Please use this identifier to cite or link to this item:
Title: Revisiting Convolutional Neural Networks for Urban Flow Analytics
Authors: Liang, Yuxuan 
Ouyang, Kun
Wang, Yiwei
David Samuel Rosenblum 
Keywords: Urban Computing
Crowd Flow
Convolutional Networks
Issue Date: 14-Sep-2020
Citation: Liang, Yuxuan, Ouyang, Kun, Wang, Yiwei, David Samuel Rosenblum (2020-09-14). Revisiting Convolutional Neural Networks for Urban Flow Analytics. 2020 European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD 2020). ScholarBank@NUS Repository.
Abstract: Citywide crowd flow prediction is of great importance to smart city efforts. It aims to model the crowd flow (e.g., inflow and outflow) of each region in a city based on historical observations. Nowadays, Convolutional Neural Networks (CNNs) have been widely adopted in raster-based crowd flow analytics by virtue of their capability in capturing spatial dependencies. After revisiting CNN-based methods for different analytics tasks, we expose two common critical drawbacks in the existing uses: 1) inefficiency in learning global spatial dependencies, and 2) overlooking latent region functions. To tackle these challenges, in this paper we present a novel framework entitled DeepLGR that can be easily generalized to address various citywide crowd flow analytics problems. This framework consists of three parts: 1) a local feature extraction module to learn representations for each region; 2) a global context module to extract global contextual priors and up sample them to generate the global features; and 3) a region-specific predictor based on tensor decomposition to provide customized predictions for each region, which is very parameter-efficient compared to previous methods. Extensive experiments on two typical crowd flow analytics tasks demonstrate the effectiveness, stability, and generality of our framework.
Source Title: 2020 European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD 2020)
Appears in Collections:Elements
Staff Publications

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
ecmlpkdd2020-preprint.pdfSubmitted version1.75 MBAdobe PDF



Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.