{"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/a-dataset-for-movie-description","title":"A Dataset for Movie Description","arxiv_id":"1501.02530","date":"2015-01-12","proceeding":"CVPR 2015 6","authors":["Anna Rohrbach","Marcus Rohrbach","Niket Tandon","Bernt Schiele"],"abstract":"Descriptive video service (DVS) provides linguistic descriptions of movies\nand allows visually impaired people to follow a movie along with their peers.\nSuch descriptions are by design mainly visual and thus naturally form an\ninteresting data source for computer vision and computational linguistics. In\nthis work we propose a novel dataset which contains transcribed DVS, which is\ntemporally aligned to full length HD movies. In addition we also collected the\naligned movie scripts which have been used in prior work and compare the two\ndifferent sources of descriptions. In total the Movie Description dataset\ncontains a parallel corpus of over 54,000 sentences and video snippets from 72\nHD movies. We characterize the dataset by benchmarking different approaches for\ngenerating video descriptions. Comparing DVS to scripts, we find that DVS is\nfar more visual and describes precisely what is shown rather than what should\nhappen according to the scripts created prior to movie production.","url_abs":"http://arxiv.org/abs/1501.02530v1","url_pdf":"http://arxiv.org/pdf/1501.02530v1.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":[],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"descriptive","task_name":"Descriptive"}],"methods":[],"datasets_introduced":[{"slug":"lsmdc","name":"LSMDC","full_name":"Large Scale Movie Description Challenge"}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1501.02530","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}