{"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/structure-preserving-transformers-for","title":"Structure-Preserving Transformers for Sequences of SPD Matrices","arxiv_id":"2309.07579","date":"2023-09-14","proceeding":null,"authors":["Mathieu Seraphim","Alexis Lechervy","Florian Yger","Luc Brun","Olivier Etard"],"abstract":"In recent years, Transformer-based auto-attention mechanisms have been successfully applied to the analysis of a variety of context-reliant data types, from texts to images and beyond, including data from non-Euclidean geometries. In this paper, we present such a mechanism, designed to classify sequences of Symmetric Positive Definite matrices while preserving their Riemannian geometry throughout the analysis. We apply our method to automatic sleep staging on timeseries of EEG-derived covariance matrices from a standard dataset, obtaining high levels of stage-wise performance.","url_abs":"https://arxiv.org/abs/2309.07579v7","url_pdf":"https://arxiv.org/pdf/2309.07579v7.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":"structure-preserving-transformers-for","repo_url":"https://github.com/mathieuseraphim/spdtransnet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"structure-preserving-transformers-for","repo_url":"https://github.com/MathieuSeraphim/SPDTransNet_plus","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"eeg-1","task_name":"EEG"},{"task_slug":"eeg-based-sleep-staging","task_name":"EEG based sleep staging"},{"task_slug":"sleep-stage-detection","task_name":"Sleep Stage Detection"},{"task_slug":"sleep-staging","task_name":"Sleep Staging"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/sleep-stage-detection-on-mass-ss3","task":"Sleep Stage Detection","dataset":"MASS SS3","model":"SPDTransNet","rank_in_archive_order":6,"of":6,"metrics":{"Macro-F1":"0.8124","Macro-averaged Accuracy":"84.40%"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}