{"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/changing-the-image-memorability-from-basic","title":"Changing the Image Memorability: From Basic Photo Editing to GANs","arxiv_id":"1811.03825","date":"2018-11-09","proceeding":null,"authors":["Oleksii Sidorov"],"abstract":"Memorability is considered to be an important characteristic of visual\ncontent, whereas for advertisement and educational purposes it is often\ncrucial. Despite numerous studies on understanding and predicting image\nmemorability, there are almost no achievements in memorability modification. In\nthis work, we study two approaches to image editing - GAN and classical image\nprocessing - and show their impact on memorability. The visual features which\ninfluence memorability directly stay unknown till now, hence it is impossible\nto control it manually. As a solution, we let GAN learn it deeply using labeled\ndata, and then use it for conditional generation of new images. By analogy with\nalgorithms which edit facial attributes, we consider memorability as yet\nanother attribute and operate with it in the same way. Obtained data is also\ninteresting for analysis, simply because there are no real-world examples of\nsuccessful change of image memorability while preserving its other attributes.\nWe believe this may give many new answers to the question \"what makes an image\nmemorable?\" Apart from that we also study the influence of conventional\nphoto-editing tools (Photoshop, Instagram, etc.) used daily by a wide audience\non memorability. In this case, we start from real practical methods and study\nit using statistics and recent advances in memorability prediction.\nPhotographers, designers, and advertisers will benefit from the results of this\nstudy directly.","url_abs":"http://arxiv.org/abs/1811.03825v4","url_pdf":"http://arxiv.org/pdf/1811.03825v4.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":"changing-the-image-memorability-from-basic","repo_url":"https://github.com/acecreamu/changing-the-memorability","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.03825","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}