SCU-Counting: A large-scale benchmark dataset for multi-class object counting
Published in Transportation Research Part C: Emerging Technologies, 2024
This paper proposes a spatiotemporal deep learning framework for citywide short-term crash risk prediction across multiple temporal resolutions, integrating historical crash data, traffic dynamics, and point-of-interest information.
Recommended citation: Wei, X.-Y., Zhang, L., Ma, H.-Y., & Zhang, X.-F. (2024). SCU-Counting: A large-scale benchmark dataset for multi-class object counting. Journal or Conference Name.
Download Paper | Download Slides | Download Bibtex