Transformer Networks for Trajectory Forecasting

@article{Giuliari2021TransformerNF,
  title={Transformer Networks for Trajectory Forecasting},
  author={Francesco Giuliari and Irtiza Hasan and M. Cristani and Fabio Galasso},
  journal={2020 25th International Conference on Pattern Recognition (ICPR)},
  year={2021},
  pages={10335-10342}
}
Most recent successes on forecasting the people motion are based on LSTM models and all most recent progress has been achieved by modelling the social interaction among people and the people interaction with the scene. We question the use of the LSTM models and propose the novel use of Transformer Networks for trajectory forecasting. This is a fundamental switch from the sequential step-by-step processing of LSTMs to the only-attention-based memory mechanisms of Transformers. In particular, we… Expand

Figures and Tables from this paper

Pedestrian Trajectory Prediction using Context-Augmented Transformer Networks
Multimodal Motion Prediction with Stacked Transformers
TRiPOD: Human Trajectory and Pose Dynamics Forecasting in the Wild
FloMo: Tractable Motion Prediction with Normalizing Flows
baller2vec: A Multi-Entity Transformer For Multi-Agent Spatiotemporal Modeling
Trajectory Prediction with Latent Belief Energy-Based Model
UB-LSTM: A Trajectory Prediction Method Combined with Vehicle Behavior Recognition
AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecasting
...
1
2
3
...

References

SHOWING 1-10 OF 56 REFERENCES
Social LSTM: Human Trajectory Prediction in Crowded Spaces
SR-LSTM: State Refinement for LSTM Towards Pedestrian Trajectory Prediction
MX-LSTM: Mixing Tracklets and Vislets to Jointly Forecast Trajectories and Head Poses
An Evaluation of Trajectory Prediction Approaches and Notes on the TrajNet Benchmark
The Trajectron: Probabilistic Multi-Agent Trajectory Modeling With Dynamic Spatiotemporal Graphs
  • B. Ivanovic, M. Pavone
  • Computer Science
  • 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
  • 2019
RED: A Simple but Effective Baseline Predictor for the TrajNet Benchmark
Self-Growing Spatial Graph Networks for Pedestrian Trajectory Prediction
  • Sirin Haddad, S. Lam
  • Computer Science
  • 2020 IEEE Winter Conference on Applications of Computer Vision (WACV)
  • 2020
Activity Forecasting
Forecast the Plausible Paths in Crowd Scenes
...
1
2
3
4
5
...