 2023Staged Contact-Aware Global Human Motion Forecastingcited by 6
  27. 2024Multi-Condition Latent Diffusion Network for Scene-Aware Neural Human Motion Predictioncited by 6
  28. 2023Dynamic Compositional Graph Convolutional Network for Efficient Composite Human Motion Predictioncited by 3
  29. 2024Existence Is Chaos: Enhancing 3D Human Motion Prediction with Uncertainty Considerationcited by 3
  30. 2024Massively Multi-Person 3D Human Motion Forecasting with Scene Contextcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026HumanFlow -- Diffusion-Driven MAV Navigation Among Humans via Tightly-Coupled Motion Tracking, Forecasting, and Controlcited by 0
  2. 2026Multi-Person Human Motion Forecasting in Complex Scenescited by 0