{"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/truly-multi-modal-youtube-8m-video","title":"Truly Multi-modal YouTube-8M Video Classification with Video, Audio, and Text","arxiv_id":"1706.05461","date":"2017-06-17","proceeding":null,"authors":["Zhe Wang","Kingsley Kuan","Mathieu Ravaut","Gaurav Manek","Sibo Song","Yuan Fang","Seokhwan Kim","Nancy Chen","Luis Fernando D'Haro","Luu Anh Tuan","Hongyuan Zhu","Zeng Zeng","Ngai Man Cheung","Georgios Piliouras","Jie Lin","Vijay Chandrasekhar"],"abstract":"The YouTube-8M video classification challenge requires teams to classify 0.7\nmillion videos into one or more of 4,716 classes. In this Kaggle competition,\nwe placed in the top 3% out of 650 participants using released video and audio\nfeatures. Beyond that, we extend the original competition by including text\ninformation in the classification, making this a truly multi-modal approach\nwith vision, audio and text. The newly introduced text data is termed as\nYouTube-8M-Text. We present a classification framework for the joint use of\ntext, visual and audio features, and conduct an extensive set of experiments to\nquantify the benefit that this additional mode brings. The inclusion of text\nyields state-of-the-art results, e.g. 86.7% GAP on the YouTube-8M-Text\nvalidation dataset.","url_abs":"http://arxiv.org/abs/1706.05461v3","url_pdf":"http://arxiv.org/pdf/1706.05461v3.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":"truly-multi-modal-youtube-8m-video","repo_url":"https://github.com/hrx2010/YouTube8m-Text","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"video-classification","task_name":"Video Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}