{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T17:54:40Z","timestamp":1781546080340,"version":"3.54.5"},"reference-count":103,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T00:00:00Z","timestamp":1781481600000},"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 Interact. Mob. Wearable Ubiquitous Technol."],"published-print":{"date-parts":[[2026,6,15]]},"abstract":"<jats:p>\n                    Automatic sign language recognition (SLR) has become a key enabler of inclusive human-computer interaction, fostering seamless communication between deaf individuals and hearing communities. Despite significant advances in multimodal learning, existing SLR research remains dominated by vision-based datasets, which are limited by sensitivity to lighting and occlusion, privacy concerns, and a lack of cross-modal diversity. To address these challenges, we introduce\n                    <jats:bold>SIGMA-ASL<\/jats:bold>\n                    , a large-scale multimodal dataset for SLR. The dataset integrates an Azure Kinect RGB-D camera, a millimeter-wave (mmWave) radar, and two wrist-worn inertial measurement units (IMUs) to capture complementary visual, radio-reflection, and kinematic information. Collected in a controlled studio environment with 20 participants performing 160 common American sign language (ASL) signs,\n                    <jats:bold>SIGMA-ASL<\/jats:bold>\n                    provides 93,545 temporally synchronized word-level multimodal clips. A unified sensing framework achieves millisecond-level alignment across modalities, enabling reliable sensor fusion and cross-modal learning. We further design standardized preprocessing pipelines and benchmarking protocols under both user-dependent and user-independent settings, offering a comprehensive foundation for evaluating single and multimodal SLR. Extensive experiments validate the dataset's quality and demonstrate its potential as a valuable resource for developing robust, privacy-preserving, and ubiquitous sign language recognition systems.\n                  <\/jats:p>","DOI":"10.1145\/3810202","type":"journal-article","created":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T17:06:41Z","timestamp":1781543201000},"page":"1-33","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["SIGMA-ASL: Sensor-Integrated Multimodal Dataset for Sign Language Recognition"],"prefix":"10.1145","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-7715-2393","authenticated-orcid":false,"given":"Xiaofang","family":"Xiao","sequence":"first","affiliation":[{"name":"School of Software, Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9625-1265","authenticated-orcid":false,"given":"Guangchao","family":"Li","sequence":"additional","affiliation":[{"name":"School of Software, Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4703-9397","authenticated-orcid":false,"given":"Guangrong","family":"Zhao","sequence":"additional","affiliation":[{"name":"Shandong University, School of Software, jinan, Shandong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3676-9789","authenticated-orcid":false,"given":"Qi","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6601-1090","authenticated-orcid":false,"given":"Wen","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Foreign Language and Literature, Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1159-090X","authenticated-orcid":false,"given":"Hongkai","family":"Wen","sequence":"additional","affiliation":[{"name":"University of Warwick, Coventry, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1466-4006","authenticated-orcid":false,"given":"Yanxiang","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Software, Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1385-1480","authenticated-orcid":false,"given":"Yiran","family":"Shen","sequence":"additional","affiliation":[{"name":"School of Software, Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,15]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1504\/IJAPR.2016.079048","article-title":"A survey on manual and non-manual sign language recognition for isolated and continuous sign","volume":"3","author":"Agrawal Subhash Chand","year":"2016","unstructured":"Subhash Chand Agrawal, Anand Singh Jalal, and Rajesh Kumar Tripathi. 2016. A survey on manual and non-manual sign language recognition for isolated and continuous sign. International Journal of Applied Pattern Recognition 3, 2 (2016), 99\u2013134.","journal-title":"International Journal of Applied Pattern Recognition"},{"key":"e_1_2_1_2_1","doi-asserted-by":"crossref","first-page":"5470","DOI":"10.3390\/s22155470","article-title":"Towards a low-cost solution for gait analysis using millimeter wave sensor and machine learning","volume":"22","author":"Alanazi Mubarak A","year":"2022","unstructured":"Mubarak A Alanazi, Abdullah K Alhazmi, Osama Alsattam, Kara Gnau, Meghan Brown, Shannon Thiel, Kurt Jackson, and Vamsy P Chodavarapu. 2022. Towards a low-cost solution for gait analysis using millimeter wave sensor and machine learning. Sensors 22, 15 (2022), 5470.","journal-title":"Sensors"},{"key":"e_1_2_1_3_1","volume-title":"European conference on computer vision. Springer, 35\u201353","author":"Albanie Samuel","year":"2020","unstructured":"Samuel Albanie, G\u00fcl Varol, Liliane Momeni, Triantafyllos Afouras, Joon Son Chung, Neil Fox, and Andrew Zisserman. 2020. BSL-1K: Scaling up co-articulated sign language recognition using mouthing cues. In European conference on computer vision. Springer, 35\u201353."},{"key":"e_1_2_1_4_1","doi-asserted-by":"crossref","first-page":"103774","DOI":"10.1016\/j.ipm.2024.103774","article-title":"Reviewing 25 years of continuous sign language recognition research: Advances, challenges, and prospects","volume":"61","author":"Alyami Sarah","year":"2024","unstructured":"Sarah Alyami, Hamzah Luqman, and Mohammad Hammoudeh. 2024. Reviewing 25 years of continuous sign language recognition research: Advances, challenges, and prospects. Information Processing & Management 61, 5 (2024), 103774.","journal-title":"Information Processing & Management"},{"key":"e_1_2_1_5_1","volume-title":"mri: Multi-modal 3d human pose estimation dataset using mmwave, rgb-d, and inertial sensors. Advances in neural information processing systems 35","author":"An Sizhe","year":"2022","unstructured":"Sizhe An, Yin Li, and Umit Ogras. 2022. mri: Multi-modal 3d human pose estimation dataset using mmwave, rgb-d, and inertial sensors. Advances in neural information processing systems 35 (2022), 27414\u201327426."},{"key":"e_1_2_1_6_1","volume-title":"The american sign language lexicon video dataset. In 2008 IEEE computer society conference on computer vision and pattern recognition workshops","author":"Athitsos Vassilis","unstructured":"Vassilis Athitsos, Carol Neidle, Stan Sclaroff, Joan Nash, Alexandra Stefan, Quan Yuan, and Ashwin Thangali. 2008. The american sign language lexicon video dataset. In 2008 IEEE computer society conference on computer vision and pattern recognition workshops. IEEE, 1\u20138."},{"key":"e_1_2_1_7_1","volume-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv preprint arXiv:1803.01271","author":"Bai Shaojie","year":"2018","unstructured":"Shaojie Bai, J Zico Kolter, and Vladlen Koltun. 2018. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv preprint arXiv:1803.01271 (2018)."},{"key":"e_1_2_1_8_1","first-page":"4","article-title":"Is space-time attention all you need for video understanding?","volume":"2","author":"Bertasius Gedas","year":"2021","unstructured":"Gedas Bertasius, Heng Wang, and Lorenzo Torresani. 2021. Is space-time attention all you need for video understanding?. In Icml, Vol. 2. 4.","journal-title":"Icml"},{"key":"e_1_2_1_9_1","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition. 7784\u20137793","author":"Camgoz Necati Cihan","year":"2018","unstructured":"Necati Cihan Camgoz, Simon Hadfield, Oscar Koller, Hermann Ney, and Richard Bowden. 2018. Neural sign language translation. In Proceedings of the IEEE conference on computer vision and pattern recognition. 7784\u20137793."},{"key":"e_1_2_1_10_1","volume-title":"proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 6299\u20136308","author":"Carreira Joao","year":"2017","unstructured":"Joao Carreira and Andrew Zisserman. 2017. Quo vadis, action recognition? a new model and the kinetics dataset. In proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 6299\u20136308."},{"key":"e_1_2_1_11_1","volume-title":"IEEE conf. on AFGR","volume":"655","author":"Chai Xiujuan","year":"2013","unstructured":"Xiujuan Chai, Guang Li, Yushun Lin, Zhihao Xu, Yili Tang, Xilin Chen, and Ming Zhou. 2013. Sign language recognition and translation with kinect. In IEEE conf. on AFGR, Vol. 655. 4."},{"key":"e_1_2_1_12_1","volume-title":"The 25th Annual International Conference on Mobile Computing and Networking. 1\u201316","author":"Chen Wenqiang","year":"2019","unstructured":"Wenqiang Chen, Lin Chen, Yandao Huang, Xinyu Zhang, Lu Wang, Rukhsana Ruby, and Kaishun Wu. 2019. Taprint: Secure text input for commodity smart wristbands. In The 25th Annual International Conference on Mobile Computing and Networking. 1\u201316."},{"key":"e_1_2_1_13_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3448119","article-title":"ViFin: Harness passive vibration to continuous micro finger writing with a commodity smartwatch","volume":"5","author":"Chen Wenqiang","year":"2021","unstructured":"Wenqiang Chen, Lin Chen, Meiyi Ma, Farshid Salemi Parizi, Shwetak Patel, and John Stankovic. 2021. ViFin: Harness passive vibration to continuous micro finger writing with a commodity smartwatch. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 5, 1 (2021), 1\u201325.","journal-title":"Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies"},{"key":"e_1_2_1_14_1","doi-asserted-by":"crossref","first-page":"1880","DOI":"10.1109\/TMM.2018.2889563","article-title":"A deep neural framework for continuous sign language recognition by iterative training","volume":"21","author":"Cui Runpeng","year":"2019","unstructured":"Runpeng Cui, Hu Liu, and Changshui Zhang. 2019. A deep neural framework for continuous sign language recognition by iterative training. IEEE Transactions on Multimedia 21, 7 (2019), 1880\u20131891.","journal-title":"IEEE Transactions on Multimedia"},{"key":"e_1_2_1_15_1","volume-title":"2009 IEEE conference on computer vision and pattern recognition. Ieee, 248\u2013255","author":"Deng Jia","year":"2009","unstructured":"Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei. 2009. Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition. Ieee, 248\u2013255."},{"key":"e_1_2_1_16_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3580872","article-title":"Midas: Generating mmwave radar data from videos for training pervasive and privacy-preserving human sensing tasks","volume":"7","author":"Deng Kaikai","year":"2023","unstructured":"Kaikai Deng, Dong Zhao, Qiaoyue Han, Zihan Zhang, Shuyue Wang, Anfu Zhou, and Huadong Ma. 2023. Midas: Generating mmwave radar data from videos for training pervasive and privacy-preserving human sensing tasks. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 7, 1 (2023), 1\u201326.","journal-title":"Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies"},{"key":"e_1_2_1_17_1","volume-title":"G 3 R: Generating Rich and Fine-Grained mmWave Radar Data From 2D Videos for Generalized Gesture Recognition","author":"Deng Kaikai","year":"2024","unstructured":"Kaikai Deng, Dong Zhao, Wenxin Zheng, Yue Ling, Kangwen Yin, and Huadong Ma. 2024. G 3 R: Generating Rich and Fine-Grained mmWave Radar Data From 2D Videos for Generalized Gesture Recognition. IEEE Transactions on Mobile Computing (2024)."},{"key":"e_1_2_1_18_1","first-page":"76893","article-title":"ASL citizen: a community-sourced dataset for advancing isolated sign language recognition","volume":"36","author":"Desai Aashaka","year":"2023","unstructured":"Aashaka Desai, Lauren Berger, Fyodor Minakov, Nessa Milano, Chinmay Singh, Kriston Pumphrey, Richard Ladner, Hal Daum\u00e9 III, Alex X Lu, Naomi Caselli, et al. 2023. ASL citizen: a community-sourced dataset for advancing isolated sign language recognition. Advances in Neural Information Processing Systems 36 (2023), 76893\u201376907.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_19_1","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision. 6889\u20136899","author":"Ding Zhipeng","year":"2021","unstructured":"Zhipeng Ding, Xu Han, Peirong Liu, and Marc Niethammer. 2021. Local temperature scaling for probability calibration. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 6889\u20136899."},{"key":"e_1_2_1_20_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3631455","article-title":"Bias mitigation in federated learning for edge computing","volume":"7","author":"Djebrouni Yasmine","year":"2024","unstructured":"Yasmine Djebrouni, Nawel Benarba, Ousmane Touat, Pasquale De Rosa, Sara Bouchenak, Angela Bonifati, Pascal Felber, Vania Marangozova, and Valerio Schiavoni. 2024. Bias mitigation in federated learning for edge computing. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 7, 4 (2024), 1\u201335.","journal-title":"Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies"},{"key":"e_1_2_1_21_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_2_1_22_1","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2969\u20132978","author":"Duan Haodong","year":"2022","unstructured":"Haodong Duan, Yue Zhao, Kai Chen, Dahua Lin, and Bo Dai. 2022. Revisiting skeleton-based action recognition. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2969\u20132978."},{"key":"e_1_2_1_23_1","volume-title":"Proceedings of the 11th international conference on language resources and evaluation (LREC)","author":"Ebling Sarah","year":"2018","unstructured":"Sarah Ebling, Necati Cihan Camg\u00f6z, Penny Boyes Braem, Katja Tissi, Sandra Sidler-Miserez, Stephanie Stoll, Simon Hadfield, Tobias Haug, Richard Bowden, Sandrine Tornay, et al. 2018. SMILE Swiss German sign language dataset. In Proceedings of the 11th international conference on language resources and evaluation (LREC) 2018. The European Language Resources Association (ELRA)."},{"key":"e_1_2_1_24_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3633808","article-title":"Pastel: Privacy-preserving federated learning in edge computing","volume":"7","author":"Elhattab Fatima","year":"2024","unstructured":"Fatima Elhattab, Sara Bouchenak, and C\u00e9dric Boscher. 2024. Pastel: Privacy-preserving federated learning in edge computing. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 7, 4 (2024), 1\u201329.","journal-title":"Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies"},{"key":"e_1_2_1_25_1","volume-title":"Proceedings of the IEEE\/CVF international conference on computer vision. 6202\u20136211","author":"Feichtenhofer Christoph","year":"2019","unstructured":"Christoph Feichtenhofer, Haoqi Fan, Jitendra Malik, and Kaiming He. 2019. Slowfast networks for video recognition. In Proceedings of the IEEE\/CVF international conference on computer vision. 6202\u20136211."},{"key":"e_1_2_1_26_1","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition. 1933\u20131941","author":"Feichtenhofer Christoph","year":"2016","unstructured":"Christoph Feichtenhofer, Axel Pinz, and Andrew Zisserman. 2016. Convolutional two-stream network fusion for video action recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition. 1933\u20131941."},{"key":"e_1_2_1_27_1","volume-title":"2021 International Joint Conference on Neural Networks (IJCNN). IEEE, 1\u20138.","author":"Fink J\u00e9r\u00f4me","year":"2021","unstructured":"J\u00e9r\u00f4me Fink, Beno\u00eet Fr\u00e9nay, Laurence Meurant, and Anthony Cleve. 2021. Lsfb-cont and lsfb-isol: Two new datasets for vision-based sign language recognition. In 2021 International Joint Conference on Neural Networks (IJCNN). IEEE, 1\u20138."},{"key":"e_1_2_1_28_1","doi-asserted-by":"crossref","first-page":"3785","DOI":"10.63317\/4vmmiu4jeew5","article-title":"RWTH-PHOENIX-weather: A large vocabulary sign language recognition and translation corpus","volume":"9","author":"Forster Jens","year":"2012","unstructured":"Jens Forster, Christoph Schmidt, Thomas Hoyoux, Oscar Koller, Uwe Zelle, Justus H Piater, and Hermann Ney. 2012. RWTH-PHOENIX-weather: A large vocabulary sign language recognition and translation corpus. In LREC, Vol. 9. 3785\u20133789.","journal-title":"LREC"},{"key":"e_1_2_1_29_1","first-page":"1","volume-title":"Proceedings of the ACM on interactive, mobile, wearable and ubiquitous technologies 7","author":"Gao Chenyang","year":"2023","unstructured":"Chenyang Gao, Ivan Marsic, Aleksandra Sarcevic, Waverly Gestrich-Thompson, and Randall S Burd. 2023. Real-time context-aware multimodal network for activity and activity-stage recognition from team communication in dynamic clinical settings. Proceedings of the ACM on interactive, mobile, wearable and ubiquitous technologies 7, 1 (2023), 1\u201328."},{"key":"e_1_2_1_30_1","volume-title":"Proceedings of the 2016 ACM international joint conference on pervasive and ubiquitous computing. 1112\u20131123","author":"Guo Haodong","year":"2016","unstructured":"Haodong Guo, Ling Chen, Liangying Peng, and Gencai Chen. 2016. Wearable sensor based multimodal human activity recognition exploiting the diversity of classifier ensemble. In Proceedings of the 2016 ACM international joint conference on pervasive and ubiquitous computing. 1112\u20131123."},{"key":"e_1_2_1_31_1","doi-asserted-by":"crossref","unstructured":"Sevgi Z Gurbuz Ali C Gurbuz Evie A Malaia Darrin J Griffin Chris Crawford M Mahbubur Rahman Ridvan Aksu Emre Kurtoglu Robiulhossain Mdrafi Ajaymehul Anbuselvam et al. 2020. A linguistic perspective on radar micro-Doppler analysis of American sign language. In 2020 IEEE international radar conference (RADAR).","DOI":"10.1109\/RADAR42522.2020.9114818"},{"key":"e_1_2_1_32_1","first-page":"3763","article-title":"American sign language recognition using rf sensing","volume":"21","author":"Gurbuz Sevgi Z","year":"2020","unstructured":"Sevgi Z Gurbuz, Ali Cafer Gurbuz, Evie A Malaia, Darrin J Griffin, Chris S Crawford, Mohammad Mahbubur Rahman, Emre Kurtoglu, Ridvan Aksu, Trevor Macks, and Robiulhossain Mdrafi. 2020. American sign language recognition using rf sensing. IEEE Sensors Journal 21, 3 (2020), 3763\u20133775.","journal-title":"IEEE Sensors Journal"},{"key":"e_1_2_1_33_1","volume-title":"LSE-sign: A lexical database for spanish sign language. Behavior research methods 48, 1","author":"Gutierrez-Sigut Eva","year":"2016","unstructured":"Eva Gutierrez-Sigut, Brendan Costello, Cristina Baus, and Manuel Carreiras. 2016. LSE-sign: A lexical database for spanish sign language. Behavior research methods 48, 1 (2016), 123\u2013137."},{"key":"e_1_2_1_34_1","volume-title":"Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. 6546\u20136555","author":"Hara Kensho","year":"2018","unstructured":"Kensho Hara, Hirokatsu Kataoka, and Yutaka Satoh. 2018. Can spatiotemporal 3d cnns retrace the history of 2d cnns and imagenet?. In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. 6546\u20136555."},{"key":"e_1_2_1_35_1","volume-title":"The 25th Annual International Conference on Mobile Computing and Networking. 1\u201315","author":"Hou Jiahui","year":"2019","unstructured":"Jiahui Hou, Xiang-Yang Li, Peide Zhu, Zefan Wang, Yu Wang, Jianwei Qian, and Panlong Yang. 2019. Signspeaker: A real-time, high-precision smartwatch-based sign language translator. In The 25th Annual International Conference on Mobile Computing and Networking. 1\u201315."},{"key":"e_1_2_1_36_1","doi-asserted-by":"crossref","first-page":"2822","DOI":"10.1109\/TCSVT.2018.2870740","article-title":"Attention-based 3D-CNNs for large-vocabulary sign language recognition","volume":"29","author":"Huang Jie","year":"2018","unstructured":"Jie Huang, Wengang Zhou, Houqiang Li, and Weiping Li. 2018. Attention-based 3D-CNNs for large-vocabulary sign language recognition. IEEE Transactions on Circuits and Systems for Video Technology 29, 9 (2018), 2822\u20132832.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"e_1_2_1_37_1","volume-title":"Proceedings of the AAAI conference on artificial intelligence","volume":"32","author":"Huang Jie","year":"2018","unstructured":"Jie Huang, Wengang Zhou, Qilin Zhang, Houqiang Li, and Weiping Li. 2018. Video-based sign language recognition without temporal segmentation. In Proceedings of the AAAI conference on artificial intelligence, Vol. 32."},{"key":"e_1_2_1_38_1","volume-title":"Llm maybe longlm: Self-extend llm context window without tuning. arXiv preprint arXiv:2401.01325","author":"Jin Hongye","year":"2024","unstructured":"Hongye Jin, Xiaotian Han, Jingfeng Yang, Zhimeng Jiang, Zirui Liu, Chia-Yuan Chang, Huiyuan Chen, and Xia Hu. 2024. Llm maybe longlm: Self-extend llm context window without tuning. arXiv preprint arXiv:2401.01325 (2024)."},{"key":"e_1_2_1_39_1","first-page":"1","article-title":"SmartASL: \u201cPoint-of-Care","volume":"7","author":"Jin Yincheng","year":"2023","unstructured":"Yincheng Jin, Shibo Zhang, Yang Gao, Xuhai Xu, Seokmin Choi, Zhengxiong Li, Henry J Adler, and Zhanpeng Jin. 2023. SmartASL: \u201cPoint-of-Care\u201d Comprehensive ASL Interpreter Using Wearables. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 7, 2 (2023), 1\u201321.","journal-title":"Comprehensive ASL Interpreter Using Wearables. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies"},{"key":"e_1_2_1_40_1","volume-title":"Ms-asl: A large-scale data set and benchmark for understanding american sign language. arXiv preprint arXiv:1812.01053","author":"Vaezi Joze Hamid Reza","year":"2018","unstructured":"Hamid Reza Vaezi Joze and Oscar Koller. 2018. Ms-asl: A large-scale data set and benchmark for understanding american sign language. arXiv preprint arXiv:1812.01053 (2018)."},{"key":"e_1_2_1_41_1","volume-title":"Transfer: Cross Modality Knowledge Transfer using Adversarial Networks-A Study on Gesture Recognition. arXiv preprint arXiv:2306.15114","author":"Kamboj Payal","year":"2023","unstructured":"Payal Kamboj, Ayan Banerjee, and Sandeep KS Gupta. 2023. Transfer: Cross Modality Knowledge Transfer using Adversarial Networks-A Study on Gesture Recognition. arXiv preprint arXiv:2306.15114 (2023)."},{"key":"e_1_2_1_42_1","unstructured":"Will Kay Joao Carreira Karen Simonyan Brian Zhang Chloe Hillier Sudheendra Vijayanarasimhan Fabio Viola Tim Green Trevor Back Paul Natsev et al. 2017. The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)."},{"key":"e_1_2_1_43_1","doi-asserted-by":"crossref","first-page":"108471","DOI":"10.1016\/j.measurement.2020.108471","article-title":"Persian sign language recognition using IMU and surface EMG sensors","volume":"168","author":"Khomami Sara Askari","year":"2021","unstructured":"Sara Askari Khomami and Sina Shamekhi. 2021. Persian sign language recognition using IMU and surface EMG sensors. Measurement 168 (2021), 108471.","journal-title":"Measurement"},{"key":"e_1_2_1_44_1","volume-title":"Quantitative survey of the state of the art in sign language recognition. arXiv preprint arXiv:2008.09918","author":"Koller Oscar","year":"2020","unstructured":"Oscar Koller. 2020. Quantitative survey of the state of the art in sign language recognition. arXiv preprint arXiv:2008.09918 (2020)."},{"key":"e_1_2_1_45_1","volume-title":"Proceedings of the British Machine Vision Conference","author":"Koller Oscar","year":"2016","unstructured":"Oscar Koller, O Zargaran, Hermann Ney, and Richard Bowden. 2016. Deep sign: Hybrid CNN-HMM for continuous sign language recognition. In Proceedings of the British Machine Vision Conference 2016."},{"key":"e_1_2_1_46_1","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision. 8658\u20138667","author":"Kong Quan","year":"2019","unstructured":"Quan Kong, Ziming Wu, Ziwei Deng, Martin Klinkigt, Bin Tong, and Tomokazu Murakami. 2019. Mmact: A large-scale dataset for cross modal human action understanding. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 8658\u20138667."},{"key":"e_1_2_1_47_1","doi-asserted-by":"crossref","first-page":"27273","DOI":"10.1109\/JSEN.2023.3324369","article-title":"Applying mmWave radar sensors to vocabulary-level dynamic Chinese sign language recognition for the community with deafness and hearing loss","volume":"23","author":"Lan Shengchang","year":"2023","unstructured":"Shengchang Lan, Linting Ye, and Kang Zhang. 2023. Applying mmWave radar sensors to vocabulary-level dynamic Chinese sign language recognition for the community with deafness and hearing loss. IEEE Sensors Journal 23, 22 (2023), 27273\u201327283.","journal-title":"IEEE Sensors Journal"},{"key":"e_1_2_1_48_1","volume-title":"Michael Cogswell, Viresh Ranjan, David Crandall, and Dhruv Batra.","author":"Lee Stefan","year":"2016","unstructured":"Stefan Lee, Senthil Purushwalkam Shiva Prakash, Michael Cogswell, Viresh Ranjan, David Crandall, and Dhruv Batra. 2016. Stochastic multiple choice learning for training diverse deep ensembles. Advances in Neural Information Processing Systems 29 (2016)."},{"key":"e_1_2_1_49_1","volume-title":"Proceedings of the IEEE\/CVF winter conference on applications of computer vision. 1459\u20131469","author":"Li Dongxu","year":"2020","unstructured":"Dongxu Li, Cristian Rodriguez, Xin Yu, and Hongdong Li. 2020. Word-level deep sign language recognition from video: A new large-scale dataset and methods comparison. In Proceedings of the IEEE\/CVF winter conference on applications of computer vision. 1459\u20131469."},{"key":"e_1_2_1_50_1","first-page":"1","article-title":"Signring: Continuous american sign language recognition using imu rings and virtual imu data","volume":"7","author":"Li Jiyang","year":"2023","unstructured":"Jiyang Li, Lin Huang, Siddharth Shah, Sean J Jones, Yincheng Jin, Dingran Wang, Adam Russell, Seokmin Choi, Yang Gao, Junsong Yuan, et al. 2023. Signring: Continuous american sign language recognition using imu rings and virtual imu data. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 7, 3 (2023), 1\u201329.","journal-title":"Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies"},{"key":"e_1_2_1_51_1","volume-title":"International conference on machine learning. PMLR","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In International conference on machine learning. PMLR, 19730\u201319742."},{"key":"e_1_2_1_52_1","volume-title":"Active Domain Adaptation for mmWave-based HAR via Renyi Entropy-based Uncertainty Estimation. arXiv preprint arXiv:2511.04219","author":"Lin Mingzhi","year":"2025","unstructured":"Mingzhi Lin, Teng Huang, Han Ding, Cui Zhao, Fei Wang, Ge Wang, and Wei Xi. 2025. Active Domain Adaptation for mmWave-based HAR via Renyi Entropy-based Uncertainty Estimation. arXiv preprint arXiv:2511.04219 (2025)."},{"key":"e_1_2_1_53_1","first-page":"1","article-title":"Pmc: A privacy-preserving deep learning model customization framework for edge computing","volume":"4","author":"Liu Bingyan","year":"2020","unstructured":"Bingyan Liu, Yuanchun Li, Yunxin Liu, Yao Guo, and Xiangqun Chen. 2020. Pmc: A privacy-preserving deep learning model customization framework for edge computing. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 4, 4 (2020), 1\u201325.","journal-title":"Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies"},{"key":"e_1_2_1_54_1","volume-title":"Pku-mmd: A large scale benchmark for continuous multi-modal human action understanding. arXiv","author":"Liu Chunhui","year":"2017","unstructured":"Chunhui Liu, Yueyu Hu, Yanghao Li, Sijie Song, and Jiaying Liu. 2017. Pku-mmd: A large scale benchmark for continuous multi-modal human action understanding. arXiv 2017. arXiv preprint arXiv: 1703.07475 (2017)."},{"key":"e_1_2_1_55_1","first-page":"1","article-title":"mtranssee: Enabling environment-independent mmwave sensing based gesture recognition via transfer learning","volume":"6","author":"Liu Haipeng","year":"2022","unstructured":"Haipeng Liu, Kening Cui, Kaiyuan Hu, Yuheng Wang, Anfu Zhou, Liang Liu, and Huadong Ma. 2022. mtranssee: Enabling environment-independent mmwave sensing based gesture recognition via transfer learning. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 6, 1 (2022), 1\u201328.","journal-title":"Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies"},{"key":"e_1_2_1_56_1","volume-title":"Late fusion incomplete multi-view clustering","author":"Liu Xinwang","year":"2018","unstructured":"Xinwang Liu, Xinzhong Zhu, Miaomiao Li, Lei Wang, Chang Tang, Jianping Yin, Dinggang Shen, Huaimin Wang, and Wen Gao. 2018. Late fusion incomplete multi-view clustering. IEEE transactions on pattern analysis and machine intelligence 41, 10 (2018), 2410\u20132423."},{"key":"e_1_2_1_57_1","volume-title":"Juhyun Lee, et al.","author":"Lugaresi Camillo","year":"2019","unstructured":"Camillo Lugaresi, Jiuqiang Tang, Hadon Nash, Chris McClanahan, Esha Uboweja, Michael Hays, Fan Zhang, Chuo-Ling Chang, Ming Guang Yong, Juhyun Lee, et al. 2019. Mediapipe: A framework for building perception pipelines. arXiv preprint arXiv:1906.08172 (2019)."},{"key":"e_1_2_1_58_1","volume-title":"Proceedings. Fourth IEEE International Conference on Multimodal Interfaces. IEEE, 167\u2013172","author":"Mart\u00ednez Aleix M","year":"2002","unstructured":"Aleix M Mart\u00ednez, Ronnie B Wilbur, Robin Shay, and Avinash C Kak. 2002. Purdue RVL-SLLL ASL database for automatic recognition of American Sign Language. In Proceedings. Fourth IEEE International Conference on Multimodal Interfaces. IEEE, 167\u2013172."},{"key":"e_1_2_1_59_1","unstructured":"Microsoft. 2020. Azure Kinect DK. https:\/\/learn.microsoft.com\/zh-cn\/previous-versions\/azure\/kinect-dk\/. Accessed: 2025-10-09."},{"key":"e_1_2_1_60_1","volume-title":"Proceedings of the IEEE\/ACM 46th International Conference on Software Engineering. 1\u201313","author":"Nam Daye","year":"2024","unstructured":"Daye Nam, Andrew Macvean, Vincent Hellendoorn, Bogdan Vasilescu, and Brad Myers. 2024. Using an llm to help with code understanding. In Proceedings of the IEEE\/ACM 46th International Conference on Software Engineering. 1\u201313."},{"key":"e_1_2_1_61_1","doi-asserted-by":"crossref","first-page":"15065","DOI":"10.1109\/JSEN.2021.3074642","article-title":"Gesture recognition using wearable sensors with bi-long short-term memory convolutional neural networks","volume":"21","author":"Nguyen-Trong Khanh","year":"2021","unstructured":"Khanh Nguyen-Trong, Hoai Nam Vu, Ngon Nguyen Trung, and Cuong Pham. 2021. Gesture recognition using wearable sensors with bi-long short-term memory convolutional neural networks. IEEE Sensors Journal 21, 13 (2021), 15065\u201315079.","journal-title":"IEEE Sensors Journal"},{"key":"e_1_2_1_62_1","volume-title":"2012 IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 2200\u20132207","author":"Ong Eng-Jon","year":"2012","unstructured":"Eng-Jon Ong, Helen Cooper, Nicolas Pugeault, and Richard Bowden. 2012. Sign language recognition using sequential pattern trees. In 2012 IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 2200\u20132207."},{"key":"e_1_2_1_63_1","volume-title":"Necati Cihan Camg\u00f6z, and Lale Akarun.","author":"\u00d6zdemir O\u011fulcan","year":"2020","unstructured":"O\u011fulcan \u00d6zdemir, Ahmet Alp Kindiro\u011flu, Necati Cihan Camg\u00f6z, and Lale Akarun. 2020. Bosphorussign22k sign language recognition dataset. arXiv preprint arXiv:2004.01283 (2020)."},{"key":"e_1_2_1_64_1","volume-title":"Proceedings of the AAAI conference on artificial intelligence","volume":"32","author":"Perez Ethan","year":"2018","unstructured":"Ethan Perez, Florian Strub, Harm De Vries, Vincent Dumoulin, and Aaron Courville. 2018. Film: Visual reasoning with a general conditioning layer. In Proceedings of the AAAI conference on artificial intelligence, Vol. 32."},{"key":"e_1_2_1_65_1","volume-title":"2023 IEEE 20th International Conference on Mobile Ad Hoc and Smart Systems (MASS). IEEE, 218\u2013226","author":"Pinyoanuntapong Ekkasit","year":"2023","unstructured":"Ekkasit Pinyoanuntapong, Ayman Ali, Kalvik Jakkala, Pu Wang, Minwoo Lee, Qucheng Peng, Chen Chen, and Zhi Sun. 2023. Gaitsada: Self-aligned domain adaptation for mmwave gait recognition. In 2023 IEEE 20th International Conference on Mobile Ad Hoc and Smart Systems (MASS). IEEE, 218\u2013226."},{"key":"e_1_2_1_66_1","volume-title":"Rankvicuna: Zero-shot listwise document reranking with open-source large language models. arXiv preprint arXiv:2309.15088","author":"Pradeep Ronak","year":"2023","unstructured":"Ronak Pradeep, Sahel Sharifymoghaddam, and Jimmy Lin. 2023. Rankvicuna: Zero-shot listwise document reranking with open-source large language models. arXiv preprint arXiv:2309.15088 (2023)."},{"key":"e_1_2_1_67_1","volume-title":"International conference on machine learning. PmLR, 8748\u20138763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PmLR, 8748\u20138763."},{"key":"e_1_2_1_68_1","volume-title":"2021 IEEE Radar Conference (RadarConf21)","author":"Rahman M Mahbubur","year":"2021","unstructured":"M Mahbubur Rahman, Robiulhossain Mdrafi, Ali C Gurbuz, Evie Malaia, Chris Crawford, Darrin Griffin, and Sevgi Z Gurbuz. 2021. Word-level sign language recognition using linguistic adaptation of 77 GHz FMCW radar data. In 2021 IEEE Radar Conference (RadarConf21). IEEE, 1\u20136."},{"key":"e_1_2_1_69_1","volume-title":"C\u00e9sar Estrebou, Laura Lanzarini, and Alejandro Rosete.","author":"Ronchetti Franco","year":"2023","unstructured":"Franco Ronchetti, Facundo Manuel Quiroga, C\u00e9sar Estrebou, Laura Lanzarini, and Alejandro Rosete. 2023. LSA64: An Argentinian sign language dataset. arXiv preprint arXiv:2310.17429 (2023)."},{"key":"e_1_2_1_70_1","volume-title":"2020 17th Annual IEEE International Conference on Sensing, Communication, and Networking (SECON). IEEE, 1\u20139.","author":"Santhalingam Panneer Selvam","year":"2020","unstructured":"Panneer Selvam Santhalingam, Yuanqi Du, Riley Wilkerson, Al Amin Hosain, Ding Zhang, Parth Pathak, Huzefa Rangwala, and Raja Kushalnagar. 2020. Expressive asl recognition using millimeter-wave wireless signals. In 2020 17th Annual IEEE International Conference on Sensing, Communication, and Networking (SECON). IEEE, 1\u20139."},{"key":"e_1_2_1_71_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3381010","article-title":"mmasl: Environment-independent asl gesture recognition using 60 ghz millimeter-wave signals","volume":"4","author":"Santhalingam Panneer Selvam","year":"2020","unstructured":"Panneer Selvam Santhalingam, Al Amin Hosain, Ding Zhang, Parth Pathak, Huzefa Rangwala, and Raja Kushalnagar. 2020. mmasl: Environment-independent asl gesture recognition using 60 ghz millimeter-wave signals. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 4, 1 (2020), 1\u201330.","journal-title":"Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies"},{"key":"e_1_2_1_72_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3596261","article-title":"Synthetic smartwatch imu data generation from in-the-wild asl videos","volume":"7","author":"Santhalingam Panneer Selvam","year":"2023","unstructured":"Panneer Selvam Santhalingam, Parth Pathak, Huzefa Rangwala, and Jana Kosecka. 2023. Synthetic smartwatch imu data generation from in-the-wild asl videos. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 7, 2 (2023), 1\u201334.","journal-title":"Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies"},{"key":"e_1_2_1_73_1","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision. 3210\u20133219","author":"Sarhan Noha","year":"2023","unstructured":"Noha Sarhan and Simone Frintrop. 2023. Unraveling a decade: A comprehensive survey on isolated sign language recognition. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 3210\u20133219."},{"key":"e_1_2_1_74_1","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition. 1010\u20131019","author":"Shahroudy Amir","year":"2016","unstructured":"Amir Shahroudy, Jun Liu, Tian-Tsong Ng, and Gang Wang. 2016. Ntu rgb+ d: A large scale dataset for 3d human activity analysis. In Proceedings of the IEEE conference on computer vision and pattern recognition. 1010\u20131019."},{"key":"e_1_2_1_75_1","doi-asserted-by":"crossref","first-page":"30746","DOI":"10.1007\/s10489-023-05159-2","article-title":"Radar based automated system for people walk identification using correlation information and flexible analytic wavelet transform: RR Sharma et al","volume":"53","author":"Sharma Rishi Raj","year":"2023","unstructured":"Rishi Raj Sharma, Gunupuru Aravind, and Rahul Dubey. 2023. Radar based automated system for people walk identification using correlation information and flexible analytic wavelet transform: RR Sharma et al. Applied Intelligence 53, 24 (2023), 30746\u201330756.","journal-title":"Applied Intelligence"},{"key":"e_1_2_1_76_1","first-page":"69700","article-title":"MM-WLAuslan: Multi-View Multi-Modal Word-Level Australian Sign Language Recognition Dataset","volume":"37","author":"Shen Xin","year":"2024","unstructured":"Xin Shen, Heming Du, Hongwei Sheng, Shuyun Wang, Hui Chen, Huiqiang Chen, Zhuojie Wu, Xiaobiao Du, Jiaying Ying, Ruihan Lu, et al. 2024. MM-WLAuslan: Multi-View Multi-Modal Word-Level Australian Sign Language Recognition Dataset. Advances in Neural Information Processing Systems 37 (2024), 69700\u201369715.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_77_1","first-page":"80455","article-title":"Auslan-daily: Australian sign language translation for daily communication and news","volume":"36","author":"Shen Xin","year":"2023","unstructured":"Xin Shen, Shaozu Yuan, Hongwei Sheng, Heming Du, and Xin Yu. 2023. Auslan-daily: Australian sign language translation for daily communication and news. Advances in Neural Information Processing Systems 36 (2023), 80455\u201380469.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_78_1","volume-title":"Human Activity Recognition Based on Feature Fusion of Millimeter Wave Radar and Inertial Navigation","author":"Shi Jiajia","year":"2025","unstructured":"Jiajia Shi, Yihan Zhu, Jiaqing He, Zhihuo Xu, Liu Chu, Robin Braun, and Quan Shi. 2025. Human Activity Recognition Based on Feature Fusion of Millimeter Wave Radar and Inertial Navigation. IEEE Journal of Microwaves (2025)."},{"key":"e_1_2_1_79_1","volume-title":"Two-stream convolutional networks for action recognition in videos. Advances in neural information processing systems 27","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Two-stream convolutional networks for action recognition in videos. Advances in neural information processing systems 27 (2014)."},{"key":"e_1_2_1_80_1","volume-title":"Autsl: A large scale multi-modal turkish sign language dataset and baseline methods","author":"Sincan Ozge Mercanoglu","year":"2020","unstructured":"Ozge Mercanoglu Sincan and Hacer Yalim Keles. 2020. Autsl: A large scale multi-modal turkish sign language dataset and baseline methods. IEEE access 8 (2020), 181340\u2013181355."},{"key":"e_1_2_1_81_1","doi-asserted-by":"crossref","first-page":"8575","DOI":"10.1109\/JSEN.2020.3045135","article-title":"Deep ConvLSTM with self-attention for human activity decoding using wearable sensors","volume":"21","author":"Singh Satya P","year":"2020","unstructured":"Satya P Singh, Madan Kumar Sharma, Aim\u00e9 Lay-Ekuakille, Deepak Gangwar, and Sukrit Gupta. 2020. Deep ConvLSTM with self-attention for human activity decoding using wearable sensors. IEEE Sensors Journal 21, 6 (2020), 8575\u20138582.","journal-title":"IEEE Sensors Journal"},{"key":"e_1_2_1_82_1","volume-title":"Proceedings of the 28th ACM international conference on multimedia. 1366\u20131375","author":"Sridhar Advaith","year":"2020","unstructured":"Advaith Sridhar, Rohith Gandhi Ganesan, Pratyush Kumar, and Mitesh Khapra. 2020. Include: A large scale dataset for indian sign language recognition. In Proceedings of the 28th ACM international conference on multimedia. 1366\u20131375."},{"key":"e_1_2_1_83_1","first-page":"184","article-title":"Popsign ASL v1. 0: An isolated american sign language dataset collected via smartphones","volume":"36","author":"Starner Thad","year":"2023","unstructured":"Thad Starner, Sean Forbes, Matthew So, David Martin, Rohit Sridhar, Gururaj Deshpande, Sam Sepah, Sahir Shahryar, Khushi Bhardwaj, Tyler Kwok, et al. 2023. Popsign ASL v1. 0: An isolated american sign language dataset collected via smartphones. Advances in Neural Information Processing Systems 36 (2023), 184\u2013196.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_84_1","first-page":"1","article-title":"Tramba: A hybrid transformer and mamba architecture for practical audio and bone conduction speech super resolution and enhancement on mobile and wearable platforms","volume":"8","author":"Sui Yueyuan","year":"2024","unstructured":"Yueyuan Sui, Minghui Zhao, Junxi Xia, Xiaofan Jiang, and Stephen Xia. 2024. Tramba: A hybrid transformer and mamba architecture for practical audio and bone conduction speech super resolution and enhancement on mobile and wearable platforms. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 8, 4 (2024), 1\u201329.","journal-title":"Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies"},{"key":"e_1_2_1_85_1","volume-title":"Chameleon: Mixed-modal early-fusion foundation models. arXiv preprint arXiv:2405.09818","author":"Team Chameleon","year":"2024","unstructured":"Chameleon Team. 2024. Chameleon: Mixed-modal early-fusion foundation models. arXiv preprint arXiv:2405.09818 (2024)."},{"key":"e_1_2_1_86_1","unstructured":"Texas Instruments. 2014. IWR1443BOOST: Single-Chip mmWave Sensor Evaluation Module. https:\/\/www.ti.com\/tool\/IWR1443BOOST. Accessed: 2025-10-09."},{"key":"e_1_2_1_87_1","volume-title":"Proceedings of the IEEE international conference on computer vision. 4489\u20134497","author":"Tran Du","year":"2015","unstructured":"Du Tran, Lubomir Bourdev, Rob Fergus, Lorenzo Torresani, and Manohar Paluri. 2015. Learning spatiotemporal features with 3d convolutional networks. In Proceedings of the IEEE international conference on computer vision. 4489\u20134497."},{"key":"e_1_2_1_88_1","volume-title":"Proceedings of the conference. Association for computational linguistics. Meeting","volume":"2019","author":"Hubert Tsai Yao-Hung","year":"2019","unstructured":"Yao-Hung Hubert Tsai, Shaojie Bai, Paul Pu Liang, J Zico Kolter, Louis-Philippe Morency, and Ruslan Salakhutdinov. 2019. Multimodal transformer for unaligned multimodal language sequences. In Proceedings of the conference. Association for computational linguistics. Meeting, Vol. 2019. 6558."},{"key":"e_1_2_1_89_1","volume-title":"First 100 Signs: American Sign Language (ASL). https:\/\/www.lifeprint.com\/asl101\/pages-layout\/concepts.htm. https:\/\/www.lifeprint.com\/asl101\/pages-layout\/concepts.htm Lifeprint.com","author":"Vicars William","unstructured":"William Vicars. 2025. First 100 Signs: American Sign Language (ASL). https:\/\/www.lifeprint.com\/asl101\/pages-layout\/concepts.htm. https:\/\/www.lifeprint.com\/asl101\/pages-layout\/concepts.htm Lifeprint.com, ASL University."},{"key":"e_1_2_1_90_1","volume-title":"WitMotion Shenzhen Co","year":"2021","unstructured":"Ltd. WitMotion Shenzhen Co. 2021. BWT901CL Bluetooth 2.0 9-Axis IMU Sensor. https:\/\/www.wit-motion.com\/BLE\/50.html Accessed: 2025-10-09."},{"key":"e_1_2_1_91_1","unstructured":"World Federation of the Deaf. 2023. About the WFD. https:\/\/wfdeaf.org\/. Accessed: 2025-10-19."},{"key":"e_1_2_1_92_1","first-page":"1","article-title":"VibRun: Real-time unobtrusive gait analysis for treadmill running via footstep vibrations","volume":"9","author":"Wu Tianhao","year":"2025","unstructured":"Tianhao Wu, Yi Wu, Bibek Poudel, Syed Irfan Ali Meerza, Rajasi Gore Athawale, Weizi Li, Zan Gao, \u00c7a\u011fdas Karata\u015e, and Jian Liu. 2025. VibRun: Real-time unobtrusive gait analysis for treadmill running via footstep vibrations. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 9, 3 (2025), 1\u201325.","journal-title":"Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies"},{"key":"e_1_2_1_93_1","volume-title":"Proceedings of the European conference on computer vision (ECCV). 305\u2013321","author":"Xie Saining","year":"2018","unstructured":"Saining Xie, Chen Sun, Jonathan Huang, Zhuowen Tu, and Kevin Murphy. 2018. Rethinking spatiotemporal feature learning: Speed-accuracy trade-offs in video classification. In Proceedings of the European conference on computer vision (ECCV). 305\u2013321."},{"key":"e_1_2_1_94_1","volume-title":"Proceedings of the AAAI conference on artificial intelligence","volume":"32","author":"Yan Sijie","year":"2018","unstructured":"Sijie Yan, Yuanjun Xiong, and Dahua Lin. 2018. Spatial temporal graph convolutional networks for skeleton-based action recognition. In Proceedings of the AAAI conference on artificial intelligence, Vol. 32."},{"key":"e_1_2_1_95_1","first-page":"539","article-title":"Hand gesture recognition using deep feature fusion network based on wearable sensors","volume":"21","author":"Yuan Guan","year":"2020","unstructured":"Guan Yuan, Xiao Liu, Qiuyan Yan, Shaojie Qiao, Zhixiao Wang, and Li Yuan. 2020. Hand gesture recognition using deep feature fusion network based on wearable sensors. IEEE Sensors Journal 21, 1 (2020), 539\u2013547.","journal-title":"IEEE Sensors Journal"},{"key":"e_1_2_1_96_1","volume-title":"Joint Pattern Recognition Symposium. Springer, 401\u2013408","author":"Zahedi Morteza","year":"2005","unstructured":"Morteza Zahedi, Daniel Keysers, Thomas Deselaers, and Hermann Ney. 2005. Combination of tangent distance and an image distortion model for appearance-based sign language recognition. In Joint Pattern Recognition Symposium. Springer, 401\u2013408."},{"key":"e_1_2_1_97_1","volume-title":"Recurrent neural network regularization. arXiv preprint arXiv: 1409.2329","author":"Zaremba Wojciech","year":"2014","unstructured":"Wojciech Zaremba, Ilya Sutskever, and Oriol Vinyals. 2014. Recurrent neural network regularization. arXiv preprint arXiv: 1409.2329 (2014)."},{"key":"e_1_2_1_98_1","doi-asserted-by":"crossref","first-page":"21026","DOI":"10.1109\/JIOT.2023.3284496","article-title":"Unsupervised domain adaptation for rf-based gesture recognition","volume":"10","author":"Zhang Bin-Bin","year":"2023","unstructured":"Bin-Bin Zhang, Dongheng Zhang, Yadong Li, Yang Hu, and Yan Chen. 2023. Unsupervised domain adaptation for rf-based gesture recognition. IEEE Internet of Things Journal 10, 23(2023), 21026\u201321038.","journal-title":"IEEE Internet of Things Journal"},{"key":"e_1_2_1_99_1","volume-title":"Mediapipe hands: On-device real-time hand tracking. arXiv preprint arXiv:2006.10214","author":"Zhang Fan","year":"2020","unstructured":"Fan Zhang, Valentin Bazarevsky, Andrey Vakunov, Andrei Tkachenka, George Sung, Chuo-Ling Chang, and Matthias Grundmann. 2020. Mediapipe hands: On-device real-time hand tracking. arXiv preprint arXiv:2006.10214 (2020)."},{"key":"e_1_2_1_100_1","first-page":"1","volume-title":"Proceedings of the ACM on interactive, mobile, wearable and ubiquitous technologies 6","author":"Zhang Qian","year":"2022","unstructured":"Qian Zhang, JiaZhen Jing, Dong Wang, and Run Zhao. 2022. Wearsign: Pushing the limit of sign language translation using inertial and emg wearables. Proceedings of the ACM on interactive, mobile, wearable and ubiquitous technologies 6, 1 (2022), 1\u201327."},{"key":"e_1_2_1_101_1","volume-title":"Evf-sam: Early vision-language fusion for text-prompted segment anything model. arXiv preprint arXiv:2406.20076","author":"Zhang Yuxuan","year":"2024","unstructured":"Yuxuan Zhang, Tianheng Cheng, Lianghui Zhu, Rui Hu, Lei Liu, Heng Liu, Longjin Ran, Xiaoxin Chen, Wenyu Liu, and Xinggang Wang. 2024. Evf-sam: Early vision-language fusion for text-prompted segment anything model. arXiv preprint arXiv:2406.20076 (2024)."},{"key":"e_1_2_1_102_1","doi-asserted-by":"crossref","first-page":"11428","DOI":"10.1109\/TPAMI.2023.3274783","article-title":"A unified multimodal de-and re-coupling framework for rgb-d motion recognition","volume":"45","author":"Zhou Benjia","year":"2023","unstructured":"Benjia Zhou, Pichao Wang, Jun Wan, Yanyan Liang, and Fan Wang. 2023. A unified multimodal de-and re-coupling framework for rgb-d motion recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence 45, 10 (2023), 11428\u201311442.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_2_1_103_1","first-page":"1","article-title":"MASTER: A multi-modal foundation model for human activity recognition","volume":"9","author":"Zhu Guanzhou","year":"2025","unstructured":"Guanzhou Zhu, Dong Zhao, Chunliang Li, Mingyue Zhao, Zhengyuan Zhang, Hefeng Quan, and Huadong Ma. 2025. MASTER: A multi-modal foundation model for human activity recognition. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 9, 3 (2025), 1\u201326.","journal-title":"Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies"}],"container-title":["Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3810202","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T17:18:20Z","timestamp":1781543900000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3810202"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,15]]},"references-count":103,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,6,15]]}},"alternative-id":["10.1145\/3810202"],"URL":"https:\/\/doi.org\/10.1145\/3810202","relation":{},"ISSN":["2474-9567"],"issn-type":[{"value":"2474-9567","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,15]]},"assertion":[{"value":"2026-06-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}