{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/outfit-generation-and-style-extraction-via","title":"Outfit Generation and Style Extraction via Bidirectional LSTM and Autoencoder","arxiv_id":"1807.03133","date":"2018-06-29","proceeding":null,"authors":["Takuma Nakamura","Ryosuke Goto"],"abstract":"When creating an outfit, style is a criterion in selecting each fashion item.\nThis means that style can be regarded as a feature of the overall outfit.\nHowever, in various previous studies on outfit generation, there have been few\nmethods focusing on global information obtained from an outfit. To address this\ndeficiency, we have incorporated an unsupervised style extraction module into a\nmodel to learn outfits. Using the style information of an outfit as a whole,\nthe proposed model succeeded in generating outfits more flexibly without\nrequiring additional information. Moreover, the style information extracted by\nthe proposed model is easy to interpret. The proposed model was evaluated on\ntwo human-generated outfit datasets. In a fashion item prediction task (missing\nprediction task), the proposed model outperformed a baseline method. In a style\nextraction task, the proposed model extracted some easily distinguishable\nstyles. In an outfit generation task, the proposed model generated an outfit\nwhile controlling its styles. This capability allows us to generate fashionable\noutfits according to various preferences.","url_abs":"http://arxiv.org/abs/1807.03133v3","url_pdf":"http://arxiv.org/pdf/1807.03133v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"outfit-generation-and-style-extraction-via","repo_url":"https://github.com/AemikaChow/DATASOURCE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}