{"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/gestsync-determining-who-is-speaking-without","title":"GestSync: Determining who is speaking without a talking head","arxiv_id":"2310.05304","date":"2023-10-08","proceeding":null,"authors":["Sindhu B Hegde","Andrew Zisserman"],"abstract":"In this paper we introduce a new synchronisation task, Gesture-Sync: determining if a person's gestures are correlated with their speech or not. In comparison to Lip-Sync, Gesture-Sync is far more challenging as there is a far looser relationship between the voice and body movement than there is between voice and lip motion. We introduce a dual-encoder model for this task, and compare a number of input representations including RGB frames, keypoint images, and keypoint vectors, assessing their performance and advantages. We show that the model can be trained using self-supervised learning alone, and evaluate its performance on the LRS3 dataset. Finally, we demonstrate applications of Gesture-Sync for audio-visual synchronisation, and in determining who is the speaker in a crowd, without seeing their faces. The code, datasets and pre-trained models can be found at: \\url{https://www.robots.ox.ac.uk/~vgg/research/gestsync}.","url_abs":"https://arxiv.org/abs/2310.05304v1","url_pdf":"https://arxiv.org/pdf/2310.05304v1.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":"gestsync-determining-who-is-speaking-without","repo_url":"https://github.com/Sindhu-Hegde/gestsync","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"active-speaker-detection","task_name":"Active Speaker Detection"},{"task_slug":"gesture-synchronization","task_name":"Gesture Synchronization"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/active-speaker-detection-on-lrs3-ted","task":"Active Speaker Detection","dataset":"LRS3-TED","model":"GestSync","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"87 %"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2310.05304","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}