2026-09-21T17:42:27Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/108720 2023-07-11 col_2142_5131 col_2142_10761 com_2142_5130 com_2142_10755 com_2142_234

2020-10-07T22:50:04Z Forsyth, David A Forsyth, David A Hoiem, Derek Schwing, Alexander Berg, Tamara L Vasileva, Mariya Ivanova 2020-10-07T22:50:04Z 2022-10-07T22:50:13Z 2020-07-22 2020-08 Many computer vision applications in the fashion domain require solving tasks where complex relationships between images, such as the notion of item compatibility, are being learned. We take a metric learning approach to representing compatibility between pairs of items. First, we introduce a model that learns compatibility relationships in dedicated embedding subspaces dependent on item type, which results in significant gains on established fashion compatibility prediction tasks. Second, we present a method for learning a richer notion of compatibility across multiple compatibility conditions whose contributions are learned as a latent variable, which provides better performance on established tasks while requiring fewer embedding subspaces to be learned. Third, we make the first published attempt at diagnosing the salient features of a pair of items that make them compatible, and linking them to human-interpretable concepts. Finally, we demonstrate that our representation of outfits enables diverse, novel, and practically-useful visual search queries for the fashion domain, and results in semantically-meaningful style summaries with several directions for future work. Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2022-08-01 The student, Mariya Vasileva, accepted the attached license on 2020-07-17 at 16:21. The student, Mariya Vasileva, submitted this Dissertation for approval on 2020-07-17 at 16:57. This Dissertation was approved for publication on 2020-07-22 at 16:02. DSpace SAF Submission Ingestion Package generated from Vireo submission #15686 on 2020-10-02 at 15:51:30 Made available in DSpace on 2020-10-07T22:50:04Z (GMT). No. of bitstreams: 2 VASILEVA-DISSERTATION-2020.pdf: 99966586 bytes, checksum: cc64cfc74eaf7ef959e65f68e6bcd298 (MD5) LICENSE.txt: 4212 bytes, checksum: 85c3a1a0b4ade05054da9d9c0d3c7e19 (MD5) Previous issue date: 2020-07-22 Embargo set by: Seth Robbins for item 116349 Lift date: 2022-10-07T22:50:13Z Reason: Author requested closed access (OA after 2yrs) in Vireo ETD system Author requested closed access (OA after 2yrs) in Vireo ETD system Limited application/pdf http://hdl.handle.net/2142/108720 en Copyright 2020 Mariya I. Vasileva Computer vision machine learning applications explainability embedding models vision and language image search and retrieval style summarization fashion compatibility Understanding the rich world of outfits: a study of fashion compatibility, latent style, and outfit behavior text Thesis Computer Science Computer Science University of Illinois at Urbana-Champaign Dissertation Ph.D.