{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T17:18:20Z","timestamp":1783012700435,"version":"3.54.6"},"reference-count":39,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T00:00:00Z","timestamp":1782691200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Proc. ACM Hum.-Comput. Interact."],"published-print":{"date-parts":[[2026,6,30]]},"abstract":"<jats:p>\n                    Wearable e-textile interfaces require gesture recognition capabilities but face severe constraints in power consumption, computational capacity, and form factor that make traditional deep learning impractical. While lightweight architectures like MobileNet improve efficiency, they still demand thousands of parameters, limiting deployment on textile-integrated platforms. We introduce a convexified attention mechanism for wearable applications that dynamically weights features while preserving convexity through nonexpansive simplex projection and convex loss functions. Unlike conventional attention mechanisms using non-convex softmax operations, our approach employs Euclidean projection onto the probability simplex combined with multi-class hinge loss, ensuring global convergence guarantees. Implemented on a textile-based capacitive sensor with four connection points, our approach achieves 100.00% accuracy on tap gestures and 100.00% on swipe gestures\u2014consistent across 10-fold cross-validation and held-out test evaluation\u2014while requiring only 120\u2013360 parameters, a 97% reduction compared to conventional approaches. With sub-millisecond inference times (290\u2013296\n                    <jats:italic toggle=\"yes\">\u03bc<\/jats:italic>\n                    s) and minimal storage requirements (&lt; 7KB), our method enables gesture interfaces directly within e-textiles without external processing. Our evaluation, conducted in controlled laboratory conditions with a single-user dataset, demonstrates feasibility for basic gesture interactions. Real-world deployment would require validation across multiple users, environmental conditions, and more complex gesture vocabularies. These results demonstrate how convex optimization can enable efficient on-device machine learning for textile interfaces.\n                  <\/jats:p>","DOI":"10.1145\/3815369","type":"journal-article","created":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T15:39:14Z","timestamp":1782747554000},"page":"1-25","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Resource-Efficient Gesture Recognition through Convexified Attention EICS006"],"prefix":"10.1145","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7301-2622","authenticated-orcid":false,"given":"Daniel","family":"Schwartz","sequence":"first","affiliation":[{"name":"College of Computing and Informatics","place":["Philadelphia, USA"]},{"name":"Drexel University","place":["Philadelphia, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8812-4996","authenticated-orcid":false,"given":"Dario","family":"Salvucci","sequence":"additional","affiliation":[{"name":"Department of Computer Science","place":["Philadelphia, USA"]},{"name":"Drexel University","place":["Philadelphia, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9997-9479","authenticated-orcid":false,"given":"Yusuf","family":"Osmanlioglu","sequence":"additional","affiliation":[{"name":"Drexel University","place":["Philadelphia, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7876-4137","authenticated-orcid":false,"given":"Richard","family":"Vallett","sequence":"additional","affiliation":[{"name":"Center for Functional Fabrics","place":["Philadelphia, USA"]},{"name":"Drexel University","place":["Philadelphia, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4873-288X","authenticated-orcid":false,"given":"Genevieve","family":"Dion","sequence":"additional","affiliation":[{"name":"Drexel University","place":["Philadelphia, USA"]},{"name":"Westphal College of Media Arts & Design","place":["Philadelphia, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3729-4490","authenticated-orcid":false,"given":"Ali","family":"Shokoufandeh","sequence":"additional","affiliation":[{"name":"Drexel University","place":["Philadelphia, USA"]},{"name":"College of Computing and Informatics","place":["Philadelphia, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,29]]},"reference":[{"key":"e_1_3_3_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330701"},{"key":"e_1_3_3_3_2","unstructured":"Colby Banbury Chuteng Zhou Igor Fedorov Ramon Matas Urmish Thakker Dibakar Gope Vijay Janapa\u00a0Reddi Matthew Mattina and Paul Whatmough. 2021. Micronets: Neural network architectures for deploying tinyml applications on commodity microcontrollers. Proceedings of machine learning and systems 3 (2021) 517\u2013532."},{"key":"e_1_3_3_4_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-9467-7"},{"key":"e_1_3_3_5_2","doi-asserted-by":"crossref","unstructured":"Mohammed\u00a0Wasim Bhatt and Sparsh Sharma. 2023. An IoMT-Based Approach for Real-Time Monitoring Using Wearable Neuro-Sensors. Journal of Healthcare Engineering 2023 1 (2023) 1066547.","DOI":"10.1155\/2023\/1066547"},{"key":"e_1_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"e_1_3_3_7_2","doi-asserted-by":"crossref","unstructured":"Yanjiao Chen Baolin Zheng Zihan Zhang Qian Wang Chao Shen and Qian Zhang. 2020. Deep learning on mobile and embedded devices: State-of-the-art challenges and future directions. ACM Computing Surveys (CSUR) 53 4 (2020) 1\u201337.","DOI":"10.1145\/3398209"},{"key":"e_1_3_3_8_2","unstructured":"Krzysztof Choromanski Valerii Likhosherstov David Dohan Xingyou Song Andreea Gane Tamas Sarlos Peter Hawkins Jared Davis Afroz Mohiuddin Lukasz Kaiser et\u00a0al. 2020. Rethinking attention with performers. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2009.14794 (2020)."},{"key":"e_1_3_3_9_2","unstructured":"Koby Crammer and Yoram Singer. 2001. On the Algorithmic Implementation of Multiclass Kernel-based Vector Machines. Journal of Machine Learning Research 2 (2001) 265\u2013292. https:\/\/www.jmlr.org\/papers\/v2\/crammer01a.html"},{"key":"e_1_3_3_10_2","doi-asserted-by":"crossref","unstructured":"Maur\u00edcio\u00a0Pasetto de Freitas Vin\u00edcius\u00a0Aquino Piai Ricardo\u00a0Heffel Farias Anita\u00a0MR Fernandes Anubis\u00a0Graciela de Moraes\u00a0Rossetto and Valderi Reis\u00a0Quietinho Leithardt. 2022. Artificial intelligence of things applied to assistive technology: a systematic literature review. Sensors 22 21 (2022) 8531.","DOI":"10.3390\/s22218531"},{"key":"e_1_3_3_11_2","unstructured":"Jacob Devlin. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1810.04805 (2018)."},{"key":"e_1_3_3_12_2","doi-asserted-by":"crossref","unstructured":"John Duchi Shai Shalev-Shwartz Yoram Singer and Tushar Chandra. 2008. Efficient projections onto the l1-ball for learning in high dimensions. Proceedings of the 25th international conference on Machine learning (2008) 272\u2013279.","DOI":"10.1145\/1390156.1390191"},{"key":"e_1_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.1201\/9781003162810-13"},{"key":"e_1_3_3_14_2","volume-title":"Matrix Analysis (2 ed.)","author":"Horn Roger\u00a0A.","year":"2013","unstructured":"Roger\u00a0A. Horn and Charles\u00a0R. Johnson. 2013. Matrix Analysis (2 ed.). Cambridge University Press."},{"key":"e_1_3_3_15_2","unstructured":"Andrew\u00a0G Howard Menglong Zhu Bo Chen Dmitry Kalenichenko Weijun Wang Tobias Weyand Marco Andreetto and Hartwig Adam. 2017. Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1704.04861 (2017)."},{"key":"e_1_3_3_16_2","unstructured":"Forrest\u00a0N Iandola. 2016. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and< 0.5 MB model size. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1602.07360 (2016)."},{"key":"e_1_3_3_17_2","first-page":"5156","volume-title":"International conference on machine learning","author":"Katharopoulos Angelos","year":"2020","unstructured":"Angelos Katharopoulos, Apoorv Vyas, Nikolaos Pappas, and Fran\u00e7ois Fleuret. 2020. Transformers are rnns: Fast autoregressive transformers with linear attention. In International conference on machine learning. PMLR, 5156\u20135165."},{"key":"e_1_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.5555\/2959355.2959378"},{"key":"e_1_3_3_19_2","doi-asserted-by":"crossref","unstructured":"Nicholas\u00a0D Lane Sourav Bhattacharya Akhil Mathur Petko Georgiev Claudio Forlivesi and Fahim Kawsar. 2017. Squeezing deep learning into mobile and embedded devices. IEEE Pervasive Computing 16 3 (2017) 82\u201388.","DOI":"10.1109\/MPRV.2017.2940968"},{"key":"e_1_3_3_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445780"},{"key":"e_1_3_3_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3502077"},{"key":"e_1_3_3_22_2","doi-asserted-by":"crossref","unstructured":"Denisa\u00a0Qori McDonald Richard Vallett Erin Solovey Genevi\u00e8ve Dion and Ali Shokoufandeh. 2020. Knitted sensors: designs and novel approaches for real-time real-world sensing. Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies 4 4 (2020) 1\u201325.","DOI":"10.1145\/3432201"},{"key":"e_1_3_3_23_2","doi-asserted-by":"crossref","unstructured":"Neal Parikh and Stephen Boyd. 2014. Proximal Algorithms. Foundations and Trends in Optimization 1 3 (2014) 127\u2013239.","DOI":"10.1561\/2400000003"},{"key":"e_1_3_3_24_2","unstructured":"Ali Rahimi and Benjamin Recht. 2007. Random features for large-scale kernel machines. Advances in neural information processing systems 20 (2007)."},{"key":"e_1_3_3_25_2","doi-asserted-by":"crossref","unstructured":"Alejandro Rafael\u00a0Garcia Ramirez. 2023. Introductory chapter: trends in assistive technology. Trends in Assistive Technologies (2023).","DOI":"10.5772\/intechopen.111413"},{"key":"e_1_3_3_26_2","doi-asserted-by":"publisher","DOI":"10.1515\/9781400873173"},{"key":"e_1_3_3_27_2","first-page":"19050","volume-title":"International Conference on Machine Learning","author":"Sahiner Arda","year":"2022","unstructured":"Arda Sahiner, Tolga Ergen, Batu Ozturkler, John Pauly, Morteza Mardani, and Mert Pilanci. 2022. Unraveling attention via convex duality: Analysis and interpretations of vision transformers. In International Conference on Machine Learning. PMLR, 19050\u201319088."},{"key":"e_1_3_3_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_3_3_29_2","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/4175.001.0001"},{"key":"e_1_3_3_30_2","first-page":"6105","volume-title":"International conference on machine learning","author":"Tan Mingxing","year":"2019","unstructured":"Mingxing Tan and Quoc Le. 2019. Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning. PMLR, 6105\u20136114."},{"key":"e_1_3_3_31_2","doi-asserted-by":"crossref","unstructured":"Rayane Tchantchane Hao Zhou Shen Zhang and Gursel Alici. 2023. A review of hand gesture recognition systems based on noninvasive wearable sensors. Advanced Intelligent Systems 5 10 (2023) 2300207.","DOI":"10.1002\/aisy.202300207"},{"key":"e_1_3_3_32_2","doi-asserted-by":"crossref","unstructured":"Richard Vallett Denisa\u00a0Qori McDonald Genevieve Dion Youngmoo Kim and Ali Shokoufandeh. 2020. Toward Accurate Sensing with Knitted Fabric: Applications and Technical Considerations. Proceedings of the ACM on Human-Computer Interaction 4 EICS (2020) 1\u201326.","DOI":"10.1145\/3394981"},{"key":"e_1_3_3_33_2","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-323-99135-3.00003-8"},{"key":"e_1_3_3_34_2","doi-asserted-by":"crossref","unstructured":"Richard Vallett Ryan Young Chelsea Knittel Youngmoo Kim and Genevieve Dion. 2016. Development of a carbon fiber knitted capacitive touch sensor. MRS Advances 1 38 (2016) 2641\u20132651.","DOI":"10.1557\/adv.2016.498"},{"key":"e_1_3_3_35_2","unstructured":"A Vaswani. 2017. Attention is all you need. Advances in Neural Information Processing Systems (2017)."},{"key":"e_1_3_3_36_2","unstructured":"Sinong Wang Belinda\u00a0Z Li Madian Khabsa Han Fang and Hao Ma. 2020. Linformer: Self-attention with linear complexity. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2006.04768 (2020)."},{"key":"e_1_3_3_37_2","first-page":"219","volume-title":"Proceedings of the European Symposium on Artificial Neural Networks (ESANN)","author":"Weston Jason","year":"1999","unstructured":"Jason Weston and Chris Watkins. 1999. Support Vector Machines for Multi-Class Pattern Recognition. In Proceedings of the European Symposium on Artificial Neural Networks (ESANN). D-Facto public., Bruges, Belgium, 219\u2013224. https:\/\/www.esann.org\/sites\/default\/files\/proceedings\/legacy\/es1999-461.pdf"},{"key":"e_1_3_3_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/GEM.2018.8516521"},{"key":"e_1_3_3_39_2","doi-asserted-by":"crossref","unstructured":"Shibo Zhang Yaxuan Li Shen Zhang Farzad Shahabi Stephen Xia Yu Deng and Nabil Alshurafa. 2022. Deep learning in human activity recognition with wearable sensors: A review on advances. Sensors 22 4 (2022) 1476.","DOI":"10.3390\/s22041476"},{"key":"e_1_3_3_40_2","first-page":"4044","volume-title":"International Conference on Machine Learning","author":"Zhang Yuchen","year":"2017","unstructured":"Yuchen Zhang, Percy Liang, and Martin\u00a0J Wainwright. 2017. Convexified convolutional neural networks. In International Conference on Machine Learning. PMLR, 4044\u20134053."}],"container-title":["Proceedings of the ACM on Human-Computer Interaction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3815369","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T16:32:08Z","timestamp":1783009928000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3815369"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,29]]},"references-count":39,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,6,30]]}},"alternative-id":["10.1145\/3815369"],"URL":"https:\/\/doi.org\/10.1145\/3815369","relation":{},"ISSN":["2573-0142"],"issn-type":[{"value":"2573-0142","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,29]]},"assertion":[{"value":"2026-06-29","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}