{"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/single-shot-motion-completion-with","title":"Single-Shot Motion Completion with Transformer","arxiv_id":"2103.00776","date":"2021-03-01","proceeding":null,"authors":["Yinglin Duan","Tianyang Shi","Zhengxia Zou","Yenan Lin","Zhehui Qian","Bohan Zhang","Yi Yuan"],"abstract":"Motion completion is a challenging and long-discussed problem, which is of great significance in film and game applications. For different motion completion scenarios (in-betweening, in-filling, and blending), most previous methods deal with the completion problems with case-by-case designs. In this work, we propose a simple but effective method to solve multiple motion completion problems under a unified framework and achieves a new state of the art accuracy under multiple evaluation settings. Inspired by the recent great success of attention-based models, we consider the completion as a sequence to sequence prediction problem. Our method consists of two modules - a standard transformer encoder with self-attention that learns long-range dependencies of input motions, and a trainable mixture embedding module that models temporal information and discriminates key-frames. Our method can run in a non-autoregressive manner and predict multiple missing frames within a single forward propagation in real time. We finally show the effectiveness of our method in music-dance applications.","url_abs":"https://arxiv.org/abs/2103.00776v1","url_pdf":"https://arxiv.org/pdf/2103.00776v1.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":"single-shot-motion-completion-with","repo_url":"https://github.com/FuxiCV/SSMCT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"motion-synthesis","task_name":"Motion Synthesis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/motion-synthesis-on-lafan1","task":"Motion Synthesis","dataset":"LaFAN1","model":"SSMCT","rank_in_archive_order":2,"of":4,"metrics":{"L2P@15":"0.56","L2P@30":"1.1","L2P@5":"0.22","L2Q@15":"0.36","L2Q@30":"0.61","L2Q@5":"0.14","NPSS@15":"0.0234","NPSS@30":"0.1222","NPSS@5":"0.0016"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2103.00776","atlas_url":"https://app.syntology.ai/?focus=2103.00776","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}