Urban-ImageNet is a 2-million-image multi-modal dataset with HUSIC 10-class taxonomy enabling benchmarks for urban scene classification, cross-modal retrieval, and instance segmentation.
Macmillan, New York
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
A new framework recasts urban scene explainability as a bounded search over structured visual levers and prompt-based counterfactual edits, with a pilot on 50 scenes identifying mobility and maintenance changes as high-impact for safety perception.
citing papers explorer
-
Urban-ImageNet: A Large-Scale Multi-Modal Dataset and Evaluation Framework for Urban Space Perception
Urban-ImageNet is a 2-million-image multi-modal dataset with HUSIC 10-class taxonomy enabling benchmarks for urban scene classification, cross-modal retrieval, and instance segmentation.
-
How Many Visual Levers Drive Urban Perception? Interventional Counterfactuals via Multiple Localised Edits
A new framework recasts urban scene explainability as a bounded search over structured visual levers and prompt-based counterfactual edits, with a pilot on 50 scenes identifying mobility and maintenance changes as high-impact for safety perception.