{"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/complete-the-look-scene-based-complementary","title":"Complete the Look: Scene-based Complementary Product Recommendation","arxiv_id":"1812.01748","date":"2018-12-04","proceeding":"CVPR 2019 6","authors":["Wang-Cheng Kang","Eric Kim","Jure Leskovec","Charles Rosenberg","Julian McAuley"],"abstract":"Modeling fashion compatibility is challenging due to its complexity and\nsubjectivity. Existing work focuses on predicting compatibility between product\nimages (e.g. an image containing a t-shirt and an image containing a pair of\njeans). However, these approaches ignore real-world 'scene' images (e.g.\nselfies); such images are hard to deal with due to their complexity, clutter,\nvariations in lighting and pose (etc.) but on the other hand could potentially\nprovide key context (e.g. the user's body type, or the season) for making more\naccurate recommendations. In this work, we propose a new task called 'Complete\nthe Look', which seeks to recommend visually compatible products based on scene\nimages. We design an approach to extract training data for this task, and\npropose a novel way to learn the scene-product compatibility from fashion or\ninterior design images. Our approach measures compatibility both globally and\nlocally via CNNs and attention mechanisms. Extensive experiments show that our\nmethod achieves significant performance gains over alternative systems. Human\nevaluation and qualitative analysis are also conducted to further understand\nmodel behavior. We hope this work could lead to useful applications which link\nlarge corpora of real-world scenes with shoppable products.","url_abs":"http://arxiv.org/abs/1812.01748v2","url_pdf":"http://arxiv.org/pdf/1812.01748v2.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":"complete-the-look-scene-based-complementary","repo_url":"https://github.com/kang205/STL-Dataset","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"product-recommendation","task_name":"Product Recommendation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1812.01748","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}