{"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/a-spatio-temporal-multilayer-perceptron-for","title":"A Spatio-Temporal Multilayer Perceptron for Gesture Recognition","arxiv_id":"2204.11511","date":"2022-04-25","proceeding":null,"authors":["Adrian Holzbock","Alexander Tsaregorodtsev","Youssef Dawoud","Klaus Dietmayer","Vasileios Belagiannis"],"abstract":"Gesture recognition is essential for the interaction of autonomous vehicles with humans. While the current approaches focus on combining several modalities like image features, keypoints and bone vectors, we present neural network architecture that delivers state-of-the-art results only with body skeleton input data. We propose the spatio-temporal multilayer perceptron for gesture recognition in the context of autonomous vehicles. Given 3D body poses over time, we define temporal and spatial mixing operations to extract features in both domains. Additionally, the importance of each time step is re-weighted with Squeeze-and-Excitation layers. An extensive evaluation of the TCG and Drive&Act datasets is provided to showcase the promising performance of our approach. Furthermore, we deploy our model to our autonomous vehicle to show its real-time capability and stable execution.","url_abs":"https://arxiv.org/abs/2204.11511v2","url_pdf":"https://arxiv.org/pdf/2204.11511v2.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":"a-spatio-temporal-multilayer-perceptron-for","repo_url":"https://github.com/holzbock/st_mlp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"autonomous-vehicles","task_name":"Autonomous Vehicles"},{"task_slug":"gesture-recognition","task_name":"Gesture Recognition"},{"task_slug":"skeleton-based-action-recognition","task_name":"Skeleton Based Action Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/skeleton-based-action-recognition-on-drive","task":"Skeleton Based Action Recognition","dataset":"Drive&Act","model":"stMLP","rank_in_archive_order":2,"of":2,"metrics":{"mean per-class accuracy":"34.61"},"uses_additional_data":false},{"leaderboard":"/sota/skeleton-based-action-recognition-on-tcg","task":"Skeleton Based Action Recognition","dataset":"TCG-dataset","model":"stMLP","rank_in_archive_order":2,"of":2,"metrics":{"Acc":"85.99","F1-Score":"80.05","Jaccard Index":"67.88"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}