{"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/recognizing-image-style","title":"Recognizing Image Style","arxiv_id":"1311.3715","date":"2013-11-15","proceeding":null,"authors":["Sergey Karayev","Matthew Trentacoste","Helen Han","Aseem Agarwala","Trevor Darrell","Aaron Hertzmann","Holger Winnemoeller"],"abstract":"The style of an image plays a significant role in how it is viewed, but style\nhas received little attention in computer vision research. We describe an\napproach to predicting style of images, and perform a thorough evaluation of\ndifferent image features for these tasks. We find that features learned in a\nmulti-layer network generally perform best -- even when trained with object\nclass (not style) labels. Our large-scale learning methods results in the best\npublished performance on an existing dataset of aesthetic ratings and\nphotographic style annotations. We present two novel datasets: 80K Flickr\nphotographs annotated with 20 curated style labels, and 85K paintings annotated\nwith 25 style/genre labels. Our approach shows excellent classification\nperformance on both datasets. We use the learned classifiers to extend\ntraditional tag-based image search to consider stylistic constraints, and\ndemonstrate cross-dataset understanding of style.","url_abs":"http://arxiv.org/abs/1311.3715v3","url_pdf":"http://arxiv.org/pdf/1311.3715v3.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":"recognizing-image-style","repo_url":"https://github.com/jppgks/style-transfer-papers","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"tag","task_name":"TAG"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1311.3715","atlas_url":"https://app.syntology.ai/?focus=1311.3715","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}