{"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/video-description-using-bidirectional","title":"Video Description using Bidirectional Recurrent Neural Networks","arxiv_id":"1604.03390","date":"2016-04-12","proceeding":null,"authors":["Álvaro Peris","Marc Bolaños","Petia Radeva","Francisco Casacuberta"],"abstract":"Although traditionally used in the machine translation field, the\nencoder-decoder framework has been recently applied for the generation of video\nand image descriptions. The combination of Convolutional and Recurrent Neural\nNetworks in these models has proven to outperform the previous state of the\nart, obtaining more accurate video descriptions. In this work we propose\npushing further this model by introducing two contributions into the encoding\nstage. First, producing richer image representations by combining object and\nlocation information from Convolutional Neural Networks and second, introducing\nBidirectional Recurrent Neural Networks for capturing both forward and backward\ntemporal relationships in the input frames.","url_abs":"http://arxiv.org/abs/1604.03390v2","url_pdf":"http://arxiv.org/pdf/1604.03390v2.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":"video-description-using-bidirectional","repo_url":"https://github.com/lvapeab/ABiViRNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"text-generation","task_name":"Text Generation"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"video-captioning","task_name":"Video Captioning"},{"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}