{"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/style2vec-representation-learning-for-fashion","title":"Style2Vec: Representation Learning for Fashion Items from Style Sets","arxiv_id":"1708.04014","date":"2017-08-14","proceeding":null,"authors":["Hanbit Lee","Jinseok Seol","Sang-goo Lee"],"abstract":"With the rapid growth of online fashion market, demand for effective fashion\nrecommendation systems has never been greater. In fashion recommendation, the\nability to find items that goes well with a few other items based on style is\nmore important than picking a single item based on the user's entire purchase\nhistory. Since the same user may have purchased dress suits in one month and\ncasual denims in another, it is impossible to learn the latent style features\nof those items using only the user ratings. If we were able to represent the\nstyle features of fashion items in a reasonable way, we will be able to\nrecommend new items that conform to some small subset of pre-purchased items\nthat make up a coherent style set. We propose Style2Vec, a vector\nrepresentation model for fashion items. Based on the intuition of\ndistributional semantics used in word embeddings, Style2Vec learns the\nrepresentation of a fashion item using other items in matching outfits as\ncontext. Two different convolutional neural networks are trained to maximize\nthe probability of item co-occurrences. For evaluation, a fashion analogy test\nis conducted to show that the resulting representation connotes diverse fashion\nrelated semantics like shapes, colors, patterns and even latent styles. We also\nperform style classification using Style2Vec features and show that our method\noutperforms other baselines.","url_abs":"http://arxiv.org/abs/1708.04014v1","url_pdf":"http://arxiv.org/pdf/1708.04014v1.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":"style2vec-representation-learning-for-fashion","repo_url":"https://github.com/trhgu/awesome-fashion-contents","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"recommendation-systems","task_name":"Recommendation Systems"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"stochastic-optimization","task_name":"Stochastic Optimization"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1708.04014","atlas_url":"https://app.syntology.ai/?focus=1708.04014","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}