mlsanityData to 14 Oct 2026

MSN: Multi-Style Network for Trajectory Prediction

arXiv 2107.00932 ↗First posted 2 Jul 2021cs.CVcited by 19

Not on the map. Why?

Abstract (arXiv)

Trajectory prediction aims to forecast agents' possible future locations considering their observations along with the video context. It is strongly needed by many autonomous platforms like tracking, detection, robot navigation, and self-driving cars. Whether it is agents' internal personality factors, interactive behaviors with the neighborhood, or the influence of surroundings, they all impact agents' future planning. However, many previous methods model and predict agents' behaviors with the same strategy or feature distribution, making them challenging to make predictions with sufficient style differences. This paper proposes the Multi-Style Network (MSN), which utilizes style proposal and stylized prediction using two sub-networks, to provide multi-style predictions in a novel categorical way adaptively. The proposed network contains a series of style channels, and each channel is bound to a unique and specific behavior style. We use agents' end-point plannings and their interaction context as the basis for the behavior classification, so as to adaptively learn multiple diverse behavior styles through these channels. Then, we assume that the target agents may plan their future behaviors according to each of these categorized styles, thus utilizing different style channels to make predictions with significant style differences in parallel. Experiments show that the proposed MSN outperforms current state-of-the-art methods up to 10% quantitatively on two widely used datasets, and presents better multi-style characteristics qualitatively.

Key facts. Cited by 19 papers in the map (data through 14 Oct 2026). Builds on 36 of its 78 references that are in the map. First posted on arXiv 2 Jul 2021.

Builds on

36 of 78 references.

References · 36

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  3. 2018Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networkscited by 690
  4. 2019MultiPath: Multiple Probabilistic Anchor Trajectory Hypotheses for Behavior Predictioncited by 420
  5. 2020Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Predictioncited by 325
  6. 2017DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agentscited by 310
  7. 2018SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraintscited by 298
  8. 2018Multimodal Trajectory Predictions for Autonomous Driving using Deep Convolutional Networkscited by 289
  9. 2019CoverNet: Multimodal Behavior Prediction using Trajectory Setscited by 259
  10. 2020It Is Not the Journey but the Destination: Endpoint Conditioned Trajectory Predictioncited by 236
  11. 2019Human Motion Trajectory Prediction: A Surveycited by 232
  12. 2019Social-BiGAT: Multimodal Trajectory Forecasting using Bicycle-GAN and Graph Attention Networkscited by 229
24 more
  1. 2018Convolutional Social Pooling for Vehicle Trajectory Predictioncited by 221
  2. 2020Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Predictioncited by 218
  3. 2017Social Attention: Modeling Attention in Human Crowdscited by 186
  4. 2020Transformer Networks for Trajectory Forecastingcited by 181
  5. 2019PRECOG: PREdiction Conditioned On Goals in Visual Multi-Agent Settingscited by 179
  6. 2020From Goals, Waypoints & Paths To Long Term Human Trajectory Forecastingcited by 167
  7. 2020Human Trajectory Forecasting in Crowds: A Deep Learning Perspectivecited by 129
  8. 2019Peeking into the Future: Predicting Future Person Activities and Locations in Videoscited by 114
  9. 2019SR-LSTM: State Refinement for LSTM towards Pedestrian Trajectory Predictioncited by 111
  10. 2019Social Ways: Learning Multi-Modal Distributions of Pedestrian Trajectories with GANscited by 79
  11. 2019The Garden of Forking Paths: Towards Multi-Future Trajectory Predictioncited by 72
  12. 2021Trajectory Prediction with Latent Belief Energy-Based Modelcited by 60
  13. 2018How would surround vehicles move? A Unified Framework for Maneuver Classification and Motion Predictioncited by 46
  14. 2021Three Steps to Multimodal Trajectory Prediction: Modality Clustering, Classification and Synthesiscited by 46
  15. 2021Interpretable Social Anchors for Human Trajectory Forecasting in Crowdscited by 44
  16. 2021Spectral Temporal Graph Neural Network for Trajectory Predictioncited by 36
  17. 2018Scene-LSTM: A Model for Human Trajectory Predictioncited by 25
  18. 2020Goal-driven Long-Term Trajectory Predictioncited by 24
  19. 2020Temporal Pyramid Network for Pedestrian Trajectory Prediction with Multi-Supervisioncited by 20
  20. 2019Social and Scene-Aware Trajectory Prediction in Crowded Spacescited by 19
  21. 2017Pedestrian Prediction by Planning using Deep Neural Networkscited by 11
  22. 2018A Scalable Framework for Trajectory Predictioncited by 7
  23. 2020ArTIST: Autoregressive Trajectory Inpainting and Scoring for Trackingcited by 6
  24. 2020BGM: Building a Dynamic Guidance Map without Visual Images for Trajectory Predictioncited by 1

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 0; 2023: 5; 2024: 6; 2025: 7.

19 papers.

Sort:

By area:

  1. 2021View Vertically: A Hierarchical Network for Trajectory Prediction via Fourier Spectrumscited by 45
  2. 2023SocialCircle: Learning the Angle-based Social Interaction Representation for Pedestrian Trajectory Predictioncited by 27
  3. 2024Progressive Pretext Task Learning for Human Trajectory Predictioncited by 16
  4. 2023Another Vertical View: A Hierarchical Network for Heterogeneous Trajectory Prediction via Spectrumscited by 14
  5. 2024Risk-Aware Vehicle Trajectory Prediction Under Safety-Critical Scenarioscited by 7
  6. 2024SocialCircle+: Learning the Angle-based Conditioned Interaction Representation for Pedestrian Trajectory Predictioncited by 7
  7. 2025Continuous Locomotive Crowd Behavior Generationcited by 7
  8. 2024Resonance: Learning to Predict Social-Aware Pedestrian Trajectories as Co-Vibrationscited by 5
  9. 2025Social-Pose: Enhancing Trajectory Prediction with Human Body Posecited by 5
  10. 2023Pedestrian Trajectory Forecasting Using Deep Ensembles Under Sensing Uncertaintycited by 3
  11. 2024Agile Decision-Making and Safety-Critical Motion Planning for Emergency Autonomous Vehiclescited by 3
  12. 2024Who Walks With You Matters: Perceiving Social Interactions with Groups for Pedestrian Trajectory Predictioncited by 3
7 more
  1. 2025Recent Advances in Multi-Agent Human Trajectory Prediction: A Comprehensive Reviewcited by 2
  2. 2023Improving Trajectory Prediction in Dynamic Multi-Agent Environment by Dropping Waypointscited by 1
  3. 2023Enhancing Trajectory Prediction through Self-Supervised Waypoint Noise Predictioncited by 1
  4. 2025Quantifying and Modeling Driving Styles in Trajectory Forecastingcited by 1
  5. 2025Learning Velocity and Acceleration: Self-Supervised Motion Consistency for Pedestrian Trajectory Predictioncited by 1
  6. 2025Out-of-Sight Embodied Agents: Multimodal Tracking, Sensor Fusion, and Trajectory Forecastingcited by 1
  7. 2025Reverberation: Learning the Latencies Before Forecasting Trajectoriescited by 1