mlsanityData to 14 Oct 2026

Traj-MAE: Masked Autoencoders for Trajectory Prediction

arXiv 2303.06697 ↗First posted 12 Mar 2023cs.CVcited by 42

Not on the map. Why?

Abstract (arXiv)

Trajectory prediction has been a crucial task in building a reliable autonomous driving system by anticipating possible dangers. One key issue is to generate consistent trajectory predictions without colliding. To overcome the challenge, we propose an efficient masked autoencoder for trajectory prediction (Traj-MAE) that better represents the complicated behaviors of agents in the driving environment. Specifically, our Traj-MAE employs diverse masking strategies to pre-train the trajectory encoder and map encoder, allowing for the capture of social and temporal information among agents while leveraging the effect of environment from multiple granularities. To address the catastrophic forgetting problem that arises when pre-training the network with multiple masking strategies, we introduce a continual pre-training framework, which can help Traj-MAE learn valuable and diverse information from various strategies efficiently. Our experimental results in both multi-agent and single-agent settings demonstrate that Traj-MAE achieves competitive results with state-of-the-art methods and significantly outperforms our baseline model.

Key facts. Cited by 42 papers in the map (data through 14 Oct 2026). Builds on 60 of its 76 references that are in the map. First posted on arXiv 12 Mar 2023.

Builds on

60 of 76 references.

References · 60

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  4. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  5. 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,811
  6. 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,375
  7. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,333
  8. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,382
  9. 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,330
  10. 2022VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Trainingcited by 1,322
  11. 2018Experience Replay for Continual Learningcited by 1,095
  12. 2019Learning Robust Global Representations by Penalizing Local Predictive Powercited by 1,013
38 more
  1. 2017PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruningcited by 898
  2. 2019Argoverse: 3D Tracking and Forecasting with Rich Mapscited by 732
  3. 2018Overcoming catastrophic forgetting with hard attention to the taskcited by 681
  4. 2020VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representationcited by 530
  5. 2022Masked Autoencoders for Point Cloud Self-supervised Learningcited by 459
  6. 2022Masked Autoencoders As Spatiotemporal Learnerscited by 429
  7. 2020TNT: Target-driveN Trajectory Predictioncited by 347
  8. 2021AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecastingcited by 331
  9. 2018SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraintscited by 298
  10. 2021DenseTNT: End-to-end Trajectory Prediction from Dense Goal Setscited by 295
  11. 2022MultiMAE: Multi-modal Multi-task Masked Autoencoderscited by 291
  12. 2022Wayformer: Motion Forecasting via Simple & Efficient Attention Networkscited by 280
  13. 2022Motion Transformer with Global Intention Localization and Local Movement Refinementcited by 270
  14. 2022Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-trainingcited by 264
  15. 2021MultiPath++: Efficient Information Fusion and Trajectory Aggregation for Behavior Predictioncited by 246
  16. 2018Selective Experience Replay for Lifelong Learningcited by 241
  17. 2019ERNIE 2.0: A Continual Pre-training Framework for Language Understandingcited by 231
  18. 2019INTERACTION Dataset: An INTERnational, Adversarial and Cooperative moTION Dataset in Interactive Driving Scenarios with Semantic Mapscited by 231
  19. 2020Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Predictioncited by 218
  20. 2021Multimodal Motion Prediction with Stacked Transformerscited by 208
  21. 2020UniLMv2: Pseudo-Masked Language Models for Unified Language Model Pre-Trainingcited by 204
  22. 2021Scene Transformer: A unified architecture for predicting multiple agent trajectoriescited by 165
  23. 2021GOHOME: Graph-Oriented Heatmap Output for future Motion Estimationcited by 146
  24. 2022Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoderscited by 144
  25. 2021Latent Variable Sequential Set Transformers For Joint Multi-Agent Motion Predictioncited by 131
  26. 2020Human Trajectory Forecasting in Crowds: A Deep Learning Perspectivecited by 129
  27. 2021Are Large-scale Datasets Necessary for Self-Supervised Pre-training?cited by 117
  28. 2020Implicit Latent Variable Model for Scene-Consistent Motion Forecastingcited by 116
  29. 2021LaneRCNN: Distributed Representations for Graph-Centric Motion Forecastingcited by 113
  30. 2019SR-LSTM: State Refinement for LSTM towards Pedestrian Trajectory Predictioncited by 111
  31. 2022HDGT: Heterogeneous Driving Graph Transformer for Multi-Agent Trajectory Prediction via Scene Encodingcited by 110
  32. 2017Encoder Based Lifelong Learningcited by 102
  33. 2021THOMAS: Trajectory Heatmap Output with learned Multi-Agent Samplingcited by 101
  34. 2021TPCN: Temporal Point Cloud Networks for Motion Forecastingcited by 94
  35. 2022M2I: From Factored Marginal Trajectory Prediction to Interactive Predictioncited by 81
  36. 2021Category-Level 6D Object Pose Estimation via Cascaded Relation and Recurrent Reconstruction Networkscited by 69
  37. 2018Task Agnostic Continual Learning Using Online Variational Bayescited by 61
  38. 2023Joint-MAE: 2D-3D Joint Masked Autoencoders for 3D Point Cloud Pre-trainingcited by 52

50 most cited of 60 All 60 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 7; 2024: 17; 2025: 15; 2026: 3.

42 papers.

Sort:

By area:

  1. 2023RealGen: Retrieval Augmented Generation for Controllable Traffic Scenarioscited by 46
  2. 2024HPNet: Dynamic Trajectory Forecasting with Historical Prediction Attentioncited by 38
  3. 2024Can Language Beat Numerical Regression? Language-Based Multimodal Trajectory Predictioncited by 31
  4. 2023SEPT: Towards Efficient Scene Representation Learning for Motion Predictioncited by 27
  5. 2024Adapting to Length Shift: FlexiLength Network for Trajectory Predictioncited by 22
  6. 2024Multi-Transmotion: Pre-trained Model for Human Motion Predictioncited by 21
  7. 2024T4P: Test-Time Training of Trajectory Prediction via Masked Autoencoder and Actor-specific Token Memorycited by 20
  8. 2024Sports-Traj: A Unified Trajectory Generation Model for Multi-Agent Movement in Sportscited by 19
  9. 2023Pre-training on Synthetic Driving Data for Trajectory Predictioncited by 18
  10. 2025Trajectory Prediction for Autonomous Driving: Progress, Limitations, and Future Directionscited by 14
  11. 2023Masked Modeling for Self-supervised Representation Learning on Vision and Beyondcited by 13
  12. 2024CooPre: Cooperative Pretraining for V2X Cooperative Perceptioncited by 11
30 more
  1. 2024Motion Forecasting in Continuous Drivingcited by 11
  2. 2025TurboTrain: Towards Efficient and Balanced Multi-Task Learning for Multi-Agent Perception and Predictioncited by 9
  3. 2025Motion Forecasting for Autonomous Vehicles: A Surveycited by 8
  4. 2024JointMotion: Joint Self-Supervision for Joint Motion Predictioncited by 7
  5. 2024SmartPretrain: Model-Agnostic and Dataset-Agnostic Representation Learning for Motion Predictioncited by 7
  6. 2025Continuous Locomotive Crowd Behavior Generationcited by 7
  7. 2023RedMotion: Motion Prediction via Redundancy Reductioncited by 6
  8. 2023RMP: A Random Mask Pretrain Framework for Motion Predictioncited by 6
  9. 2024MS-Net: A Multi-Path Sparse Model for Motion Prediction in Multi-Scenescited by 4
  10. 2024SceneMotion: From Agent-Centric Embeddings to Scene-Wide Forecastscited by 4
  11. 2023Navigating Uncertainty: The Role of Short-Term Trajectory Prediction in Autonomous Vehicle Safetycited by 3
  12. 2024UVTM: Universal Vehicle Trajectory Modeling with ST Feature Domain Generationcited by 3
  13. 2024Forecast-PEFT: Parameter-Efficient Fine-Tuning for Pre-trained Motion Forecasting Modelscited by 3
  14. 2024RealTraj: Towards Real-World Pedestrian Trajectory Forecastingcited by 3
  15. 2025Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Promptingcited by 3
  16. 2025Vector Representations of Vessel Treescited by 3
  17. 2024Scalable and Generalizable Correspondence Pruning via Geometry-Consistent Pre-trainingcited by 2
  18. 2025GAMDTP: Dynamic Trajectory Prediction with Graph Attention Mamba Networkcited by 2
  19. 2025Deep Space Weather Model: Long-Range Solar Flare Prediction from Multi-Wavelength Imagescited by 2
  20. 2025Map-World: Masked Action planning and Path-Integral World Model for Autonomous Drivingcited by 2
  21. 2026Recover to Predict: Progressive Retrospective Learning for Variable-Length Trajectory Predictioncited by 2
  22. 2024CrowdMAC: Masked Crowd Density Completion for Robust Crowd Density Forecastingcited by 1
  23. 2025Structure-preserving contrastive learning for spatial time seriescited by 1
  24. 2025Recurrent Auto-Encoders for Enhanced Deep Reinforcement Learning in Wilderness Search and Rescue Planningcited by 0
  25. 2025ILNet: Trajectory Prediction with Inverse Learning Attention for Enhancing Intention Capturecited by 0
  26. 2025ProgD: Progressive Multi-scale Decoding with Dynamic Graphs for Joint Multi-agent Motion Forecastingcited by 0
  27. 2025AdaSports-Traj: Role- and Domain-Aware Adaptation for Multi-Agent Trajectory Modeling in Sportscited by 0
  28. 2025Monocular 3D Lane Detection via Structure Uncertainty-Aware Network with Curve-Point Queriescited by 0
  29. 2026TaPD: Temporal-adaptive Progressive Distillation for Observation-Adaptive Trajectory Forecasting in Autonomous Drivingcited by 0
  30. 2026MetaDAT: Generalizable Trajectory Prediction via Meta Pre-training and Data-Adaptive Test-Time Updatingcited by 0