{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T16:22:44Z","timestamp":1775665364563,"version":"3.50.1"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/100007219","name":"Shanghai Natural Science Foundation","doi-asserted-by":"publisher","award":["21ZR1403000"],"award-info":[{"award-number":["21ZR1403000"]}],"id":[{"id":"10.13039\/100007219","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2023.3346933","type":"journal-article","created":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T20:13:53Z","timestamp":1703535233000},"page":"281-293","source":"Crossref","is-referenced-by-count":4,"title":["Text-Conditioned Outfit Recommendation With Hybrid Attention Layer"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4315-1867","authenticated-orcid":false,"given":"Xin","family":"Wang","sequence":"first","affiliation":[{"name":"College of Textiles, Donghua University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2056-7672","authenticated-orcid":false,"given":"Yueqi","family":"Zhong","sequence":"additional","affiliation":[{"name":"Key Laboratory of Textile Science and Technology, Ministry of Education, Shanghai, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583435"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-99736-6_3"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00337"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00359"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01047"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_24"},{"key":"ref7","article-title":"Coherent and controllable outfit generation","author":"Li","year":"2019","journal-title":"arXiv:1906.07273"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-23052-9"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557369"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2022.08.011"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123394"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2020.3024221"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2023.103434"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3125424"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240546"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401430"},{"key":"ref20","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","author":"Su","year":"2019","journal-title":"arXiv:1908.08530"},{"key":"ref21","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Lu"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01246"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1394-4"},{"key":"ref24","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/762"},{"key":"ref26","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref27","article-title":"MusicLM: Generating music from text","author":"Agostinelli","year":"2023","journal-title":"arXiv:2301.11325"},{"key":"ref28","article-title":"CogVideo: Large-scale pretraining for text-to-video generation via transformers","author":"Hong","year":"2022","journal-title":"arXiv:2205.15868"},{"key":"ref29","first-page":"4651","article-title":"Perceiver: General perception with iterative attention","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Jaegle"},{"key":"ref30","article-title":"Perceiver IO: A general architecture for structured inputs & outputs","author":"Jaegle","year":"2021","journal-title":"arXiv:2107.14795"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref32","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01290"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-019-0131-z"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3390\/bioengineering10101144"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2017.2723014"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102645"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107404"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10380310\/10373836.pdf?arnumber=10373836","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,24]],"date-time":"2024-01-24T04:00:31Z","timestamp":1706068831000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10373836\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3346933","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}