{"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/personalized-saliency-and-its-prediction","title":"Personalized Saliency and its Prediction","arxiv_id":"1710.03011","date":"2017-10-09","proceeding":null,"authors":["Yanyu Xu","Shenghua Gao","Junru Wu","Nianyi Li","Jingyi Yu"],"abstract":"Nearly all existing visual saliency models by far have focused on predicting\na universal saliency map across all observers. Yet psychology studies suggest\nthat visual attention of different observers can vary significantly under\nspecific circumstances, especially a scene is composed of multiple salient\nobjects. To study such heterogenous visual attention pattern across observers,\nwe first construct a personalized saliency dataset and explore correlations\nbetween visual attention, personal preferences, and image contents.\nSpecifically, we propose to decompose a personalized saliency map (referred to\nas PSM) into a universal saliency map (referred to as USM) predictable by\nexisting saliency detection models and a new discrepancy map across users that\ncharacterizes personalized saliency. We then present two solutions towards\npredicting such discrepancy maps, i.e., a multi-task convolutional neural\nnetwork (CNN) framework and an extended CNN with Person-specific Information\nEncoded Filters (CNN-PIEF). Extensive experimental results demonstrate the\neffectiveness of our models for PSM prediction as well their generalization\ncapability for unseen observers.","url_abs":"http://arxiv.org/abs/1710.03011v2","url_pdf":"http://arxiv.org/pdf/1710.03011v2.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":"personalized-saliency-and-its-prediction","repo_url":"https://github.com/xuyanyu-shh/Personalized-Saliency","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"saliency-detection","task_name":"Saliency Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1710.03011","atlas_url":"https://app.syntology.ai/?focus=1710.03011","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}