{"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-make-an-image-more-memorable-a-deep","title":"How to Make an Image More Memorable? A Deep Style Transfer Approach","arxiv_id":"1704.01745","date":"2017-04-06","proceeding":null,"authors":["Aliaksandr Siarohin","Gloria Zen","Cveta Majtanovic","Xavier Alameda-Pineda","Elisa Ricci","Nicu Sebe"],"abstract":"Recent works have shown that it is possible to automatically predict\nintrinsic image properties like memorability. In this paper, we take a step\nforward addressing the question: \"Can we make an image more memorable?\".\nMethods for automatically increasing image memorability would have an impact in\nmany application fields like education, gaming or advertising. Our work is\ninspired by the popular editing-by-applying-filters paradigm adopted in photo\nediting applications, like Instagram and Prisma. In this context, the problem\nof increasing image memorability maps to that of retrieving \"memorabilizing\"\nfilters or style \"seeds\". Still, users generally have to go through most of the\navailable filters before finding the desired solution, thus turning the editing\nprocess into a resource and time consuming task. In this work, we show that it\nis possible to automatically retrieve the best style seeds for a given image,\nthus remarkably reducing the number of human attempts needed to find a good\nmatch. Our approach leverages from recent advances in the field of image\nsynthesis and adopts a deep architecture for generating a memorable picture\nfrom a given input image and a style seed. Importantly, to automatically select\nthe best style a novel learning-based solution, also relying on deep models, is\nproposed. Our experimental evaluation, conducted on publicly available\nbenchmarks, demonstrates the effectiveness of the proposed approach for\ngenerating memorable images through automatic style seed selection","url_abs":"http://arxiv.org/abs/1704.01745v1","url_pdf":"http://arxiv.org/pdf/1704.01745v1.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":"how-to-make-an-image-more-memorable-a-deep","repo_url":"https://github.com/aliaksandrsiarohin/mem-transfer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":null}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"style-transfer","task_name":"Style Transfer"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}