Corpus ID: 235683454

CityNet: A Multi-city Multi-modal Dataset for Smart City Applications

  title={CityNet: A Multi-city Multi-modal Dataset for Smart City Applications},
  author={Xu Geng and Yilun Jin and Zhengfei Zheng and Yu Yang and Yexin Li and Han Tian and Peibo Duan and Leye Wang and Jiannong Cao and Hai Yang and Qiang Yang and Kai Chen},
Data-driven approaches have been applied to many problems in urban computing. However, in the research community, such approaches are commonly studied under data from limited sources, and are thus unable to characterize the complexity of urban data coming from multiple entities and the correlations among them. Consequently, an inclusive and multifaceted dataset is necessary to facilitate more extensive studies on urban computing. In this paper, we present CityNet, a multimodal urban dataset… Expand

Figures and Tables from this paper


Learning from Multiple Cities: A Meta-Learning Approach for Spatial-Temporal Prediction
This paper is the first to leverage information from multiple cities to increase the stability of transfer and designs a spatial-temporal network with a meta-learning paradigm designed to utilize the long-period data from other cities via transfer learning. Expand
Transfer Knowledge between Cities
A FLexible multimOdal tRAnsfer Learning (FLORAL) method to transfer knowledge from a city where there exist sufficient multimodal data and labels, to this kind of cities to fully alleviate the two problems. Expand
Cross-City Transfer Learning for Deep Spatio-Temporal Prediction
Results show that RegionTrans can outperform the state-of-the-art fine-tuning deep spatio-temporal prediction models by reducing up to 10.7% prediction error. Expand
Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Prediction
A deep-learning-based approach to collectively forecast the inflow and outflow of crowds in each and every region of a city, using the residual neural network framework to model the temporal closeness, period, and trend properties of crowd traffic. Expand
Visual Exploration of Big Spatio-Temporal Urban Data: A Study of New York City Taxi Trips
A new model is proposed that allows users to visually query taxi trips and is able to express a wide range of spatio-temporal queries, and it is flexible in that not only can queries be composed but also different aggregations and visual representations can be applied, allowing users to explore and compare results. Expand
DNN-based prediction model for spatio-temporal data
A Deep-learning-based prediction model for Spatio-Temporal data (DeepST), which is comprised of two components: spatio-temporal and global, and built on a real-time crowd flow forecasting system called UrbanFlow1. Expand
AutoST: Efficient Neural Architecture Search for Spatio-Temporal Prediction
This paper designs a novel search space tailored for ST-domain which consists of two categories of components: optional convolution operations at each layer to automatically extract multi-range spatio-temporal dependencies and learnable skip connections among layers to dynamically fuse low- and high-level ST-features. Expand
Urban Computing: Concepts, Methodologies, and Applications
The concept of urban computing is introduced, discussing its general framework and key challenges from the perspective of computer sciences, and the typical technologies that are needed in urban computing are summarized into four folds. Expand
Spatiotemporal Multi-Graph Convolution Network for Ride-Hailing Demand Forecasting
The spatiotemporal multi-graph convolution network (ST-MGCN), a novel deep learning model for ride-hailing demand forecasting, is proposed which first encode the non-Euclidean pair-wise correlations among regions into multiple graphs and then explicitly model these correlations using multi- graph convolution. Expand
Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting
This paper proposes a novel deep learning framework, Spatio-Temporal Graph Convolutional Networks (STGCN), to tackle the time series prediction problem in traffic domain, and builds the model with complete convolutional structures, which enable much faster training speed with fewer parameters. Expand