{"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/omniart-multi-task-deep-learning-for-artistic","title":"OmniArt: Multi-task Deep Learning for Artistic Data Analysis","arxiv_id":"1708.00684","date":"2017-08-02","proceeding":null,"authors":["Gjorgji Strezoski","Marcel Worring"],"abstract":"Vast amounts of artistic data is scattered on-line from both museums and art\napplications. Collecting, processing and studying it with respect to all\naccompanying attributes is an expensive process. With a motivation to speed up\nand improve the quality of categorical analysis in the artistic domain, in this\npaper we propose an efficient and accurate method for multi-task learning with\na shared representation applied in the artistic domain. We continue to show how\ndifferent multi-task configurations of our method behave on artistic data and\noutperform handcrafted feature approaches as well as convolutional neural\nnetworks. In addition to the method and analysis, we propose a challenge like\nnature to the new aggregated data set with almost half a million samples and\nstructured meta-data to encourage further research and societal engagement.","url_abs":"http://arxiv.org/abs/1708.00684v1","url_pdf":"http://arxiv.org/pdf/1708.00684v1.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":"art-period-estimation-544-artists","task_name":"Art Period Estimation (544 Artists)"},{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"period-estimation","task_name":"Period Estimation"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[{"slug":"omniart","name":"OmniArt","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/period-estimation-on-omniart","task":"Period Estimation","dataset":"OmniArt","model":"OmniArt","rank_in_archive_order":1,"of":2,"metrics":{"Mean absolute error":"77.9"},"uses_additional_data":false},{"leaderboard":"/sota/period-estimation-on-omniart","task":"Period Estimation","dataset":"OmniArt","model":"ResNet-50","rank_in_archive_order":2,"of":2,"metrics":{"Mean absolute error":"79.3"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1708.00684","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}