{"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/good-news-everyone-context-driven-entity","title":"Good News, Everyone! Context driven entity-aware captioning for news images","arxiv_id":"1904.01475","date":"2019-04-02","proceeding":"CVPR 2019 6","authors":["Ali Furkan Biten","Lluis Gomez","Marçal Rusiñol","Dimosthenis Karatzas"],"abstract":"Current image captioning systems perform at a merely descriptive level,\nessentially enumerating the objects in the scene and their relations. Humans,\non the contrary, interpret images by integrating several sources of prior\nknowledge of the world. In this work, we aim to take a step closer to producing\ncaptions that offer a plausible interpretation of the scene, by integrating\nsuch contextual information into the captioning pipeline. For this we focus on\nthe captioning of images used to illustrate news articles. We propose a novel\ncaptioning method that is able to leverage contextual information provided by\nthe text of news articles associated with an image. Our model is able to\nselectively draw information from the article guided by visual cues, and to\ndynamically extend the output dictionary to out-of-vocabulary named entities\nthat appear in the context source. Furthermore we introduce `GoodNews', the\nlargest news image captioning dataset in the literature and demonstrate\nstate-of-the-art results.","url_abs":"http://arxiv.org/abs/1904.01475v1","url_pdf":"http://arxiv.org/pdf/1904.01475v1.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":"good-news-everyone-context-driven-entity","repo_url":"https://github.com/furkanbiten/GoodNews","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"articles","task_name":"Articles"},{"task_slug":"descriptive","task_name":"Descriptive"},{"task_slug":"image-captioning","task_name":"Image Captioning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.01475","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}