mlsanityData to 7 Oct 2026

Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Prediction

arXiv 2005.08514 ↗First posted 18 May 2020cs.CV cs.LG cs.ROcited by 218

Not on the map. Why?

Abstract (arXiv)

Understanding crowd motion dynamics is critical to real-world applications, e.g., surveillance systems and autonomous driving. This is challenging because it requires effectively modeling the socially aware crowd spatial interaction and complex temporal dependencies. We believe attention is the most important factor for trajectory prediction. In this paper, we present STAR, a Spatio-Temporal grAph tRansformer framework, which tackles trajectory prediction by only attention mechanisms. STAR models intra-graph crowd interaction by TGConv, a novel Transformer-based graph convolution mechanism. The inter-graph temporal dependencies are modeled by separate temporal Transformers. STAR captures complex spatio-temporal interactions by interleaving between spatial and temporal Transformers. To calibrate the temporal prediction for the long-lasting effect of disappeared pedestrians, we introduce a read-writable external memory module, consistently being updated by the temporal Transformer. We show that with only attention mechanism, STAR achieves state-of-the-art performance on 5 commonly used real-world pedestrian prediction datasets.

Key facts. Cited by 218 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 May 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 39; 2022: 52; 2023: 46; 2024: 38; 2025: 36; 2026: 7.

218 papers.

Sort:

By area:

  1. 2022Transformers in Time Series: A Surveycited by 489
  2. 2021AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecastingcited by 327
  3. 2022Wayformer: Motion Forecasting via Simple & Efficient Attention Networkscited by 279
  4. 2022Stochastic Trajectory Prediction via Motion Indeterminacy Diffusioncited by 184
  5. 2021Scene Transformer: A unified architecture for predicting multiple agent trajectoriescited by 165
  6. 2023A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detectioncited by 145
  7. 2021Latent Variable Sequential Set Transformers For Joint Multi-Agent Motion Predictioncited by 131
  8. 2023Leapfrog Diffusion Model for Stochastic Trajectory Predictioncited by 129
  9. 2022GroupNet: Multiscale Hypergraph Neural Networks for Trajectory Prediction with Relational Reasoningcited by 128
  10. 2022Joint Hand Motion and Interaction Hotspots Prediction from Egocentric Videoscited by 110
  11. 2021SGCN:Sparse Graph Convolution Network for Pedestrian Trajectory Predictioncited by 97
  12. 2021TransMOT: Spatial-Temporal Graph Transformer for Multiple Object Trackingcited by 93
38 more
  1. 2022Remember Intentions: Retrospective-Memory-based Trajectory Predictioncited by 86
  2. 2024UniST: A Prompt-Empowered Universal Model for Urban Spatio-Temporal Predictioncited by 86
  3. 2022SocialVAE: Human Trajectory Prediction using Timewise Latentscited by 65
  4. 2021Multi-Person 3D Motion Prediction with Multi-Range Transformerscited by 63
  5. 2021Stepwise Goal-Driven Networks for Trajectory Predictioncited by 62
  6. 2022A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspectivecited by 56
  7. 2022Adaptive Trajectory Prediction via Transferable GNNcited by 51
  8. 2023LAformer: Trajectory Prediction for Autonomous Driving with Lane-Aware Scene Constraintscited by 50
  9. 2021On Exposing the Challenging Long Tail in Future Prediction of Traffic Actorscited by 48
  10. 2023Uncovering the Missing Pattern: Unified Framework Towards Trajectory Imputation and Predictioncited by 47
  11. 2021Three Steps to Multimodal Trajectory Prediction: Modality Clustering, Classification and Synthesiscited by 46
  12. 2022Non-Probability Sampling Network for Stochastic Human Trajectory Predictioncited by 46
  13. 2021View Vertically: A Hierarchical Network for Trajectory Prediction via Fourier Spectrumscited by 44
  14. 2022Learning Pedestrian Group Representations for Multi-modal Trajectory Predictioncited by 44
  15. 2022Contrastive Trajectory Similarity Learning with Dual-Feature Attentioncited by 44
  16. 2021Human Trajectory Prediction via Counterfactual Analysiscited by 42
  17. 2023Traj-MAE: Masked Autoencoders for Trajectory Predictioncited by 42
  18. 2023EigenTrajectory: Low-Rank Descriptors for Multi-Modal Trajectory Forecastingcited by 41
  19. 2023Memory-and-Anticipation Transformer for Online Action Understandingcited by 39
  20. 2021Multiscale Spatio-Temporal Graph Neural Networks for 3D Skeleton-Based Motion Predictioncited by 36
  21. 2022Graph-based Spatial Transformer with Memory Replay for Multi-future Pedestrian Trajectory Predictioncited by 36
  22. 2022How many Observations are Enough? Knowledge Distillation for Trajectory Forecastingcited by 35
  23. 2024SingularTrajectory: Universal Trajectory Predictor Using Diffusion Modelcited by 35
  24. 2021Self-supervised Video Representation Learning by Context and Motion Decouplingcited by 34
  25. 2023Social-Transmotion: Promptable Human Trajectory Predictioncited by 33
  26. 2021Are socially-aware trajectory prediction models really socially-aware?cited by 32
  27. 2023FEND: A Future Enhanced Distribution-Aware Contrastive Learning Framework for Long-tail Trajectory Predictioncited by 31
  28. 2024Can Language Beat Numerical Regression? Language-Based Multimodal Trajectory Predictioncited by 31
  29. 2021Personalized Trajectory Prediction via Distribution Discriminationcited by 30
  30. 2021Occlusion-Aware Video Object Inpaintingcited by 30
  31. 2021Review of Pedestrian Trajectory Prediction Methods: Comparing Deep Learning and Knowledge-based Approachescited by 30
  32. 2022Rethinking Learning Approaches for Long-Term Action Anticipationcited by 29
  33. 2022Goal-driven Self-Attentive Recurrent Networks for Trajectory Predictioncited by 28
  34. 2022Dynamic-Group-Aware Networks for Multi-Agent Trajectory Prediction with Relational Reasoningcited by 28
  35. 2023Stochastic Multi-Person 3D Motion Forecastingcited by 28
  36. 2023Fast Inference and Update of Probabilistic Density Estimation on Trajectory Predictioncited by 27
  37. 2023SocialCircle: Learning the Angle-based Social Interaction Representation for Pedestrian Trajectory Predictioncited by 27
  38. 2022SMEMO: Social Memory for Trajectory Forecastingcited by 26

50 most cited of 218 All 218 (JSON)