{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T21:25:17Z","timestamp":1776115517850,"version":"3.50.1"},"reference-count":53,"publisher":"Association for Computing Machinery (ACM)","issue":"3","license":[{"start":{"date-parts":[[2024,8,22]],"date-time":"2024-08-22T00:00:00Z","timestamp":1724284800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Proc. ACM Interact. Mob. Wearable Ubiquitous Technol."],"published-print":{"date-parts":[[2024,8,22]]},"abstract":"<jats:p>Advances in mmWave-based sensing have enabled a privacy-friendly approach to pose and gesture recognition. Yet, providing robustness with the sparsity of reflected signals has been a long-standing challenge towards its practical deployment, constraining subjects to often face the radar. We present RF-HAC- a first-of-its-kind system that brings robust, automated and real-time human activity cataloging to practice by not only classifying exercises performed by subjects in their natural environments and poses, but also tracking the corresponding number of exercise repetitions. RF-HAC's unique approach (i) brings the diversity of multiple radars to scalably train a novel, self-supervised, pose-agnostic transformer-based exercise classifier directly on 3D RF point clouds with minimal manual effort and be deployed on a single radar; and (ii) leverages the underlying doppler behavior of exercises to design a robust self-similarity based segmentation algorithm for counting the repetitions in unstructured RF point clouds. Evaluations on a comprehensive set of challenging exercises in both seen and unseen environments\/subjects highlight RF-HAC's robustness with high accuracy (over 90%) and readiness for real-time, practical deployments over prior art.<\/jats:p>","DOI":"10.1145\/3678512","type":"journal-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T14:36:21Z","timestamp":1725892581000},"page":"1-23","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["View-agnostic Human Exercise Cataloging with Single MmWave Radar"],"prefix":"10.1145","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8021-8207","authenticated-orcid":false,"given":"Alan","family":"Liu","sequence":"first","affiliation":[{"name":"Georgia Institute of Technology, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0564-8618","authenticated-orcid":false,"given":"Yu-Tai","family":"Lin","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8089-4264","authenticated-orcid":false,"given":"Karthikeyan","family":"Sundaresan","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology, USA"}]}],"member":"320","published-online":{"date-parts":[[2024,9,9]]},"reference":[{"key":"e_1_2_2_1_1","unstructured":"[n. d.]. Intel\u00ae NUC 11 Enthusiast Mini PC - NUC11PHKi7CAA. https:\/\/www.intel.com\/content\/www\/us\/en\/products\/sku\/195961\/intel-nuc-11-enthusiast-mini-pc-nuc11phki7caa\/specifications.html."},{"key":"e_1_2_2_2_1","unstructured":"[n. d.]. Linux cgroups. https:\/\/man7.org\/linux\/man-pages\/man7\/cgroups.7.html."},{"key":"e_1_2_2_3_1","unstructured":"[n. d.]. Review: Amazon Halo Rise. https:\/\/www.wired.com\/review\/amazon-halo-rise\/."},{"key":"e_1_2_2_4_1","unstructured":"[n. d.]. RF-HAC datasets and code. https:\/\/bit.ly\/493DXQw."},{"key":"e_1_2_2_5_1","unstructured":"[n.d.]. RF-HAC github. https:\/\/github.com\/Ohesachite\/radar-nn-model."},{"key":"e_1_2_2_6_1","unstructured":"[n. d.]. TI 3x4 radar chips. https:\/\/www.ti.com\/product\/AWR6843?utm_source=google&utm_medium=cpc&utm_campaign=epd-null-null-GPN_EN-cpc-pf-google-wwe&utm_content=AWR6843&ds_k=AWR6843&DCM=yes&gclid=CjwKCAjwoqGnBhAcEiwAwK-OkdCizqhgLwaVF_urOlSGw9HlM3UdDdlVbRSW7tEIcjmomfrNwm3xOBoCK4oQAvD_BwE&gclsrc=aw.ds."},{"key":"e_1_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3550300"},{"key":"e_1_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/RADAR.2018.8378778"},{"key":"e_1_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.3390\/s22155470"},{"key":"e_1_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477030"},{"key":"e_1_2_2_11_1","volume-title":"Proc. of the 11th Mediterranean Conf. on Control and Automation","volume":"1","author":"Bodor Robert","year":"2003","unstructured":"Robert Bodor, Bennett Jackson, and Nikolaos Papanikolopoulos. 2003. Vision-based human tracking and activity recognition. In Proc. of the 11th Mediterranean Conf. on Control and Automation, Vol. 1. Citeseer, 1--6."},{"key":"e_1_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3372224.3419184"},{"key":"e_1_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107561"},{"key":"e_1_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3210240.3210345"},{"key":"e_1_2_2_15_1","volume-title":"Adaptive Subgradient Methods for Online Learning and Stochastic Optimization. 12, null (jul","author":"Duchi John","year":"2011","unstructured":"John Duchi, Elad Hazan, and Yoram Singer. 2011. Adaptive Subgradient Methods for Online Learning and Stochastic Optimization. 12, null (jul 2011), 2121--2159."},{"key":"e_1_2_2_16_1","volume-title":"Counting Out Time: Class Agnostic Video Repetition Counting in the Wild. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Dwibedi Debidatta","year":"2020","unstructured":"Debidatta Dwibedi, Yusuf Aytar, Jonathan Tompson, Pierre Sermanet, and Andrew Zisserman. 2020. Counting Out Time: Class Agnostic Video Repetition Counting in the Wild. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.5555\/3001460.3001507"},{"key":"e_1_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01398"},{"key":"e_1_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3349624.3356765"},{"key":"e_1_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01148"},{"key":"e_1_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3372224.3419982"},{"key":"e_1_2_2_22_1","unstructured":"Dan Hendrycks and Kevin Gimpel. 2023. Gaussian Error Linear Units (GELUs). arXiv:1606.08415 [cs.LG]"},{"key":"e_1_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3517246"},{"key":"e_1_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.2197\/ipsjjip.30.66"},{"key":"e_1_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3498361.3538926"},{"key":"e_1_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00977785"},{"key":"e_1_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.346"},{"key":"e_1_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP40000.2020.00004"},{"key":"e_1_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/18.61115"},{"key":"e_1_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3517231"},{"key":"e_1_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3631433"},{"key":"e_1_2_2_32_1","volume-title":"Human physical activity recognition based on computer vision with deep learning model. In 2016 IEEE international instrumentation and measurement technology conference proceedings","author":"Mo Lingfei","unstructured":"Lingfei Mo, Fan Li, Yanjia Zhu, and Anjie Huang. 2016. Human physical activity recognition based on computer vision with deep learning model. In 2016 IEEE international instrumentation and measurement technology conference proceedings. IEEE, 1--6."},{"key":"e_1_2_2_33_1","first-page":"516","article-title":"Vision-based body tracking: turning Kinect into a clinical tool","volume":"11","author":"Morrison Cecily","year":"2016","unstructured":"Cecily Morrison, Peter Culmer, Helena Mentis, and Tamar Pincus. 2016. Vision-based body tracking: turning Kinect into a clinical tool. Disability and Rehabilitation: Assistive Technology 11, 6 (2016), 516--520.","journal-title":"Disability and Rehabilitation: Assistive Technology"},{"key":"e_1_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"e_1_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3153717"},{"key":"e_1_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00387"},{"key":"e_1_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3349624.3356768"},{"key":"e_1_2_2_38_1","volume-title":"MilliFit: Millimeter-Wave Wireless Sensing Based At-Home Exercise Classification. In 2022 18th International Conference on Mobility, Sensing and Networking (MSN). IEEE, 150--154","author":"Sitar Edward M","year":"2022","unstructured":"Edward M Sitar and Sanjib Sur. 2022. MilliFit: Millimeter-Wave Wireless Sensing Based At-Home Exercise Classification. In 2022 18th International Conference on Mobility, Sensing and Networking (MSN). IEEE, 150--154."},{"key":"e_1_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447993.3448627"},{"key":"e_1_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2021.3077511"},{"key":"e_1_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3495243.3560543"},{"key":"e_1_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414686"},{"key":"e_1_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.3390\/s20102999"},{"key":"e_1_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2021.3111600"},{"key":"e_1_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00018"},{"key":"e_1_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCN54977.2022.9868878"},{"key":"e_1_2_2_47_1","volume-title":"tinyRadar for Fitness: A Contactless Framework for Edge Computing","author":"Yadav Satyapreet Singh","year":"2023","unstructured":"Satyapreet Singh Yadav, Radha Agarwal, Kola Bharath, Sandeep Rao, and Chetan Singh Thakur. 2023. tinyRadar for Fitness: A Contactless Framework for Edge Computing. IEEE Transactions on Biomedical Circuits and Systems (2023)."},{"key":"e_1_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM48099.2022.10000673"},{"key":"e_1_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/2942358.2942381"},{"key":"e_1_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSYST.2022.3140546"},{"key":"e_1_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00075"},{"key":"e_1_2_2_52_1","doi-asserted-by":"crossref","unstructured":"Long Zhao Yuxiao Wang Jiaping Zhao Liangzhe Yuan Jennifer J. Sun Florian Schroff Hartwig Adam Xi Peng Dimitris Metaxas and Ting Liu. 2021. Learning View-Disentangled Human Pose Representation by Contrastive Cross-View Mutual Information Maximization. arXiv:2012.01405 [cs.CV]","DOI":"10.1109\/CVPR46437.2021.01260"},{"key":"e_1_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/SPSympo51155.2020.9593799"}],"container-title":["Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3678512","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3678512","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T14:44:35Z","timestamp":1755787475000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3678512"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,22]]},"references-count":53,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,8,22]]}},"alternative-id":["10.1145\/3678512"],"URL":"https:\/\/doi.org\/10.1145\/3678512","relation":{},"ISSN":["2474-9567"],"issn-type":[{"value":"2474-9567","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,22]]},"assertion":[{"value":"2024-09-09","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}