mlsanityData to 14 Oct 2026

DESTINE: Dynamic Goal Queries with Temporal Transductive Alignment for Trajectory Prediction

arXiv 2310.07438 ↗First posted 11 Oct 2023cs.CV cs.ROcited by 5

Not on the map. Why?

Abstract (arXiv)

Predicting temporally consistent road users' trajectories in a multi-agent setting is a challenging task due to unknown characteristics of agents and their varying intentions. Besides using semantic map information and modeling interactions, it is important to build an effective mechanism capable of reasoning about behaviors at different levels of granularity. To this end, we propose Dynamic goal quErieS with temporal Transductive alIgNmEnt (DESTINE) method. Unlike past arts, our approach 1) dynamically predicts agents' goals irrespective of particular road structures, such as lanes, allowing the method to produce a more accurate estimation of destinations; 2) achieves map compliant predictions by generating future trajectories in a coarse-to-fine fashion, where the coarser predictions at a lower frame rate serve as intermediate goals; and 3) uses an attention module designed to temporally align predicted trajectories via masked attention. Using the common Argoverse benchmark dataset, we show that our method achieves state-of-the-art performance on various metrics, and further investigate the contributions of proposed modules via comprehensive ablation studies.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 55 of its 67 references that are in the map. First posted on arXiv 11 Oct 2023.

Builds on

55 of 67 references.

References · 55

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020End-to-End Object Detection with Transformerscited by 7,414
  3. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  4. 2020Reformer: The Efficient Transformercited by 1,668
  5. 2019Argoverse: 3D Tracking and Forecasting with Rich Mapscited by 732
  6. 2020VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representationcited by 530
  7. 2019MultiPath: Multiple Probabilistic Anchor Trajectory Hypotheses for Behavior Predictioncited by 420
  8. 2021Dynamic Neural Networks: A Surveycited by 408
  9. 2020Learning Lane Graph Representations for Motion Forecastingcited by 382
  10. 2020TNT: Target-driveN Trajectory Predictioncited by 347
  11. 2021AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecastingcited by 331
  12. 2020Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Predictioncited by 325
38 more
  1. 2016Dynamic Filter Networkscited by 319
  2. 2017DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agentscited by 310
  3. 2021DenseTNT: End-to-end Trajectory Prediction from Dense Goal Setscited by 295
  4. 2018Multimodal Trajectory Predictions for Autonomous Driving using Deep Convolutional Networkscited by 289
  5. 2019CondConv: Conditionally Parameterized Convolutions for Efficient Inferencecited by 273
  6. 2021MultiPath++: Efficient Information Fusion and Trajectory Aggregation for Behavior Predictioncited by 246
  7. 2019Social-BiGAT: Multimodal Trajectory Forecasting using Bicycle-GAN and Graph Attention Networkscited by 229
  8. 2020Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Predictioncited by 218
  9. 2021Multimodal Motion Prediction with Stacked Transformerscited by 208
  10. 2020From Goals, Waypoints & Paths To Long Term Human Trajectory Forecastingcited by 167
  11. 2021Instances as Queriescited by 158
  12. 2021Latent Variable Sequential Set Transformers For Joint Multi-Agent Motion Predictioncited by 131
  13. 2022GroupNet: Multiscale Hypergraph Neural Networks for Trajectory Prediction with Relational Reasoningcited by 128
  14. 2019Generalization in Generation: A closer look at Exposure Biascited by 123
  15. 2020Implicit Latent Variable Model for Scene-Consistent Motion Forecastingcited by 116
  16. 2021SGCN:Sparse Graph Convolution Network for Pedestrian Trajectory Predictioncited by 97
  17. 2021LookOut: Diverse Multi-Future Prediction and Planning for Self-Drivingcited by 96
  18. 2022Remember Intentions: Retrospective-Memory-based Trajectory Predictioncited by 86
  19. 2020TPNet: Trajectory Proposal Network for Motion Predictioncited by 80
  20. 2021Multi-modal Motion Prediction with Transformer-based Neural Network for Autonomous Drivingcited by 73
  21. 2020Diverse and Admissible Trajectory Forecasting through Multimodal Context Understandingcited by 68
  22. 2021SOLQ: Segmenting Objects by Learning Queriescited by 68
  23. 2021LaPred: Lane-Aware Prediction of Multi-Modal Future Trajectories of Dynamic Agentscited by 64
  24. 2021Stepwise Goal-Driven Networks for Trajectory Predictioncited by 62
  25. 2022MUSE-VAE: Multi-Scale VAE for Environment-Aware Long Term Trajectory Predictioncited by 59
  26. 2020Trajectron++: Dynamically-Feasible Trajectory Forecasting With Heterogeneous Datacited by 58
  27. 2021Decoupled Dynamic Filter Networkscited by 53
  28. 2020BiTraP: Bi-directional Pedestrian Trajectory Prediction with Multi-modal Goal Estimationcited by 47
  29. 2021Interpretable Social Anchors for Human Trajectory Forecasting in Crowdscited by 44
  30. 2022Learning Pedestrian Group Representations for Multi-modal Trajectory Predictioncited by 44
  31. 2021Vehicle trajectory prediction works, but not everywherecited by 39
  32. 2022Graph-based Spatial Transformer with Memory Replay for Multi-future Pedestrian Trajectory Predictioncited by 36
  33. 2020Bifold and Semantic Reasoning for Pedestrian Behavior Predictioncited by 31
  34. 2020Map-Adaptive Goal-Based Trajectory Predictioncited by 30
  35. 2021Learned Queries for Efficient Local Attentioncited by 27
  36. 2022Path-Aware Graph Attention for HD Maps in Motion Predictioncited by 23
  37. 2022PedFormer: Pedestrian Behavior Prediction via Cross-Modal Attention Modulation and Gated Multitask Learningcited by 23
  38. 2022LatentFormer: Multi-Agent Transformer-Based Interaction Modeling and Trajectory Predictioncited by 19

50 most cited of 55 All 55 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 4; 2025: 0; 2026: 1.

5 papers.

  1. 2024Curb Your Attention: Causal Attention Gating for Robust Trajectory Prediction in Autonomous Drivingcited by 9
  2. 2024TrACT: A Training Dynamics Aware Contrastive Learning Framework for Long-tail Trajectory Predictioncited by 7
  3. 2024AMEND: A Mixture of Experts Framework for Long-tailed Trajectory Predictioncited by 4
  4. 2024Diving Deeper Into Pedestrian Behavior Understanding: Intention Estimation, Action Prediction, and Event Risk Assessmentcited by 2
  5. 2026Where Will They Go? Modelling Multimodal Pedestrian Manoeuvres from Ego-centric Videoscited by 0