May 18, 2020 · In this paper, we present STAR, a Spatio-Temporal grAph tRansformer framework, which tackles trajectory prediction by only attention mechanisms.

In this paper, we introduce the Spatio-Temporal grAph tRansformer (STAR) framework, a novel framework for spatio-temporal trajectory prediction based purely on ...

This command is to train model for ETH-hotel and start test at epoch 10. For different dataset, change 'hotel' to other datasets named in the last section.

We demonstrate that our model effectively improves the accuracy of prediction by validation on five common datasets of pedestrian trajectory.

In this paper, we present STAR, a Spatio-Temporal grAph tRansformer framework, which tackles trajectory prediction by only attention mechanisms.

Oct 7, 2020 · In this paper, we present STAR, a Spatio-Temporal grAph tRansformer framework, which tackles trajectory prediction by only attention mechanisms.

Trajectory visualization of all ablations. Yellow lines denote the history, red lines denote the ground-truth, and blue lines denote the prediction.

It uses the temporal transformer to capture the state information of the pedestrian at different time points of itself, and uses the spatial transformer to ...

This work proposes Social Graph Transformer Networks for multi-modal prediction of pedestrian trajectories, where it combines Graph Convolutional Network ...

Abstract. To safely and rationally participate in dense and heterogeneous traffic, autonomous vehi- cles require to sufficiently analyze the motion patterns ...