3.5 Spatio-Temporal Graph Transformer 时间transformer可以单独模拟每个行人的运动动力学,但不能考虑空间交互作用;spatial Transformer利用TGConv处理人群交互,但很难推广到时间序列。行人预测的一个主要挑战是建模耦合时空交互作用。行人的空间和时间动态密切相关。例如,当一个人决定她的下一个动作时,她首先会预测她的...
在时间维度上,对每个行人单独考虑,应用temporal Transformer抽取时许相关性; 即使是时许上的Transformer,也提供了比RNN更好的表现; 在空间维度上,引入TGConv--Transformer-based message passing graph convolution mechanism。相较于传统的图卷积抽取行人之间的交互关系,采用TGConv在高人群密度、复杂交互关系的情形下能...
This is challenging because\nit requires effectively modeling the socially aware crowd spatial interaction\nand complex temporal dependencies. We believe attention is the most important\nfactor for trajectory prediction. In this paper, we present STAR, a\nSpatio-Temporal grAph tRansformer framework, ...
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 ...
Research track中有3个session中与时空数据(城市计算)紧密相关:Urban data Ⅰ,Ⅱ与 spatio-temporal data,还有一些其余session中有一些做的时空数据任务。 Urban data Ⅰ Multi-Task Learning for Routing Problem with Cross-Problem Zero-Shot Generalization ...
Considering the volatility and randomness of wind energy, an attention mechanism is employed to enhance the capture of temporal features in the time-series input. For instance, research [34] introduces a spatial-temporal graph transformer network (STGTN), integrating a transformer with an external ...
Therefore, we propose STST, a novel approach using a Spatiotemporal Transformer-LSTM model for stock movement prediction. Our model obtains accuracies of 63.707 and 56.879 percent against the ACL18 and KDD17 datasets, respectively. In addition, our model was used in simulation to determine its ...
problems, this paper proposes a Multi-level Multi-view Augmented Spatio-temporal Transformer (LVSTformer) for traffic prediction, which captures spatial dependencies from three different levels: local geographic, global semantic, and pivotal nodes, along with long- and short-term temporal dependencies....
此文提出了一个基于Transformer名为ST-GRAT的交通预测模型使用self-attention捕捉时空间依赖。 此文对于self-attention做出改进,首先对于spatial attention加上路网信息先验,然后对于spatial和temporal attention都使用sentinel,sentinel可以自适应的选择保留原始信息或者获取新信息。
该文章提出了attention based spatial-temporal graph convolutional network (ASTGCN) model来进行交通流的预测 交通数据网络: 为什么说交通数据网络是空间时序问题?: 图(a) 两点间的连线代表其互相影响强度(mutual influence strength),颜色越深代表影响越大*交通流的预测除了时序和空间关系之外,还与路网结构、车速等相...