Please use this identifier to cite or link to this item: https://scholarbank.nus.edu.sg/handle/10635/192262
DC FieldValue
dc.titleHierarchical (multi-label) architectural image recognition and classification
dc.contributor.authorChen, J
dc.contributor.authorStouffs, R
dc.contributor.authorBiljecki, F
dc.date.accessioned2021-06-28T09:28:33Z
dc.date.available2021-06-28T09:28:33Z
dc.date.issued2021-01-01
dc.identifier.citationChen, J, Stouffs, R, Biljecki, F (2021-01-01). Hierarchical (multi-label) architectural image recognition and classification 1 : 161-170. ScholarBank@NUS Repository.
dc.identifier.isbn9789887891758
dc.identifier.urihttps://scholarbank.nus.edu.sg/handle/10635/192262
dc.description.abstractThe task of architectural image recognition for both architectural functionality and style remains an open challenge. In addition, the paucity of well-organized, large-scale architectural image datasets with specific consideration for the domain of architectural design research has hindered the exploration of these challenging tasks. Drawing upon images from the professional architectural website Archdaily®, and leveraging state-of-the-art deep-learning-based classification models, we explore a hierarchical multi-label classification model as a potential baseline for the task of architectural image classification. The resulting model showcases the potential for innovative architectural discipline-related analyses and demonstrates some heuristic insights for visual feature extraction pertaining to both architectural functionality and architectural style.
dc.sourceElements
dc.typeConference Paper
dc.date.updated2021-06-26T04:16:10Z
dc.contributor.departmentARCHITECTURE
dc.description.volume1
dc.description.page161-170
dc.published.statePublished
Appears in Collections:Staff Publications
Elements

Show simple item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
caadria2021_039.pdfPublished version6.94 MBAdobe PDF

OPEN

PublishedView/Download

Google ScholarTM

Check

Altmetric


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