mlsanityData to 14 Oct 2026

HOME: Heatmap Output for future Motion Estimation

arXiv 2105.10968 ↗First posted 23 May 2021cs.CV cs.ROcited by 122

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose HOME, a framework tackling the motion forecasting problem with an image output representing the probability distribution of the agent's future location. This method allows for a simple architecture with classic convolution networks coupled with attention mechanism for agent interactions, and outputs an unconstrained 2D top-view representation of the agent's possible future. Based on this output, we design two methods to sample a finite set of agent's future locations. These methods allow us to control the optimization trade-off between miss rate and final displacement error for multiple modalities without having to retrain any part of the model. We apply our method to the Argoverse Motion Forecasting Benchmark and achieve 1st place on the online leaderboard.

Key facts. Cited by 122 papers in the map (data through 14 Oct 2026). Builds on 31 of its 34 references that are in the map. First posted on arXiv 23 May 2021.

Builds on

31 of 34 references.

References · 31

  1. 2017Attention Is All You Needcited by 60,361
  2. 2016Layer Normalizationcited by 5,669
  3. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  4. 2019Objects as Pointscited by 1,175
  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. 2020Learning Lane Graph Representations for Motion Forecastingcited by 382
  9. 2020TNT: Target-driveN Trajectory Predictioncited by 347
  10. 2017DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agentscited by 310
  11. 2018An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solutioncited by 307
  12. 2018Multimodal Trajectory Predictions for Autonomous Driving using Deep Convolutional Networkscited by 289
19 more
  1. 2019CoverNet: Multimodal Behavior Prediction using Trajectory Setscited by 259
  2. 2020It Is Not the Journey but the Destination: Endpoint Conditioned Trajectory Predictioncited by 236
  3. 2021Multimodal Motion Prediction with Stacked Transformerscited by 208
  4. 2019PRECOG: PREdiction Conditioned On Goals in Visual Multi-Agent Settingscited by 179
  5. 2019Multiple Futures Predictioncited by 178
  6. 2020From Goals, Waypoints & Paths To Long Term Human Trajectory Forecastingcited by 167
  7. 2020Perceive, Predict, and Plan: Safe Motion Planning Through Interpretable Semantic Representationscited by 153
  8. 2021LaneRCNN: Distributed Representations for Graph-Centric Motion Forecastingcited by 113
  9. 2021TPCN: Temporal Point Cloud Networks for Motion Forecastingcited by 94
  10. 2019Multi-Head Attention for Multi-Modal Joint Vehicle Motion Forecastingcited by 87
  11. 2020What-If Motion Prediction for Autonomous Drivingcited by 80
  12. 2019The Garden of Forking Paths: Towards Multi-Future Trajectory Predictioncited by 72
  13. 2020Trajectory Forecasts in Unknown Environments Conditioned on Grid-Based Planscited by 72
  14. 2021Learning to Predict Vehicle Trajectories with Model-based Planningcited by 63
  15. 2019Discrete Residual Flow for Probabilistic Pedestrian Behavior Predictioncited by 34
  16. 2020Map-Adaptive Goal-Based Trajectory Predictioncited by 30
  17. 2020Probabilistic Multi-modal Trajectory Prediction with Lane Attention for Autonomous Vehiclescited by 28
  18. 2019Scene Compliant Trajectory Forecast with Agent-Centric Spatio-Temporal Gridscited by 24
  19. 2020Trajectory Prediction for Autonomous Driving based on Multi-Head Attention with Joint Agent-Map Representationcited by 12

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 9; 2022: 26; 2023: 39; 2024: 22; 2025: 17; 2026: 9.

122 papers.

Sort:

By area:

  1. 2023Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecastingcited by 707
  2. 2021DenseTNT: End-to-end Trajectory Prediction from Dense Goal Setscited by 295
  3. 2022Motion Transformer with Global Intention Localization and Local Movement Refinementcited by 270
  4. 2021MultiPath++: Efficient Information Fusion and Trajectory Aggregation for Behavior Predictioncited by 246
  5. 2023MotionDiffuser: Controllable Multi-Agent Motion Prediction using Diffusioncited by 213
  6. 2021Scene Transformer: A unified architecture for predicting multiple agent trajectoriescited by 165
  7. 2021GOHOME: Graph-Oriented Heatmap Output for future Motion Estimationcited by 146
  8. 2023GameFormer: Game-theoretic Modeling and Learning of Transformer-based Interactive Prediction and Planning for Autonomous Drivingcited by 141
  9. 2023MTR++: Multi-Agent Motion Prediction with Symmetric Scene Modeling and Guided Intention Queryingcited by 140
  10. 2023Leapfrog Diffusion Model for Stochastic Trajectory Predictioncited by 132
  11. 2023Vision Language Models in Autonomous Driving: A Survey and Outlookcited by 126
  12. 2022ViP3D: End-to-end Visual Trajectory Prediction via 3D Agent Queriescited by 117
38 more
  1. 2023Recent Advancements in End-to-End Autonomous Driving using Deep Learning: A Surveycited by 103
  2. 2021THOMAS: Trajectory Heatmap Output with learned Multi-Agent Samplingcited by 101
  3. 2022M2I: From Factored Marginal Trajectory Prediction to Interactive Predictioncited by 81
  4. 2022BITS: Bi-level Imitation for Traffic Simulationcited by 80
  5. 2023Forecast-MAE: Self-supervised Pre-training for Motion Forecasting with Masked Autoencoderscited by 73
  6. 2022GoRela: Go Relative for Viewpoint-Invariant Motion Forecastingcited by 68
  7. 2023CAT: Closed-loop Adversarial Training for Safe End-to-End Drivingcited by 54
  8. 2022GANet: Goal Area Network for Motion Forecastingcited by 49
  9. 2022FJMP: Factorized Joint Multi-Agent Motion Prediction over Learned Directed Acyclic Interaction Graphscited by 41
  10. 2023ADAPT: Efficient Multi-Agent Trajectory Prediction with Adaptationcited by 41
  11. 2024HPNet: Dynamic Trajectory Forecasting with Historical Prediction Attentioncited by 38
  12. 2024Producing and Leveraging Online Map Uncertainty in Trajectory Predictioncited by 33
  13. 2022SSL-Lanes: Self-Supervised Learning for Motion Forecasting in Autonomous Drivingcited by 32
  14. 2023MacFormer: Map-Agent Coupled Transformer for Real-time and Robust Trajectory Predictioncited by 32
  15. 2023The Integration of Prediction and Planning in Deep Learning Automated Driving Systems: A Reviewcited by 29
  16. 2022Forecasting from LiDAR via Future Object Detectioncited by 28
  17. 2022Perceive, Interact, Predict: Learning Dynamic and Static Clues for End-to-End Motion Predictioncited by 28
  18. 2023SEPT: Towards Efficient Scene Representation Learning for Motion Predictioncited by 27
  19. 2022PreTraM: Self-Supervised Pre-training via Connecting Trajectory and Mapcited by 25
  20. 2022R-Pred: Two-Stage Motion Prediction Via Tube-Query Attention-Based Trajectory Refinementcited by 24
  21. 2022Bootstrap Motion Forecasting With Self-Consistent Constraintscited by 23
  22. 2023Machine Learning for Autonomous Vehicle's Trajectory Prediction: A comprehensive survey, Challenges, and Future Research Directionscited by 23
  23. 2023Large Trajectory Models are Scalable Motion Predictors and Plannerscited by 23
  24. 2021Trajectory Prediction with Graph-based Dual-scale Context Fusioncited by 19
  25. 2023Imitation with Spatial-Temporal Heatmap: 2nd Place Solution for NuPlan Challengecited by 19
  26. 2024VisionTrap: Vision-Augmented Trajectory Prediction Guided by Textual Descriptionscited by 19
  27. 2021Collaborative Uncertainty in Multi-Agent Trajectory Forecastingcited by 18
  28. 2023SCENE: Reasoning about Traffic Scenes using Heterogeneous Graph Neural Networkscited by 18
  29. 2023What Truly Matters in Trajectory Prediction for Autonomous Driving?cited by 17
  30. 2023EDA: Evolving and Distinct Anchors for Multimodal Motion Predictioncited by 17
  31. 2025Data Scaling Laws for End-to-End Autonomous Drivingcited by 15
  32. 2025Trajectory Prediction for Autonomous Driving: Progress, Limitations, and Future Directionscited by 14
  33. 2022Uncertainty estimation for Cross-dataset performance in Trajectory predictioncited by 13
  34. 2022Collaborative Uncertainty Benefits Multi-Agent Multi-Modal Trajectory Forecastingcited by 13
  35. 2025UniMM: A Unified Mixture Model Framework for Multi-Agent Simulationcited by 13
  36. 2021HYPER: Learned Hybrid Trajectory Prediction via Factored Inference and Adaptive Samplingcited by 12
  37. 2022Diverse Multiple Trajectory Prediction Using a Two-stage Prediction Network Trained with Lane Losscited by 12
  38. 2022RAP: Risk-Aware Prediction for Robust Planningcited by 12

50 most cited of 122 All 122 (JSON)