{"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/deep-multimodal-image-repurposing-detection","title":"Deep Multimodal Image-Repurposing Detection","arxiv_id":"1808.06686","date":"2018-08-20","proceeding":null,"authors":["Ekraam Sabir","Wael Abd-Almageed","Yue Wu","Prem Natarajan"],"abstract":"Nefarious actors on social media and other platforms often spread rumors and\nfalsehoods through images whose metadata (e.g., captions) have been modified to\nprovide visual substantiation of the rumor/falsehood. This type of modification\nis referred to as image repurposing, in which often an unmanipulated image is\npublished along with incorrect or manipulated metadata to serve the actor's\nulterior motives. We present the Multimodal Entity Image Repurposing (MEIR)\ndataset, a substantially challenging dataset over that which has been\npreviously available to support research into image repurposing detection. The\nnew dataset includes location, person, and organization manipulations on\nreal-world data sourced from Flickr. We also present a novel, end-to-end, deep\nmultimodal learning model for assessing the integrity of an image by combining\ninformation extracted from the image with related information from a knowledge\nbase. The proposed method is compared against state-of-the-art techniques on\nexisting datasets as well as MEIR, where it outperforms existing methods across\nthe board, with AUC improvement up to 0.23.","url_abs":"http://arxiv.org/abs/1808.06686v1","url_pdf":"http://arxiv.org/pdf/1808.06686v1.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":"deep-multimodal-image-repurposing-detection","repo_url":"https://github.com/Ekraam/MEIR","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[],"methods":[],"datasets_introduced":[{"slug":"meir","name":"MEIR","full_name":"Multimodal Entity Image Repurposing"}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1808.06686","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}