… prediction is still very challenging as it is affected by many complex factors including dynamic
spatio-temporal … Dynamic spatio-temporal dependencies simultaneously contain spatial …

… CNN) models in [44,45,46] proposed a DNN-based traffic flow model to predict the historical
… To evaluate and verify the effective learning of model parameters on spatio-temporal data, …

… The combination of forward prediction (predict from the start time) and backward prediction
(predict from the end time) will better model the changes if a second clear-sky coarse-fine …

… Mining valuable knowledge from spatio-temporal data is critically important to many real…
spatio-temporal data into five different types, and then briefly introduce the deep learning models …

… Spatio-temporal model to predict crowd traffic flow at every region on the traffic network. It
is a dynamic deep hybrid spatio-temporal … This approach is more useful as spatio-temporal …

… This paper introduces a dynamic and fair spatio-temporal scheduler (D-STACK) for multiple
DNNs to run in the GPU concurrently. We develop and validate a model that estimates the …

… and difficult to predict the traffic crowd … spatio-temporal neural network to simultaneously
predict the traffic flows at every region on the traffic network. It is a deep hybrid spatio-temporal …

… model has two components. First, we propose a spatio-temporal correlation network to model
… -temporal generative model (named, D-GAN) to predict spatio-temporal data accurately in …

… to jointly model spatial and … hybrid spatio-temporal neural network namely DHSTNet, to
predict traffic flows in every region of a city with high accuracy. In particular, our DSHTNet model …

… This paper will focus on the analysis of Spatiotemporal sequence prediction algorithms in
these two directions, hoping to help researchers who are new to these two directions quickly …