mlsanityData to 14 Oct 2026

Social-Pose: Enhancing Trajectory Prediction with Human Body Pose

arXiv 2507.22742 ↗First posted 30 Jul 2025cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Accurate human trajectory prediction is one of the most crucial tasks for autonomous driving, ensuring its safety. Yet, existing models often fail to fully leverage the visual cues that humans subconsciously communicate when navigating the space. In this work, we study the benefits of predicting human trajectories using human body poses instead of solely their Cartesian space locations in time. We propose `Social-pose', an attention-based pose encoder that effectively captures the poses of all humans in a scene and their social relations. Our method can be integrated into various trajectory prediction architectures. We have conducted extensive experiments on state-of-the-art models (based on LSTM, GAN, MLP, and Transformer), and showed improvements over all of them on synthetic (Joint Track Auto) and real (Human3.6M, Pedestrians and Cyclists in Road Traffic, and JRDB) datasets. We also explored the advantages of using 2D versus 3D poses, as well as the effect of noisy poses and the application of our pose-based predictor in robot navigation scenarios.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 42 of its 72 references that are in the map. First posted on arXiv 30 Jul 2025.

Builds on

42 of 72 references.

References · 42

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2018Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networkscited by 690
  4. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  5. 2021AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecastingcited by 331
  6. 2018SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraintscited by 298
  7. 2020Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Predictioncited by 218
  8. 2022Stochastic Trajectory Prediction via Motion Indeterminacy Diffusioncited by 185
  9. 2020Transformer Networks for Trajectory Forecastingcited by 181
  10. 2018Crowd-Robot Interaction: Crowd-aware Robot Navigation with Attention-based Deep Reinforcement Learningcited by 175
  11. 2021Latent Variable Sequential Set Transformers For Joint Multi-Agent Motion Predictioncited by 131
  12. 2020Human Trajectory Forecasting in Crowds: A Deep Learning Perspectivecited by 129
30 more
  1. 2019PifPaf: Composite Fields for Human Pose Estimationcited by 120
  2. 2019Peeking into the Future: Predicting Future Person Activities and Locations in Videoscited by 114
  3. 2019SR-LSTM: State Refinement for LSTM towards Pedestrian Trajectory Predictioncited by 111
  4. 2023EqMotion: Equivariant Multi-agent Motion Prediction with Invariant Interaction Reasoningcited by 97
  5. 2018Learning to Detect and Track Visible and Occluded Body Joints in a Virtual Worldcited by 82
  6. 2020CanonPose: Self-Supervised Monocular 3D Human Pose Estimation in the Wildcited by 65
  7. 2021MG-GAN: A Multi-Generator Model Preventing Out-of-Distribution Samples in Pedestrian Trajectory Predictioncited by 61
  8. 2017Future Person Localization in First-Person Videoscited by 58
  9. 2020Collaborative Motion Prediction via Neural Motion Message Passingcited by 55
  10. 2022Graph-based Spatial Transformer with Memory Replay for Multi-future Pedestrian Trajectory Predictioncited by 36
  11. 2023Social-Transmotion: Promptable Human Trajectory Predictioncited by 33
  12. 2021Are socially-aware trajectory prediction models really socially-aware?cited by 32
  13. 2020DAG-Net: Double Attentive Graph Neural Network for Trajectory Forecastingcited by 30
  14. 2022JRDB-Pose: A Large-scale Dataset for Multi-Person Pose Estimation and Trackingcited by 25
  15. 2024Multi-Transmotion: Pre-trained Model for Human Motion Predictioncited by 21
  16. 2021MSN: Multi-Style Network for Trajectory Predictioncited by 19
  17. 2023MTP-GO: Graph-Based Probabilistic Multi-Agent Trajectory Prediction with Neural ODEscited by 19
  18. 2021Injecting Knowledge in Data-driven Vehicle Trajectory Predictorscited by 18
  19. 2020Pedestrian Intention Prediction: A Multi-task Perspectivecited by 16
  20. 2021Euro-PVI: Pedestrian Vehicle Interactions in Dense Urban Centerscited by 16
  21. 2019Forecasting People Trajectories and Head Poses by Jointly Reasoning on Tracklets and Visletscited by 13
  22. 2022Pedestrian 3D Bounding Box Predictioncited by 11
  23. 2023Toward Reliable Human Pose Forecasting with Uncertaintycited by 11
  24. 2023Evaluating Pedestrian Trajectory Prediction Methods with Respect to Autonomous Drivingcited by 11
  25. 2022Learning the Pedestrian-Vehicle Interaction for Pedestrian Trajectory Predictioncited by 7
  26. 2021Pose and Semantic Map Based Probabilistic Forecast of Vulnerable Road Users' Trajectoriescited by 6
  27. 2025Unified Human Localization and Trajectory Prediction with Monocular Visioncited by 5
  28. 2023Sim-to-Real Causal Transfer: A Metric Learning Approach to Causally-Aware Interaction Representationscited by 4
  29. 2024Hierarchical Light Transformer Ensembles for Multimodal Trajectory Forecastingcited by 4
  30. 2024TrajPRed: Trajectory Prediction with Region-based Relation Learningcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026Social-Mamba: Socially-Aware Trajectory Forecasting with State-Space Modelscited by 1
  2. 2026Robust Human Trajectory Prediction via Self-Supervised Skeleton Representation Learningcited by 0
  3. 2026Deformable Gaussian Occupancy: Decoupling Rigid and Nonrigid Motion with Factorized Distillationcited by 0
  4. 2026Three-Step Hierarchical Transformer for Multi-Pedestrian Trajectory Predictioncited by 0
  5. 2026HumAIN: Human-Aware Implicit Social Robot Navigationcited by 0