{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/108729"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/108729","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Coherent and controllable outfit generation","abstract":"People often select outfits with a theme in mind. One might dress for a tropical getaway or to look good at a cocktail party. Existing outfit generation methods use item-wise or outfit-item compatibility tests, and lack an effective method to enforce a global constraint like style or occasion. We describe the first outfit generation method that can produce an outfit consisting of compatible items that cohere to follow a theme specified by the user. Our method generates outfits whose items match a theme described by a query sentence. Our method uses text and image embeddings to represent fashion items. We learn a multimodal embedding where the image representation for an item is close to its text representation, and use this embedding to measure item-query coherence. We then use a discriminator to compute compatibility between fashion items. This strategy yields a compatibility prediction method that meets or exceeds the state of the art. Our generation method combines item-item compatibility and item-query coherence to construct an outfit whose items are (a) close to the query and (b) compatible with one another. Quantitative evaluation shows that the items in our outfits are tightly clustered compared to standard outfits. Furthermore, outfits produced by similar queries are close to one another, and outfits produced by very different queries are far apart. Qualitative evaluation shows that our method responds well to queries. A user study suggests that people understand the match between the queries and the outfits produced by our method.","abstract_html":"People often select outfits with a theme in mind. One might dress for a tropical getaway or to look good at a cocktail party. Existing outfit generation methods use item-wise or outfit-item compatibility tests, and lack an effective method to enforce a global constraint like style or occasion. We describe the first outfit generation method that can produce an outfit consisting of compatible items that cohere to follow a theme specified by the user. Our method generates outfits whose items match a theme described by a query sentence. Our method uses text and image embeddings to represent fashion items. We learn a multimodal embedding where the image representation for an item is close to its text representation, and use this embedding to measure item-query coherence. We then use a discriminator to compute compatibility between fashion items. This strategy yields a compatibility prediction method that meets or exceeds the state of the art. Our generation method combines item-item compatibility and item-query coherence to construct an outfit whose items are (a) close to the query and (b) compatible with one another. Quantitative evaluation shows that the items in our outfits are tightly clustered compared to standard outfits. Furthermore, outfits produced by similar queries are close to one another, and outfits produced by very different queries are far apart. Qualitative evaluation shows that our method responds well to queries. A user study suggests that people understand the match between the queries and the outfits produced by our method.","abstract_has_math":false,"creators":["Liu, Chen"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Electrical & Computer Engr","degree_department":null,"school":null,"contributors":["Forsyth, David"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2020,"date_issued":"2020-10-07T22:50:08Z","date_published":"2020-10-07T22:50:08Z","updated_at":"2026-07-22T22:24:48Z","subjects":["Computer Vision","Fashion Compatibility","Image Embedding","Outfit Generation"],"languages":["en"],"rights":["Copyright 2020 Chen Liu"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/108729","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Forsyth, David"]},{"key":"dc:creator","label":"Author","values":["Liu, Chen"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2020-10-07T22:50:08Z","2022-10-07T22:50:13Z","2020-07-22","2020-08"]},{"key":"dc:type","label":"Dc Type","values":["text","Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical & Computer Engr"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Computer Vision","Fashion Compatibility","Image Embedding","Outfit Generation"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2020 Chen Liu"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/108729"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["People often select outfits with a theme in mind. One might dress for a tropical getaway or to look good at a cocktail party. Existing outfit generation methods use item-wise or outfit-item compatibility tests, and lack an effective method to enforce a global constraint like style or occasion. We describe the first outfit generation method that can produce an outfit consisting of compatible items that cohere to follow a theme specified by the user. Our method generates outfits whose items match a theme described by a query sentence. Our method uses text and image embeddings to represent fashion items. We learn a multimodal embedding where the image representation for an item is close to its text representation, and use this embedding to measure item-query coherence. We then use a discriminator to compute compatibility between fashion items. This strategy yields a compatibility prediction method that meets or exceeds the state of the art. Our generation method combines item-item compatibility and item-query coherence to construct an outfit whose items are (a) close to the query and (b) compatible with one another. Quantitative evaluation shows that the items in our outfits are tightly clustered compared to standard outfits. Furthermore, outfits produced by similar queries are close to one another, and outfits produced by very different queries are far apart. Qualitative evaluation shows that our method responds well to queries. A user study suggests that people understand the match between the queries and the outfits produced by our method.","Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2022-08-01","The student, Chen Liu, accepted the attached license on 2020-07-22 at 12:52.","The student, Chen Liu, submitted this Thesis for approval on 2020-07-22 at 13:03.","This Thesis was approved for publication on 2020-07-22 at 16:03.","DSpace SAF Submission Ingestion Package generated from Vireo submission #15725 on 2020-10-02 at 15:52:16","Made available in DSpace on 2020-10-07T22:50:08Z (GMT). No. of bitstreams: 2 LIU-THESIS-2020.pdf: 16170212 bytes, checksum: 3eb346f5a3e0cea2846be822cca27eb5 (MD5) LICENSE.txt: 4205 bytes, checksum: fb70ca1456c1229c6154898f43678ad0 (MD5) Previous issue date: 2020-07-22","Embargo set by: Seth Robbins for item 116358 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"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Coherent and controllable outfit generation"]}]}],"canonical_facts":{"dc:contributor":["Forsyth, David"],"dc:creator":["Liu, Chen"],"dc:date":["2020-10-07T22:50:08Z","2022-10-07T22:50:13Z","2020-07-22","2020-08"],"dc:description":["People often select outfits with a theme in mind. One might dress for a tropical getaway or to look good at a cocktail party. Existing outfit generation methods use item-wise or outfit-item compatibility tests, and lack an effective method to enforce a global constraint like style or occasion. We describe the first outfit generation method that can produce an outfit consisting of compatible items that cohere to follow a theme specified by the user. Our method generates outfits whose items match a theme described by a query sentence. Our method uses text and image embeddings to represent fashion items. We learn a multimodal embedding where the image representation for an item is close to its text representation, and use this embedding to measure item-query coherence. We then use a discriminator to compute compatibility between fashion items. This strategy yields a compatibility prediction method that meets or exceeds the state of the art. Our generation method combines item-item compatibility and item-query coherence to construct an outfit whose items are (a) close to the query and (b) compatible with one another. Quantitative evaluation shows that the items in our outfits are tightly clustered compared to standard outfits. Furthermore, outfits produced by similar queries are close to one another, and outfits produced by very different queries are far apart. Qualitative evaluation shows that our method responds well to queries. A user study suggests that people understand the match between the queries and the outfits produced by our method.","Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2022-08-01","The student, Chen Liu, accepted the attached license on 2020-07-22 at 12:52.","The student, Chen Liu, submitted this Thesis for approval on 2020-07-22 at 13:03.","This Thesis was approved for publication on 2020-07-22 at 16:03.","DSpace SAF Submission Ingestion Package generated from Vireo submission #15725 on 2020-10-02 at 15:52:16","Made available in DSpace on 2020-10-07T22:50:08Z (GMT). No. of bitstreams: 2 LIU-THESIS-2020.pdf: 16170212 bytes, checksum: 3eb346f5a3e0cea2846be822cca27eb5 (MD5) LICENSE.txt: 4205 bytes, checksum: fb70ca1456c1229c6154898f43678ad0 (MD5) Previous issue date: 2020-07-22","Embargo set by: Seth Robbins for item 116358 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"],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/108729"],"dc:language":["en"],"dc:rights":["Copyright 2020 Chen Liu"],"dc:subject":["Computer Vision","Fashion Compatibility","Image Embedding","Outfit Generation"],"dc:title":["Coherent and controllable outfit generation"],"dc:type":["text","Thesis"],"thesis:degree_discipline":["Electrical & Computer Engr"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:24:48Z"}