mlsanityData to 7 Oct 2026

Trustworthy Pedestrian Trajectory Prediction via Pattern-Aware Interaction Modeling

arXiv 2507.13397 ↗First posted 16 Jul 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Accurate and reliable pedestrian trajectory prediction is critical for the application of intelligent applications, yet achieving trustworthy prediction remains highly challenging due to the complexity of interactions among pedestrians. Previous methods often adopt black-box modeling of pedestrian interactions. Despite their strong performance, such opaque modeling limits the reliability of predictions in real-world deployments. To address this issue, we propose InSyn (Interaction-Synchronization Network), a novel Transformer-based model that explicitly captures diverse interaction patterns (e.g., walking in sync or conflicting) while effectively modeling direction-sensitive social behaviors. Additionally, we introduce a training strategy, termed Seq-Start of Seq (SSOS), designed to alleviate the common issue of initial-step divergence in numerical time-series prediction. Experiments on the ETH and UCY datasets demonstrate that our model not only outperforms recent black-box baselines in prediction accuracy, especially under high-density scenarios, but also provides transparent interaction modeling, as shown in the case study. Furthermore, the SSOS strategy proves to be effective in improving sequential prediction performance, reducing the initial-step prediction error by approximately 6.58%. Code is avaliable at https://github.com/rickzky1001/InSyn

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 20 of its 42 references that are in the map. First posted on arXiv 16 Jul 2025.

Builds on

20 of 42 references.

References · 20

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecastingcited by 327
  3. 2018SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraintscited by 296
  4. 2020Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Predictioncited by 218
  5. 2020Transformer Networks for Trajectory Forecastingcited by 180
  6. 2019SR-LSTM: State Refinement for LSTM towards Pedestrian Trajectory Predictioncited by 111
  7. 2019Conditional Generative Neural System for Probabilistic Trajectory Predictioncited by 76
  8. 2022Human Trajectory Prediction via Neural Social Physicscited by 66
  9. 2021Stepwise Goal-Driven Networks for Trajectory Predictioncited by 62
  10. 2022MUSE-VAE: Multi-Scale VAE for Environment-Aware Long Term Trajectory Predictioncited by 59
  11. 2018PORCA: Modeling and Planning for Autonomous Driving among Many Pedestrianscited by 36
  12. 2021Spatio-Temporal Graph Dual-Attention Network for Multi-Agent Prediction and Trackingcited by 35
8 more
  1. 2022LatentFormer: Multi-Agent Transformer-Based Interaction Modeling and Trajectory Predictioncited by 19
  2. 2023Attention-aware Social Graph Transformer Networks for Stochastic Trajectory Predictioncited by 8
  3. 2024Recurrent Aligned Network for Generalized Pedestrian Trajectory Predictioncited by 8
  4. 2024Pedestrian Trajectory Prediction with Missing Data: Datasets, Imputation, and Benchmarkingcited by 8
  5. 2025Pedestrian Trajectory Prediction Based on Social Interactions Learning With Random Weightscited by 8
  6. 2021PECNet: A Deep Multi-Label Segmentation Network for Eosinophilic Esophagitis Biopsy Diagnosticscited by 5
  7. 2020TPPO: A Novel Trajectory Predictor with Pseudo Oraclecited by 4
  8. 2023IA-LSTM: Interaction-Aware LSTM for Pedestrian Trajectory Predictioncited by 3

Built on by

Not cited yet.