{"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/how-to-read-paintings-semantic-art","title":"How to Read Paintings: Semantic Art Understanding with Multi-Modal Retrieval","arxiv_id":"1810.09617","date":"2018-10-23","proceeding":null,"authors":["Noa Garcia","George Vogiatzis"],"abstract":"Automatic art analysis has been mostly focused on classifying artworks into\ndifferent artistic styles. However, understanding an artistic representation\ninvolves more complex processes, such as identifying the elements in the scene\nor recognizing author influences. We present SemArt, a multi-modal dataset for\nsemantic art understanding. SemArt is a collection of fine-art painting images\nin which each image is associated to a number of attributes and a textual\nartistic comment, such as those that appear in art catalogues or museum\ncollections. To evaluate semantic art understanding, we envisage the Text2Art\nchallenge, a multi-modal retrieval task where relevant paintings are retrieved\naccording to an artistic text, and vice versa. We also propose several models\nfor encoding visual and textual artistic representations into a common semantic\nspace. Our best approach is able to find the correct image within the top 10\nranked images in the 45.5% of the test samples. Moreover, our models show\nremarkable levels of art understanding when compared against human evaluation.","url_abs":"http://arxiv.org/abs/1810.09617v1","url_pdf":"http://arxiv.org/pdf/1810.09617v1.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-analysis","task_name":"Art Analysis"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[{"slug":"semart","name":"SemArt","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1810.09617","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}