{"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/signal-level-deep-metric-learning-for","title":"SL-DML: Signal Level Deep Metric Learning for Multimodal One-Shot Action Recognition","arxiv_id":"2004.11085","date":"2020-04-23","proceeding":null,"authors":["Raphael Memmesheimer","Nick Theisen","Dietrich Paulus"],"abstract":"Recognizing an activity with a single reference sample using metric learning approaches is a promising research field. The majority of few-shot methods focus on object recognition or face-identification. We propose a metric learning approach to reduce the action recognition problem to a nearest neighbor search in embedding space. We encode signals into images and extract features using a deep residual CNN. Using triplet loss, we learn a feature embedding. The resulting encoder transforms features into an embedding space in which closer distances encode similar actions while higher distances encode different actions. Our approach is based on a signal level formulation and remains flexible across a variety of modalities. It further outperforms the baseline on the large scale NTU RGB+D 120 dataset for the One-Shot action recognition protocol by 5.6%. With just 60% of the training data, our approach still outperforms the baseline approach by 3.7%. With 40% of the training data, our approach performs comparably well to the second follow up. Further, we show that our approach generalizes well in experiments on the UTD-MHAD dataset for inertial, skeleton and fused data and the Simitate dataset for motion capturing data. Furthermore, our inter-joint and inter-sensor experiments suggest good capabilities on previously unseen setups.","url_abs":"https://arxiv.org/abs/2004.11085v4","url_pdf":"https://arxiv.org/pdf/2004.11085v4.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":"signal-level-deep-metric-learning-for","repo_url":"https://github.com/raphaelmemmesheimer/sl-dml","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"face-identification","task_name":"Face Identification"},{"task_slug":"metric-learning","task_name":"Metric Learning"},{"task_slug":"object-recognition","task_name":"Object Recognition"},{"task_slug":"one-shot-3d-action-recognition","task_name":"One-Shot 3D Action Recognition"},{"task_slug":null,"task_name":"Triplet"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/one-shot-3d-action-recognition-on-ntu-rgbd","task":"One-Shot 3D Action Recognition","dataset":"NTU RGB+D 120","model":"Deep Metric Learning (Triplet Loss, Signals)","rank_in_archive_order":5,"of":10,"metrics":{"Accuracy":"49.6%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2004.11085","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}