{"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/m-vad-names-a-dataset-for-video-captioning","title":"M-VAD Names: a Dataset for Video Captioning with Naming","arxiv_id":"1903.01489","date":"2019-03-04","proceeding":null,"authors":["Stefano Pini","Marcella Cornia","Federico Bolelli","Lorenzo Baraldi","Rita Cucchiara"],"abstract":"Current movie captioning architectures are not capable of mentioning\ncharacters with their proper name, replacing them with a generic \"someone\" tag.\nThe lack of movie description datasets with characters' visual annotations\nsurely plays a relevant role in this shortage. Recently, we proposed to extend\nthe M-VAD dataset by introducing such information. In this paper, we present an\nimproved version of the dataset, namely M-VAD Names, and its semi-automatic\nannotation procedure. The resulting dataset contains 63k visual tracks and 34k\ntextual mentions, all associated with character identities. To showcase the\nfeatures of the dataset and quantify the complexity of the naming task, we\ninvestigate multimodal architectures to replace the \"someone\" tags with proper\ncharacter names in existing video captions. The evaluation is further extended\nby testing this application on videos outside of the M-VAD Names dataset.","url_abs":"http://arxiv.org/abs/1903.01489v1","url_pdf":"http://arxiv.org/pdf/1903.01489v1.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":"m-vad-names-a-dataset-for-video-captioning","repo_url":"https://github.com/aimagelab/mvad-names-dataset","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"tag","task_name":"TAG"},{"task_slug":"video-captioning","task_name":"Video Captioning"}],"methods":[],"datasets_introduced":[{"slug":"m-vad-names","name":"M-VAD Names","full_name":"M-VAD Names Dataset"}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1903.01489","atlas_url":"https://app.syntology.ai/?focus=1903.01489","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}