CAR-Net: Clairvoyant Attentive Recurrent Network

@article{Sadeghian2018CARNetCA,
  title={CAR-Net: Clairvoyant Attentive Recurrent Network},
  author={Amir Sadeghian and Ferdinand Legros and Maxime Voisin and Ricky Vesel and Alexandre Alahi and Silvio Savarese},
  journal={ArXiv},
  year={2018},
  volume={abs/1711.10061}
}
  • Amir Sadeghian, Ferdinand Legros, +3 authors Silvio Savarese
  • Published 2018
  • Computer Science
  • ArXiv
  • We present an interpretable framework for path prediction that leverages dependencies between agents’ behaviors and their spatial navigation environment. We exploit two sources of information: the past motion trajectory of the agent of interest and a wide top-view image of the navigation scene. We propose a Clairvoyant Attentive Recurrent Network (CAR-Net) that learns where to look in a large image of the scene when solving the path prediction task. Our method can attend to any area, or… CONTINUE READING

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 49 CITATIONS

    SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraints

    VIEW 8 EXCERPTS
    CITES METHODS & BACKGROUND

    Enhancing Accuracy for Human Trajectory Forecasting in Crowded Scenes

    VIEW 2 EXCERPTS
    CITES BACKGROUND & METHODS

    Scene Compliant Trajectory Forecast With Agent-Centric Spatio-Temporal Grids

    VIEW 3 EXCERPTS
    CITES METHODS

    Analysis of the Effect of Various Input Representations for LSTM-Based Trajectory Prediction

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Looking to Relations for Future Trajectory Forecast

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Social and Scene-Aware Trajectory Prediction in Crowded Spaces

    VIEW 1 EXCERPT
    CITES METHODS

    FILTER CITATIONS BY YEAR

    2018
    2020

    CITATION STATISTICS

    • 4 Highly Influenced Citations

    • Averaged 16 Citations per year from 2018 through 2020

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 55 REFERENCES

    Learning to Predict Human Behavior in Crowded Scenes

    DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agents

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Social LSTM: Human Trajectory Prediction in Crowded Spaces

    VIEW 3 EXCERPTS

    Learning and Inferring “Dark Matter” and Predicting Human Intents and Trajectories in Videos