mlsanityData to 7 Oct 2026

SocialVAE: Human Trajectory Prediction using Timewise Latents

arXiv 2203.08207 ↗First posted 15 Mar 2022cs.CV cs.LGcited by 65

Not on the map. Why?

Abstract (arXiv)

Predicting pedestrian movement is critical for human behavior analysis and also for safe and efficient human-agent interactions. However, despite significant advancements, it is still challenging for existing approaches to capture the uncertainty and multimodality of human navigation decision making. In this paper, we propose SocialVAE, a novel approach for human trajectory prediction. The core of SocialVAE is a timewise variational autoencoder architecture that exploits stochastic recurrent neural networks to perform prediction, combined with a social attention mechanism and a backward posterior approximation to allow for better extraction of pedestrian navigation strategies. We show that SocialVAE improves current state-of-the-art performance on several pedestrian trajectory prediction benchmarks, including the ETH/UCY benchmark, Stanford Drone Dataset, and SportVU NBA movement dataset. Code is available at: https://github.com/xupei0610/SocialVAE.

Key facts. Cited by 65 papers in the map (data through 7 Oct 2026). Builds on 35 of its 62 references that are in the map. First posted on arXiv 15 Mar 2022.

Builds on

35 of 62 references.

References · 35

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2017Graph Attention Networkscited by 8,854
  4. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  5. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  6. 2013Auto-Encoding Variational Bayescited by 3,980
  7. 2020Learning to Simulate Complex Physics with Graph Networkscited by 867
  8. 2016Conditional Image Generation with PixelCNN Decoderscited by 859
  9. 2016Pixel Recurrent Neural Networkscited by 814
  10. 2018Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networkscited by 687
  11. 2021Machine learning accelerated computational fluid dynamicscited by 461
  12. 2015A Recurrent Latent Variable Model for Sequential Datacited by 362
23 more
  1. 2021AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecastingcited by 327
  2. 2021Skillful Precipitation Nowcasting using Deep Generative Models of Radarcited by 308
  3. 2018SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraintscited by 296
  4. 2020It Is Not the Journey but the Destination: Endpoint Conditioned Trajectory Predictioncited by 235
  5. 2020Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Predictioncited by 218
  6. 2020Long-term Human Motion Prediction with Scene Contextcited by 191
  7. 2017Social Attention: Modeling Attention in Human Crowdscited by 185
  8. 2020Transformer Networks for Trajectory Forecastingcited by 180
  9. 2020From Goals, Waypoints & Paths To Long Term Human Trajectory Forecastingcited by 166
  10. 2016Sequential Neural Models with Stochastic Layerscited by 115
  11. 2018TraPHic: Trajectory Prediction in Dense and Heterogeneous Traffic Using Weighted Interactionscited by 82
  12. 2019What the Constant Velocity Model Can Teach Us About Pedestrian Motion Predictioncited by 78
  13. 2019Social Ways: Learning Multi-Modal Distributions of Pedestrian Trajectories with GANscited by 78
  14. 2020MANTRA: Memory Augmented Networks for Multiple Trajectory Predictioncited by 69
  15. 2021Stepwise Goal-Driven Networks for Trajectory Predictioncited by 62
  16. 2014Learning Stochastic Recurrent Networkscited by 60
  17. 2017Z-Forcing: Training Stochastic Recurrent Networkscited by 51
  18. 2020BiTraP: Bi-directional Pedestrian Trajectory Prediction with Multi-modal Goal Estimationcited by 47
  19. 2017CAR-Net: Clairvoyant Attentive Recurrent Networkcited by 34
  20. 2021You Mostly Walk Alone: Analyzing Feature Attribution in Trajectory Predictioncited by 23
  21. 2020Pedestrian Trajectory Prediction with Convolutional Neural Networkscited by 21
  22. 2018An Evaluation of Trajectory Prediction Approaches and Notes on the TrajNet Benchmarkcited by 16
  23. 2016Knowledge Transfer for Scene-specific Motion Predictioncited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 13; 2024: 15; 2025: 20; 2026: 16.

65 papers.

Sort:

By area:

  1. 2023Uncovering the Missing Pattern: Unified Framework Towards Trajectory Imputation and Predictioncited by 47
  2. 2023EigenTrajectory: Low-Rank Descriptors for Multi-Modal Trajectory Forecastingcited by 41
  3. 2024SingularTrajectory: Universal Trajectory Predictor Using Diffusion Modelcited by 35
  4. 2024Can Language Beat Numerical Regression? Language-Based Multimodal Trajectory Predictioncited by 31
  5. 2025MoFlow: One-Step Flow Matching for Human Trajectory Forecasting via Implicit Maximum Likelihood Estimation based Distillationcited by 31
  6. 2023SocialCircle: Learning the Angle-based Social Interaction Representation for Pedestrian Trajectory Predictioncited by 27
  7. 2024LG-Traj: LLM Guided Pedestrian Trajectory Predictioncited by 24
  8. 2024Adapting to Length Shift: FlexiLength Network for Trajectory Predictioncited by 22
  9. 2024T4P: Test-Time Training of Trajectory Prediction via Masked Autoencoder and Actor-specific Token Memorycited by 20
  10. 2024Sports-Traj: A Unified Trajectory Generation Model for Multi-Agent Movement in Sportscited by 19
  11. 2023Unsupervised Sampling Promoting for Stochastic Human Trajectory Predictioncited by 17
  12. 2024Progressive Pretext Task Learning for Human Trajectory Predictioncited by 16
38 more
  1. 2025Learning Personalized Driving Styles via Reinforcement Learning from Human Feedbackcited by 16
  2. 2024Diffusion-Based Environment-Aware Trajectory Predictioncited by 14
  3. 2025Trajectory Prediction for Autonomous Driving: Progress, Limitations, and Future Directionscited by 14
  4. 2024Geometric Trajectory Diffusion Modelscited by 13
  5. 2025Unified Spatial-Temporal Edge-Enhanced Graph Networks for Pedestrian Trajectory Predictioncited by 13
  6. 2023Context-Aware Timewise VAEs for Real-Time Vehicle Trajectory Predictioncited by 12
  7. 2025Multi-modal Knowledge Distillation-based Human Trajectory Forecastingcited by 10
  8. 2025BP-SGCN: Behavioral Pseudo-Label Informed Sparse Graph Convolution Network for Pedestrian and Heterogeneous Trajectory Predictioncited by 9
  9. 2023Vision-based Multi-future Trajectory Prediction: A Surveycited by 8
  10. 2023Social Motion Prediction with Cognitive Hierarchiescited by 8
  11. 2024SocialCVAE: Predicting Pedestrian Trajectory via Interaction Conditioned Latentscited by 8
  12. 2024Recurrent Aligned Network for Generalized Pedestrian Trajectory Predictioncited by 8
  13. 2025Continuous Locomotive Crowd Behavior Generationcited by 7
  14. 2025STFlow: Data-Coupled Flow Matching for Geometric Trajectory Simulationcited by 7
  15. 2024SocialCircle+: Learning the Angle-based Conditioned Interaction Representation for Pedestrian Trajectory Predictioncited by 6
  16. 2024Resonance: Learning to Predict Social-Aware Pedestrian Trajectories as Co-Vibrationscited by 5
  17. 2023A Study on Learning Social Robot Navigation with Multimodal Perceptioncited by 4
  18. 2023Sim-to-Real Causal Transfer: A Metric Learning Approach to Causally-Aware Interaction Representationscited by 4
  19. 2023Discovering Intrinsic Spatial-Temporal Logic Rules to Explain Human Actionscited by 3
  20. 2023Sparse Pedestrian Character Learning for Trajectory Predictioncited by 3
  21. 2023Exploring Social Motion Latent Space and Human Awareness for Effective Robot Navigation in Crowded Environmentscited by 2
  22. 2024Controllable Diverse Sampling for Diffusion Based Motion Behavior Forecastingcited by 2
  23. 2024DenoiseRep: Denoising Model for Representation Learningcited by 2
  24. 2025Towards Predicting Any Human Trajectory In Contextcited by 2
  25. 2025Recent Advances in Multi-Agent Human Trajectory Prediction: A Comprehensive Reviewcited by 2
  26. 2025Intention-Aware Diffusion Model for Pedestrian Trajectory Predictioncited by 2
  27. 2022Learning a Pedestrian Social Behavior Dictionarycited by 1
  28. 2023GSGFormer: Generative Social Graph Transformer for Multimodal Pedestrian Trajectory Predictioncited by 1
  29. 2025Post-interactive Multimodal Trajectory Prediction for Autonomous Drivingcited by 1
  30. 2025GeoAda: Efficiently Finetune Geometric Diffusion Models with Equivariant Adapterscited by 1
  31. 2025Diffusion^2: Dual Diffusion Model with Uncertainty-Aware Adaptive Noise for Momentary Trajectory Predictioncited by 1
  32. 2026Social-Mamba: Socially-Aware Trajectory Forecasting with State-Space Modelscited by 1
  33. 2025TrajFlow: A Generative Framework for Occupancy Density Estimation Using Normalizing Flowscited by 0
  34. 2025An Efficient LiDAR-Camera Fusion Network for Multi-Class 3D Dynamic Object Detection and Trajectory Predictioncited by 0
  35. 2025KoopCast: Trajectory Forecasting via Koopman Operatorscited by 0
  36. 2025AdaSports-Traj: Role- and Domain-Aware Adaptation for Multi-Agent Trajectory Modeling in Sportscited by 0
  37. 2025Hazy Pedestrian Trajectory Prediction via Physical Priors and Graph-Mambacited by 0
  38. 2025Coherent Multi-Agent Trajectory Forecasting in Team Sports with CausalTrajcited by 0

50 most cited of 65 All 65 (JSON)