mlsanityData to 7 Oct 2026

Interpretable Social Anchors for Human Trajectory Forecasting in Crowds

arXiv 2105.03136 ↗First posted 7 May 2021cs.CVcited by 44

Not on the map. Why?

Abstract (arXiv)

Human trajectory forecasting in crowds, at its core, is a sequence prediction problem with specific challenges of capturing inter-sequence dependencies (social interactions) and consequently predicting socially-compliant multimodal distributions. In recent years, neural network-based methods have been shown to outperform hand-crafted methods on distance-based metrics. However, these data-driven methods still suffer from one crucial limitation: lack of interpretability. To overcome this limitation, we leverage the power of discrete choice models to learn interpretable rule-based intents, and subsequently utilise the expressibility of neural networks to model scene-specific residual. Extensive experimentation on the interaction-centric benchmark TrajNet++ demonstrates the effectiveness of our proposed architecture to explain its predictions without compromising the accuracy.

Key facts. Cited by 44 papers in the map (data through 7 Oct 2026). Builds on 26 of its 68 references that are in the map. First posted on arXiv 7 May 2021.

Builds on

26 of 68 references.

References · 26

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  4. 2018Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networkscited by 687
  5. 2019MultiPath: Multiple Probabilistic Anchor Trajectory Hypotheses for Behavior Predictioncited by 417
  6. 2020Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Predictioncited by 324
  7. 2017DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agentscited by 310
  8. 2018SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraintscited by 296
  9. 2019Social-BiGAT: Multimodal Trajectory Forecasting using Bicycle-GAN and Graph Attention Networkscited by 228
  10. 2020Transformer Networks for Trajectory Forecastingcited by 180
  11. 2018Crowd-Robot Interaction: Crowd-aware Robot Navigation with Attention-based Deep Reinforcement Learningcited by 162
  12. 2020Human Trajectory Forecasting in Crowds: A Deep Learning Perspectivecited by 128
14 more
  1. 2019Peeking into the Future: Predicting Future Person Activities and Locations in Videoscited by 112
  2. 2019SR-LSTM: State Refinement for LSTM towards Pedestrian Trajectory Predictioncited by 111
  3. 2016Learning in an Uncertain World: Representing Ambiguity Through Multiple Hypothesescited by 96
  4. 2019Social Ways: Learning Multi-Modal Distributions of Pedestrian Trajectories with GANscited by 78
  5. 2016Cooperative Training of Descriptor and Generator Networkscited by 60
  6. 2017Soft + Hardwired Attention: An LSTM Framework for Human Trajectory Prediction and Abnormal Event Detectioncited by 42
  7. 2017A Data-driven Model for Interaction-aware Pedestrian Motion Prediction in Object Cluttered Environmentscited by 23
  8. 2020A Neural-embedded Choice Model: TasteNet-MNL Modeling Taste Heterogeneity with Flexibility and Interpretabilitycited by 20
  9. 2019StarNet: Pedestrian Trajectory Prediction using Deep Neural Network in Star Topologycited by 17
  10. 2018GD-GAN: Generative Adversarial Networks for Trajectory Prediction and Group Detection in Crowdscited by 15
  11. 2020Social-WaGDAT: Interaction-aware Trajectory Prediction via Wasserstein Graph Double-Attention Networkcited by 14
  12. 2019Situation-Aware Pedestrian Trajectory Prediction with Spatio-Temporal Attention Modelcited by 10
  13. 2019A bi-partite generative model framework for analyzing and simulating large scale multiple discrete-continuous travel behaviour datacited by 3
  14. 2020EvolveGraph: Multi-Agent Trajectory Prediction with Dynamic Relational Reasoningcited by 3

Built on by

Cited by year

Citing papers per year: 2021: 5; 2022: 12; 2023: 12; 2024: 8; 2025: 7.

44 papers.

Sort:

By area:

  1. 2022Adaptive Trajectory Prediction via Transferable GNNcited by 51
  2. 2023Uncovering the Missing Pattern: Unified Framework Towards Trajectory Imputation and Predictioncited by 47
  3. 2023EigenTrajectory: Low-Rank Descriptors for Multi-Modal Trajectory Forecastingcited by 41
  4. 2024SingularTrajectory: Universal Trajectory Predictor Using Diffusion Modelcited by 35
  5. 2023Diverse Human Motion Prediction Guided by Multi-Level Spatial-Temporal Anchorscited by 34
  6. 2024Can Language Beat Numerical Regression? Language-Based Multimodal Trajectory Predictioncited by 31
  7. 2021Review of Pedestrian Trajectory Prediction Methods: Comparing Deep Learning and Knowledge-based Approachescited by 30
  8. 2023Stochastic Multi-Person 3D Motion Forecastingcited by 28
  9. 2023SocialCircle: Learning the Angle-based Social Interaction Representation for Pedestrian Trajectory Predictioncited by 27
  10. 2022SMEMO: Social Memory for Trajectory Forecastingcited by 26
  11. 2022Interpretable Self-Aware Neural Networks for Robust Trajectory Predictioncited by 22
  12. 2021MSN: Multi-Style Network for Trajectory Predictioncited by 19
32 more
  1. 2022LatentFormer: Multi-Agent Transformer-Based Interaction Modeling and Trajectory Predictioncited by 19
  2. 2023Joint Metrics Matter: A Better Standard for Trajectory Forecastingcited by 17
  3. 2025Trajectory Mamba: Efficient Attention-Mamba Forecasting Model Based on Selective SSMcited by 17
  4. 2021Safety-aware Motion Prediction with Unseen Vehicles for Autonomous Drivingcited by 15
  5. 2025Trajectory Prediction for Autonomous Driving: Progress, Limitations, and Future Directionscited by 14
  6. 2021HYPER: Learned Hybrid Trajectory Prediction via Factored Inference and Adaptive Samplingcited by 12
  7. 2022Safety-compliant Generative Adversarial Networks for Human Trajectory Forecastingcited by 12
  8. 2022Motion Style Transfer: Modular Low-Rank Adaptation for Deep Motion Forecastingcited by 12
  9. 2021Conditional Temporal Variational AutoEncoder for Action Video Predictioncited by 9
  10. 2022Trajectory Forecasting from Detection with Uncertainty-Aware Motion Encodingcited by 8
  11. 2023Vision-based Multi-future Trajectory Prediction: A Surveycited by 8
  12. 2024SocialCVAE: Predicting Pedestrian Trajectory via Interaction Conditioned Latentscited by 8
  13. 2024Disentangled Neural Relational Inference for Interpretable Motion Predictioncited by 7
  14. 2025Continuous Locomotive Crowd Behavior Generationcited by 7
  15. 2024Certified Human Trajectory Predictioncited by 6
  16. 2024SocialCircle+: Learning the Angle-based Conditioned Interaction Representation for Pedestrian Trajectory Predictioncited by 6
  17. 2022Pedestrian Stop and Go Forecasting with Hybrid Feature Fusioncited by 5
  18. 2022Benchmark for Models Predicting Human Behavior in Gap Acceptance Scenarioscited by 5
  19. 2023DESTINE: Dynamic Goal Queries with Temporal Transductive Alignment for Trajectory Predictioncited by 5
  20. 2024Resonance: Learning to Predict Social-Aware Pedestrian Trajectories as Co-Vibrationscited by 5
  21. 2023Interpretable Goal-Based model for Vehicle Trajectory Prediction in Interactive Scenarioscited by 3
  22. 2022A Recurrent Differentiable Engine for Modeling Tensegrity Robots Trainable with Low-Frequency Datacited by 2
  23. 2022DIDER: Discovering Interpretable Dynamically Evolving Relationscited by 2
  24. 2025Recent Advances in Multi-Agent Human Trajectory Prediction: A Comprehensive Reviewcited by 2
  25. 2025Intention-Aware Diffusion Model for Pedestrian Trajectory Predictioncited by 2
  26. 2022Learning a Pedestrian Social Behavior Dictionarycited by 1
  27. 2023GSGFormer: Generative Social Graph Transformer for Multimodal Pedestrian Trajectory Predictioncited by 1
  28. 2023Interpretable Long Term Waypoint-Based Trajectory Prediction Modelcited by 1
  29. 2025Learning Velocity and Acceleration: Self-Supervised Motion Consistency for Pedestrian Trajectory Predictioncited by 1
  30. 2023Learning Socio-Temporal Graphs for Multi-Agent Trajectory Predictioncited by 0
  31. 2024Social-MAE: Social Masked Autoencoder for Multi-person Motion Representation Learningcited by 0
  32. 2025Towards Developing Socially Compliant Automated Vehicles: Advances, Expert Insights, and A Conceptual Frameworkcited by 0