{"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/ups-and-downs-modeling-the-visual-evolution","title":"Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering","arxiv_id":"1602.01585","date":"2016-02-04","proceeding":null,"authors":["Ruining He","Julian McAuley"],"abstract":"Building a successful recommender system depends on understanding both the\ndimensions of people's preferences as well as their dynamics. In certain\ndomains, such as fashion, modeling such preferences can be incredibly\ndifficult, due to the need to simultaneously model the visual appearance of\nproducts as well as their evolution over time. The subtle semantics and\nnon-linear dynamics of fashion evolution raise unique challenges especially\nconsidering the sparsity and large scale of the underlying datasets. In this\npaper we build novel models for the One-Class Collaborative Filtering setting,\nwhere our goal is to estimate users' fashion-aware personalized ranking\nfunctions based on their past feedback. To uncover the complex and evolving\nvisual factors that people consider when evaluating products, our method\ncombines high-level visual features extracted from a deep convolutional neural\nnetwork, users' past feedback, as well as evolving trends within the community.\nExperimentally we evaluate our method on two large real-world datasets from\nAmazon.com, where we show it to outperform state-of-the-art personalized\nranking measures, and also use it to visualize the high-level fashion trends\nacross the 11-year span of our dataset.","url_abs":"http://arxiv.org/abs/1602.01585v1","url_pdf":"http://arxiv.org/pdf/1602.01585v1.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":[],"tasks":[{"task_slug":"collaborative-filtering","task_name":"Collaborative Filtering"},{"task_slug":"recommendation-systems","task_name":"Recommendation Systems"}],"methods":[],"datasets_introduced":[{"slug":"amazon-product-data","name":"Amazon Product Data","full_name":"rithik"}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1602.01585","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}