mlsanityData to 7 Oct 2026

ART: Adaptive Relational Transformer for Pedestrian Trajectory Prediction with Temporal-Aware Relations

arXiv 2604.03649 ↗First posted 4 Apr 2026cs.CV cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

Accurate prediction of real-world pedestrian trajectories is crucial for a wide range of robot-related applications. Recent approaches typically adopt graph-based or transformer-based frameworks to model interactions. Despite their effectiveness, these methods either introduce unnecessary computational overhead or struggle to represent the diverse and time-varying characteristics of human interactions. In this work, we present an Adaptive Relational Transformer (ART), which introduces a Temporal-Aware Relation Graph (TARG) to explicitly capture the evolution of pairwise interactions and an Adaptive Interaction Pruning (AIP) mechanism to reduce redundant computations efficiently. Extensive evaluations on ETH/UCY and NBA benchmarks show that ART delivers state-of-the-art accuracy with high computational efficiency.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 31 of its 39 references that are in the map. First posted on arXiv 4 Apr 2026.

Builds on

31 of 39 references.

References · 31

  1. 2017Attention Is All You Needcited by 59,932
  2. 2017Graph Attention Networkscited by 8,854
  3. 2018Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networkscited by 687
  4. 2021AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecastingcited by 327
  5. 2020Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Predictioncited by 218
  6. 2022Stochastic Trajectory Prediction via Motion Indeterminacy Diffusioncited by 184
  7. 2023Leapfrog Diffusion Model for Stochastic Trajectory Predictioncited by 129
  8. 2022GroupNet: Multiscale Hypergraph Neural Networks for Trajectory Prediction with Relational Reasoningcited by 128
  9. 2023EqMotion: Equivariant Multi-agent Motion Prediction with Invariant Interaction Reasoningcited by 97
  10. 2022Remember Intentions: Retrospective-Memory-based Trajectory Predictioncited by 86
  11. 2023On the Design Fundamentals of Diffusion Models: A Surveycited by 59
  12. 2025Twilight: Adaptive Attention Sparsity with Hierarchical Top-p Pruningcited by 48
19 more
  1. 2022Non-Probability Sampling Network for Stochastic Human Trajectory Predictioncited by 46
  2. 2022Relational Attention: Generalizing Transformers for Graph-Structured Taskscited by 41
  3. 2023EigenTrajectory: Low-Rank Descriptors for Multi-Modal Trajectory Forecastingcited by 41
  4. 2018PORCA: Modeling and Planning for Autonomous Driving among Many Pedestrianscited by 36
  5. 2024SingularTrajectory: Universal Trajectory Predictor Using Diffusion Modelcited by 35
  6. 2022Dynamic-Group-Aware Networks for Multi-Agent Trajectory Prediction with Relational Reasoningcited by 28
  7. 2022End-to-End Trajectory Distribution Prediction Based on Occupancy Grid Mapscited by 22
  8. 2024MART: MultiscAle Relational Transformer Networks for Multi-agent Trajectory Predictioncited by 21
  9. 2025Unified Spatial-Temporal Edge-Enhanced Graph Networks for Pedestrian Trajectory Predictioncited by 13
  10. 2021Learning Sparse Interaction Graphs of Partially Detected Pedestrians for Trajectory Predictioncited by 10
  11. 2022Multiclass-SGCN: Sparse Graph-based Trajectory Prediction with Agent Class Embeddingcited by 9
  12. 2025BP-SGCN: Behavioral Pseudo-Label Informed Sparse Graph Convolution Network for Pedestrian and Heterogeneous Trajectory Predictioncited by 9
  13. 2023Trajectory Prediction for Robot Navigation using Flow-Guided Markov Neural Operatorcited by 6
  14. 2024From Category to Scenery: An End-to-End Framework for Multi-Person Human-Object Interaction Recognition in Videoscited by 4
  15. 2025ViTE: Virtual Graph Trajectory Expert Router for Pedestrian Trajectory Predictioncited by 4
  16. 2022Learning Heterogeneous Interaction Strengths by Trajectory Prediction with Graph Neural Networkcited by 3
  17. 2023IA-LSTM: Interaction-Aware LSTM for Pedestrian Trajectory Predictioncited by 3
  18. 2025Large-Scale Multi-Character Interaction Synthesiscited by 3
  19. 2025Geometric Visual Fusion Graph Neural Networks for Multi-Person Human-Object Interaction Recognition in Videoscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026HSTGFormer: Hyper Spatial-Temporal Graph Transformer for 3D Human Pose Estimationcited by 0