mlsanityData to 7 Oct 2026

Raising context awareness in motion forecasting

arXiv 2109.08048 ↗First posted 16 Sep 2021cs.CV cs.AI cs.ROcited by 6

Not on the map. Why?

Abstract (arXiv)

Learning-based trajectory prediction models have encountered great success, with the promise of leveraging contextual information in addition to motion history. Yet, we find that state-of-the-art forecasting methods tend to overly rely on the agent's current dynamics, failing to exploit the semantic contextual cues provided at its input. To alleviate this issue, we introduce CAB, a motion forecasting model equipped with a training procedure designed to promote the use of semantic contextual information. We also introduce two novel metrics - dispersion and convergence-to-range - to measure the temporal consistency of successive forecasts, which we found missing in standard metrics. Our method is evaluated on the widely adopted nuScenes Prediction benchmark as well as on a subset of the most difficult examples from this benchmark. The code is available at github.com/valeoai/CAB

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 39 of its 53 references that are in the map. First posted on arXiv 16 Sep 2021.

Builds on

39 of 53 references.

References · 39

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  3. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  4. 2019Argoverse: 3D Tracking and Forecasting with Rich Mapscited by 728
  5. 2018Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networkscited by 687
  6. 2019MultiPath: Multiple Probabilistic Anchor Trajectory Hypotheses for Behavior Predictioncited by 417
  7. 2018ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worstcited by 391
  8. 2019Exploring the Limitations of Behavior Cloning for Autonomous Drivingcited by 343
  9. 2017Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answeringcited by 337
  10. 2017DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agentscited by 310
  11. 2018SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraintscited by 296
  12. 2018Multimodal Trajectory Predictions for Autonomous Driving using Deep Convolutional Networkscited by 289
27 more
  1. 2019Causal Confusion in Imitation Learningcited by 286
  2. 2019CoverNet: Multimodal Behavior Prediction using Trajectory Setscited by 259
  3. 2021End-to-end Interpretable Neural Motion Plannercited by 240
  4. 2020Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Netcited by 228
  5. 2018Convolutional Social Pooling for Vehicle Trajectory Predictioncited by 221
  6. 2019RUBi: Reducing Unimodal Biases in Visual Question Answeringcited by 183
  7. 2019PRECOG: PREdiction Conditioned On Goals in Visual Multi-Agent Settingscited by 178
  8. 2019Multiple Futures Predictioncited by 178
  9. 2021IntentNet: Learning to Predict Intention from Raw Sensor Datacited by 158
  10. 2021GOHOME: Graph-Oriented Heatmap Output for future Motion Estimationcited by 146
  11. 2019Multi-Agent Tensor Fusion for Contextual Trajectory Predictioncited by 131
  12. 2019End-to-End Bias Mitigation by Modelling Biases in Corporacited by 127
  13. 2021HOME: Heatmap Output for future Motion Estimationcited by 122
  14. 2016Analyzing the Behavior of Visual Question Answering Modelscited by 119
  15. 2019Rules of the Road: Predicting Driving Behavior with a Convolutional Model of Semantic Interactionscited by 117
  16. 2018TrafficPredict: Trajectory Prediction for Heterogeneous Traffic-Agentscited by 111
  17. 2018Overcoming Language Priors in Visual Question Answering with Adversarial Regularizationcited by 104
  18. 2019Spatially-Aware Graph Neural Networks for Relational Behavior Forecasting from Sensor Datacited by 104
  19. 2021Explainability of deep vision-based autonomous driving systems: Review and challengescited by 80
  20. 2017Probabilistic Vehicle Trajectory Prediction over Occupancy Grid Map via Recurrent Neural Networkcited by 56
  21. 2021On Exposing the Challenging Long Tail in Future Prediction of Traffic Actorscited by 48
  22. 2018Explicit Bias Discovery in Visual Question Answering Modelscited by 42
  23. 2020LaserFlow: Efficient and Probabilistic Object Detection and Motion Forecastingcited by 22
  24. 2020PLOP: Probabilistic poLynomial Objects trajectory Planning for autonomous drivingcited by 19
  25. 2019INFER: INtermediate representations for FuturE pRedictioncited by 12
  26. 2020Trajectory Prediction for Autonomous Driving based on Multi-Head Attention with Joint Agent-Map Representationcited by 12
  27. 2018Imitation Learning for End to End Vehicle Longitudinal Control with Forward Cameracited by 5

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 5.

6 papers.

  1. 2024UniTraj: A Unified Framework for Scalable Vehicle Trajectory Predictioncited by 51
  2. 2023Towards Motion Forecasting with Real-World Perception Inputs: Are End-to-End Approaches Competitive?cited by 22
  3. 2024Intention-aware Denoising Diffusion Model for Trajectory Predictioncited by 11
  4. 2024Valeo4Cast: A Modular Approach to End-to-End Forecastingcited by 5
  5. 2024Annealed Winner-Takes-All for Motion Forecastingcited by 4
  6. 2024PPT: Pretraining with Pseudo-Labeled Trajectories for Motion Forecastingcited by 2