{"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/improving-lstm-based-video-description-with","title":"Improving LSTM-based Video Description with Linguistic Knowledge Mined from Text","arxiv_id":"1604.01729","date":"2016-04-06","proceeding":"EMNLP 2016 11","authors":["Subhashini Venugopalan","Lisa Anne Hendricks","Raymond Mooney","Kate Saenko"],"abstract":"This paper investigates how linguistic knowledge mined from large text\ncorpora can aid the generation of natural language descriptions of videos.\nSpecifically, we integrate both a neural language model and distributional\nsemantics trained on large text corpora into a recent LSTM-based architecture\nfor video description. We evaluate our approach on a collection of Youtube\nvideos as well as two large movie description datasets showing significant\nimprovements in grammaticality while modestly improving descriptive quality.","url_abs":"http://arxiv.org/abs/1604.01729v2","url_pdf":"http://arxiv.org/pdf/1604.01729v2.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":"improving-lstm-based-video-description-with","repo_url":"https://github.com/TejInaco/multimodalML","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"improving-lstm-based-video-description-with","repo_url":"https://github.com/beerzyp/ECAC-Bimodal_audiovisual_recognition","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"improving-lstm-based-video-description-with","repo_url":"https://github.com/beerzyp/ECAC-Chain-Fusion","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"descriptive","task_name":"Descriptive"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"video-description","task_name":"Video Description"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}