mlsanityData to 7 Oct 2026

Asymmetrical Bi-RNN for pedestrian trajectory encoding

arXiv 2106.04419 ↗First posted 1 Jun 2021cs.CV cs.AIcited by 6

Not on the map. Why?

Abstract (arXiv)

Pedestrian motion behavior involves a combination of individual goals and social interactions with other agents. In this article, we present an asymmetrical bidirectional recurrent neural network architecture called U-RNN to encode pedestrian trajectories and evaluate its relevance to replace LSTMs for various forecasting models. Experimental results on the Trajnet++ benchmark show that the U-LSTM variant yields better results regarding every available metrics (ADE, FDE, Collision rate) than common trajectory encoders for a variety of approaches and interaction modules, suggesting that the proposed approach is a viable alternative to the de facto sequence encoding RNNs. Our implementation of the asymmetrical Bi-RNNs for the Trajnet++ benchmark is available at: github.com/JosephGesnouin/Asymmetrical-Bi-RNNs-to-encode-pedestrian-trajectories

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 17 of its 34 references that are in the map. First posted on arXiv 1 Jun 2021.

Builds on

17 of 34 references.

References · 17

  1. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,341
  2. 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,303
  3. 2018Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networkscited by 687
  4. 2020It Is Not the Journey but the Destination: Endpoint Conditioned Trajectory Predictioncited by 235
  5. 2019Human Motion Trajectory Prediction: A Surveycited by 231
  6. 2017Social Attention: Modeling Attention in Human Crowdscited by 185
  7. 2020Transformer Networks for Trajectory Forecastingcited by 180
  8. 2020Human Trajectory Forecasting in Crowds: A Deep Learning Perspectivecited by 128
  9. 2019What the Constant Velocity Model Can Teach Us About Pedestrian Motion Predictioncited by 78
  10. 2020Social NCE: Contrastive Learning of Socially-aware Motion Representationscited by 58
  11. 2020BiTraP: Bi-directional Pedestrian Trajectory Prediction with Multi-modal Goal Estimationcited by 47
  12. 2017Context-Aware Trajectory Predictioncited by 31
5 more
  1. 2017A Data-driven Model for Interaction-aware Pedestrian Motion Prediction in Object Cluttered Environmentscited by 23
  2. 2020AMENet: Attentive Maps Encoder Network for Trajectory Predictioncited by 17
  3. 20173DOF Pedestrian Trajectory Prediction Learned from Long-Term Autonomous Mobile Robot Deployment Datacited by 11
  4. 2018Convolutional Neural Network for Trajectory Predictioncited by 11
  5. 2020Robust Trajectory Forecasting for Multiple Intelligent Agents in Dynamic Scenecited by 4

Built on by

Cited by year

Citing papers per year: 2021: 3; 2022: 1; 2023: 1; 2024: 0; 2025: 1.

6 papers.

  1. 2021GOHOME: Graph-Oriented Heatmap Output for future Motion Estimationcited by 146
  2. 2021THOMAS: Trajectory Heatmap Output with learned Multi-Agent Samplingcited by 101
  3. 2021TrouSPI-Net: Spatio-temporal attention on parallel atrous convolutions and U-GRUs for skeletal pedestrian crossing predictioncited by 13
  4. 2022Assessing Cross-dataset Generalization of Pedestrian Crossing Predictorscited by 11
  5. 2023Offline Tracking with Object Permanencecited by 7
  6. 2025Addressing Challenges in Time Series Forecasting: A Comprehensive Comparison of Machine Learning Techniquescited by 1