{"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/visual-storytelling","title":"Visual Storytelling","arxiv_id":"1604.03968","date":"2016-04-13","proceeding":"NAACL 2016 6","authors":["Ting-Hao","Huang","Francis Ferraro","Nasrin Mostafazadeh","Ishan Misra","Aishwarya Agrawal","Jacob Devlin","Ross Girshick","Xiaodong He","Pushmeet Kohli","Dhruv Batra","C. Lawrence Zitnick","Devi Parikh","Lucy Vanderwende","Michel Galley","Margaret Mitchell"],"abstract":"We introduce the first dataset for sequential vision-to-language, and explore\nhow this data may be used for the task of visual storytelling. The first\nrelease of this dataset, SIND v.1, includes 81,743 unique photos in 20,211\nsequences, aligned to both descriptive (caption) and story language. We\nestablish several strong baselines for the storytelling task, and motivate an\nautomatic metric to benchmark progress. Modelling concrete description as well\nas figurative and social language, as provided in this dataset and the\nstorytelling task, has the potential to move artificial intelligence from basic\nunderstandings of typical visual scenes towards more and more human-like\nunderstanding of grounded event structure and subjective expression.","url_abs":"http://arxiv.org/abs/1604.03968v1","url_pdf":"http://arxiv.org/pdf/1604.03968v1.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":"visual-storytelling","repo_url":"https://github.com/Pendulibrium/ai-visual-storytelling-seq2seq","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"descriptive","task_name":"Descriptive"},{"task_slug":"visual-storytelling","task_name":"Visual Storytelling"}],"methods":[],"datasets_introduced":[{"slug":"vist","name":"VIST","full_name":"Visual Storytelling"}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1604.03968","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}