Smart City Gnosys

Smart city article details

Title	Urbanmc: Masking And Contrastive Self-Supervision For Fine-Grained Urban Flows Inference
ID_Doc	60301
Authors	Zhang D.; Chen L.; Zhang L.
Year	2024
Published	ACM International Conference Proceeding Series
DOI	http://dx.doi.org/10.1145/3695719.3695722
Abstract	Similar to the super-resolution problem in traditional images, fine-grained urban flow inference(FUFI) aims to predict fine-grained urban flows from observed coarse-grained data. This task is crucial in various domains, such as smart cities and intelligent transportation systems. Therefore, we propose a self-supervised learning method in which attention-based and CNN-based encoders are trained through mask-enhanced learning and contrastive learning, respectively, in the course of the pre-training stage. These pre-trained encoders are supposed to capture temporal and spatial relationships within the input data. Afterward, in the fine-tuning stage, we combine the pre-trained encoders to forecast fine-grained urban flows. Finally, we conduct experiments to compare our model with other methods, including the FUFI approaches and single image super-resolution reconstruction(SISR) approaches. The experimental results demonstrate that our model is more effective than other methods when applied to real-world datasets. © 2024 Copyright held by the owner/author(s).
Author Keywords	Contrastive learning; Fine-grained urban flow inference; Mask-enhanced learning; Self-supervision; Spatio-temporal learning

Similar Articles

Id	Similarity	Authors	Title	Published
52510	0.937	Xu X.; Wang Z.; Gao Q.; Zhong T.; Hui B.; Zhou F.; Trajcevski G.	Spatial-Temporal Contrasting For Fine-Grained Urban Flow Inference	IEEE Transactions on Big Data, 9, 6 (2023)
26539	0.907	Yu H.; Xu X.; Zhong T.; Zhou F.	Fine-Grained Urban Flow Inference Via Normalizing Flow (Student Abstract)	Proceedings of the 36th AAAI Conference on Artificial Intelligence, AAAI 2022, 36 (2022)
26540	0.897	Li J.; Wang S.; Zhang J.; Miao H.; Zhang J.; Yu P.S.	Fine-Grained Urban Flow Inference With Incomplete Data	IEEE Transactions on Knowledge and Data Engineering, 35, 6 (2023)
26538	0.89	Ouyang K.; Liang Y.; Liu Y.; Tong Z.; Ruan S.; Zheng Y.; Rosenblum D.S.	Fine-Grained Urban Flow Inference	IEEE Transactions on Knowledge and Data Engineering, 34, 6 (2022)
29131	0.886	Xu Z.; Kang Y.; Cao Y.	High-Resolution Urban Flows Forecasting With Coarse-Grained Spatiotemporal Data	IEEE Transactions on Artificial Intelligence, 4, 2 (2023)
60279	0.879	Liang Y.; Ouyang K.; Jing L.; Ruan S.; Liu Y.; Zhang J.; Rosenblum D.S.; Zheng Y.	Urbanfm: Inferring Fine-Grained Urban Flows	Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2019)
26541	0.878	Liang Y.; Ouyang K.; Sun J.; Wang Y.; Zhang J.; Zheng Y.; Rosenblum D.; Zimmermann R.	Fine-Grained Urban Flow Prediction	The Web Conference 2021 - Proceedings of the World Wide Web Conference, WWW 2021 (2021)
19922	0.878	Zheng Y.; Zhong L.; Wang S.; Yang Y.; Gu W.; Zhang J.; Wang J.	Diffuflow: Robust Fine-Grained Urban Flow Inference With Denoising Diffusion Model	International Conference on Information and Knowledge Management, Proceedings (2023)
26432	0.877	Zheng Y.; Cai Y.; Cai Z.; Fan C.; Wang S.; Wang J.	Fgitrans: Cross-City Transformer For Fine-Grained Urban Flow Inference	International Conference on Information and Knowledge Management, Proceedings (2024)
6377	0.873	Zheng Y.; Wu J.; Cai Z.; Wang S.; Wang J.	Adatm: Fine-Grained Urban Flow Inference With Adaptive Knowledge Transfer Across Multiple Cities	International Conference on Information and Knowledge Management, Proceedings (2024)