{"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/context-aware-visual-compatibility-prediction","title":"Context-Aware Visual Compatibility Prediction","arxiv_id":"1902.03646","date":"2019-02-10","proceeding":"CVPR 2019 6","authors":["Guillem Cucurull","Perouz Taslakian","David Vazquez"],"abstract":"How do we determine whether two or more clothing items are compatible or\nvisually appealing? Part of the answer lies in understanding of visual\naesthetics, and is biased by personal preferences shaped by social attitudes,\ntime, and place. In this work we propose a method that predicts compatibility\nbetween two items based on their visual features, as well as their context. We\ndefine context as the products that are known to be compatible with each of\nthese item. Our model is in contrast to other metric learning approaches that\nrely on pairwise comparisons between item features alone. We address the\ncompatibility prediction problem using a graph neural network that learns to\ngenerate product embeddings conditioned on their context. We present results\nfor two prediction tasks (fill in the blank and outfit compatibility) tested on\ntwo fashion datasets Polyvore and Fashion-Gen, and on a subset of the Amazon\ndataset; we achieve state of the art results when using context information and\nshow how test performance improves as more context is used.","url_abs":"http://arxiv.org/abs/1902.03646v2","url_pdf":"http://arxiv.org/pdf/1902.03646v2.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":"context-aware-visual-compatibility-prediction","repo_url":"https://github.com/gcucurull/visual-compatibility","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"graph-neural-network","task_name":"Graph Neural Network"},{"task_slug":"metric-learning","task_name":"Metric Learning"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"recommendation-systems","task_name":"Recommendation Systems"},{"task_slug":"slot-filling","task_name":"Slot Filling"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gcn","method_name":"GCN"},{"method_slug":"graph-neural-network","method_name":"Graph Neural Network"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/recommendation-systems-on-polyvore","task":"Recommendation Systems","dataset":"Polyvore","model":"Fashion GAE","rank_in_archive_order":1,"of":3,"metrics":{"AUC":"0.99"},"uses_additional_data":false},{"leaderboard":"/sota/slot-filling-on-polyvore","task":"Slot Filling","dataset":"Polyvore","model":"Fashion GAE","rank_in_archive_order":1,"of":1,"metrics":{"FITB":"96.9"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1902.03646","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}