论文标题
时空图形变压器网络，用于行人轨迹预测
Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Prediction
论文作者
论文摘要
了解人群运动动态对于实际应用，例如监视系统和自动驾驶至关重要。这是具有挑战性的，因为它需要有效地建模具有社会意识的人群空间互动和复杂的时间依赖性。我们认为，注意是轨迹预测的最重要因素。在本文中，我们提出了一个时空图形变压器框架，它仅通过注意机制来解决轨迹预测。 Star模型由TGCONV（一种新型的基于变压器的图形卷积机制）TGCONV模型。界面的时间依赖性由单独的颞变压器建模。星星通过在空间变压器和颞变压器之间交织来捕获复杂的时空相互作用。为了校准失踪行人的长期效果的时间预测，我们引入了一个可读取的外部记忆模块，始终由时间变压器更新。我们表明，仅通过注意机制，Star就可以在5个常用的实际人行人预测数据集上实现最先进的性能。
Understanding crowd motion dynamics is critical to real-world applications, e.g., surveillance systems and autonomous driving. This is challenging because it requires effectively modeling the socially aware crowd spatial interaction and complex temporal dependencies. We believe attention is the most important factor for trajectory prediction. In this paper, we present STAR, a Spatio-Temporal grAph tRansformer framework, which tackles trajectory prediction by only attention mechanisms. STAR models intra-graph crowd interaction by TGConv, a novel Transformer-based graph convolution mechanism. The inter-graph temporal dependencies are modeled by separate temporal Transformers. STAR captures complex spatio-temporal interactions by interleaving between spatial and temporal Transformers. To calibrate the temporal prediction for the long-lasting effect of disappeared pedestrians, we introduce a read-writable external memory module, consistently being updated by the temporal Transformer. We show that with only attention mechanism, STAR achieves state-of-the-art performance on 5 commonly used real-world pedestrian prediction datasets.
