{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:38:32Z","timestamp":1775230712706,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":82,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,4,19]],"date-time":"2023-04-19T00:00:00Z","timestamp":1681862400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Natural Science Foundation of China (NSFC)","award":["Grant No. 62132010 and No. 62002198"],"award-info":[{"award-number":["Grant No. 62132010 and No. 62002198"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,4,19]]},"DOI":"10.1145\/3544548.3581008","type":"proceedings-article","created":{"date-parts":[[2023,4,20]],"date-time":"2023-04-20T04:28:44Z","timestamp":1681964924000},"page":"1-17","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":18,"title":["Enabling Voice-Accompanying Hand-to-Face Gesture Recognition with Cross-Device Sensing"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8825-0191","authenticated-orcid":false,"given":"Zisu","family":"Li","sequence":"first","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, China and IIP (Computational Media and Arts), The Hong Kong University of Science and Technology, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0579-2716","authenticated-orcid":false,"given":"Chen","family":"Liang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4249-8893","authenticated-orcid":false,"given":"Yuntao","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, China and Global Innovation Exchange (GIX) Insitute, Tsinghua University, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1351-5284","authenticated-orcid":false,"given":"Yue","family":"Qin","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2591-7993","authenticated-orcid":false,"given":"Chun","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Computer science and Technology, Tsinghua University, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7515-3755","authenticated-orcid":false,"given":"Yukang","family":"Yan","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, China and HCII, CMU, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0356-4712","authenticated-orcid":false,"given":"Mingming","family":"Fan","sequence":"additional","affiliation":[{"name":"Computational Media and Arts Thrust, The Hong Kong University of Science and Technology (Guangzhou), China and Division of Integrative Systems and Design, The Hong Kong University of Science and Technology, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2273-6927","authenticated-orcid":false,"given":"Yuanchun","family":"Shi","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, China and Department of Computer Science and Technology, Qinghai University, China"}]}],"member":"320","published-online":{"date-parts":[[2023,4,19]]},"reference":[{"key":"e_1_3_3_3_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3379337.3415588"},{"key":"e_1_3_3_3_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3126594.3126649"},{"key":"e_1_3_3_3_3_1","volume-title":"KDD workshop, Vol.\u00a010","author":"Berndt J","year":"1994","unstructured":"Donald\u00a0J Berndt and James Clifford. 1994. Using dynamic time warping to find patterns in time series.. In KDD workshop, Vol.\u00a010. Seattle, WA, USA:, 359\u2013370."},{"key":"e_1_3_3_3_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysarc.2014.01.006"},{"key":"e_1_3_3_3_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/965105.807503"},{"key":"e_1_3_3_3_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/286498.286726"},{"key":"e_1_3_3_3_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173595"},{"key":"e_1_3_3_3_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/1449715.1449746"},{"key":"e_1_3_3_3_9_1","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2020.00637"},{"key":"e_1_3_3_3_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/BIOCAS.2019.8919210"},{"key":"e_1_3_3_3_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2006.874403"},{"key":"e_1_3_3_3_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISIE.2006.296083"},{"key":"e_1_3_3_3_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3461778.3462004"},{"key":"e_1_3_3_3_14_1","doi-asserted-by":"publisher","unstructured":"J.\u00a0Guillermo Colli-Alfaro Anas Ibrahim and Ana\u00a0Luisa Trejos. 2019. Design of User-Independent Hand Gesture Recognition Using Multilayer Perceptron Networks and Sensor Fusion Techniques. In 2019 IEEE 16th International Conference on Rehabilitation Robotics (ICORR). 1103\u20131108. https:\/\/doi.org\/10.1109\/ICORR.2019.8779533","DOI":"10.1109\/ICORR.2019.8779533"},{"key":"e_1_3_3_3_15_1","unstructured":"Matthieu Courbariaux Yoshua Bengio and Jean-Pierre David. 2014. Training deep neural networks with low precision multiplications. arxiv:1412.7024\u00a0[cs.LG]"},{"key":"e_1_3_3_3_16_1","unstructured":"Tim Dettmers. 2015. 8-Bit Approximations for Parallelism in Deep Learning. arxiv:1511.04561\u00a0[cs.NE]"},{"key":"e_1_3_3_3_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2004.1374748"},{"key":"e_1_3_3_3_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICHR.2006.321298"},{"key":"e_1_3_3_3_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411830"},{"key":"e_1_3_3_3_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/2611009.2611032"},{"key":"e_1_3_3_3_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3379337.3415901"},{"key":"e_1_3_3_3_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSENS.2017.2696520"},{"key":"e_1_3_3_3_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3332165.3347947"},{"key":"e_1_3_3_3_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3432204"},{"key":"e_1_3_3_3_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/2207676.2208331"},{"key":"e_1_3_3_3_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/1866029.1866033"},{"key":"e_1_3_3_3_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2047196.2047233"},{"key":"e_1_3_3_3_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/2047196.2047279"},{"key":"e_1_3_3_3_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2380116.2380187"},{"key":"e_1_3_3_3_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"e_1_3_3_3_31_1","volume-title":"2012 1st Annual IEEE Healthcare Innovation Conference.","author":"Hondori Hossein\u00a0Mousavi","year":"2012","unstructured":"Hossein\u00a0Mousavi Hondori, Maryam Khademi, and Cristina\u00a0V Lopes. 2012. Monitoring intake gestures using sensor fusion (microsoft kinect and inertial sensors) for smart home tele-rehab setting. In 2012 1st Annual IEEE Healthcare Innovation Conference."},{"key":"e_1_3_3_3_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"e_1_3_3_3_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW.2017.14"},{"key":"e_1_3_3_3_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3015783.3015796"},{"key":"e_1_3_3_3_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3098279.3098538"},{"key":"e_1_3_3_3_36_1","doi-asserted-by":"publisher","DOI":"10.17210\/hcik.2016.01.94"},{"key":"e_1_3_3_3_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3242587.3242609"},{"key":"e_1_3_3_3_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/2984511.2984582"},{"key":"e_1_3_3_3_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3242587.3242642"},{"key":"e_1_3_3_3_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123021.3123060"},{"key":"e_1_3_3_3_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/JERM.2019.2949456"},{"key":"e_1_3_3_3_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3569463"},{"key":"e_1_3_3_3_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3478114"},{"key":"e_1_3_3_3_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925953"},{"key":"e_1_3_3_3_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/2807442.2807489"},{"key":"e_1_3_3_3_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2886279"},{"key":"e_1_3_3_3_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449890"},{"key":"e_1_3_3_3_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3380984"},{"key":"e_1_3_3_3_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/2043674.2043723"},{"key":"e_1_3_3_3_50_1","volume-title":"Affective Computing and Intelligent Interaction, Sidney D\u2019Mello, Arthur Graesser, Bj\u00f6rn Schuller, and Jean-Claude Martin (Eds.)","author":"Mahmoud Marwa","unstructured":"Marwa Mahmoud and Peter Robinson. 2011. Interpreting Hand-Over-Face Gestures. In Affective Computing and Intelligent Interaction, Sidney D\u2019Mello, Arthur Graesser, Bj\u00f6rn Schuller, and Jean-Claude Martin (Eds.). Springer Berlin Heidelberg, Berlin, Heidelberg, 248\u2013255."},{"key":"e_1_3_3_3_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/2973750.2973755"},{"key":"e_1_3_3_3_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376479"},{"key":"e_1_3_3_3_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/2858036.2858093"},{"key":"e_1_3_3_3_54_1","volume-title":"European Signal Processing Conference(2010)","author":"Mesaros Annamaria","year":"2010","unstructured":"Annamaria Mesaros, Toni Heittola, Antti Eronen, and Tuomas Virtanen. 2010. Acoustic event detection in real life recordings. European Signal Processing Conference(2010), 1267\u20131271."},{"key":"e_1_3_3_3_55_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_33"},{"key":"e_1_3_3_3_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/1088463.1088470"},{"key":"e_1_3_3_3_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00013"},{"key":"e_1_3_3_3_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/2501988.2501989"},{"key":"e_1_3_3_3_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445687"},{"key":"e_1_3_3_3_60_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_3_3_61_1","volume-title":"Multimodal Database of Emotional Speech, Video and Gestures","author":"Sapi\u0144ski Tomasz","unstructured":"Tomasz Sapi\u0144ski, Dorota Kami\u0144ska, Adam Pelikant, Cagri Ozcinar, Egils Avots, and Gholamreza Anbarjafari. 2019. Multimodal Database of Emotional Speech, Video and Gestures. In Pattern Recognition and Information Forensics, Zhaoxiang Zhang, David Suter, Yingli Tian, Alexandra Branzan\u00a0Albu, Nicolas Sid\u00e8re, and Hugo Jair\u00a0Escalante (Eds.). Springer International Publishing, Cham, 153\u2013163."},{"key":"e_1_3_3_3_62_1","doi-asserted-by":"publisher","DOI":"10.4271\/2017-01-0068"},{"key":"e_1_3_3_3_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/2556288.2556984"},{"key":"e_1_3_3_3_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3025453.3026027"},{"key":"e_1_3_3_3_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053124"},{"key":"e_1_3_3_3_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/3191771"},{"key":"e_1_3_3_3_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/2984511.2984565"},{"key":"e_1_3_3_3_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2933987"},{"key":"e_1_3_3_3_69_1","doi-asserted-by":"publisher","DOI":"10.1145\/1107548.1107578"},{"key":"e_1_3_3_3_70_1","doi-asserted-by":"publisher","DOI":"10.1145\/2858036.2858466"},{"key":"e_1_3_3_3_71_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445484"},{"key":"e_1_3_3_3_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376875"},{"key":"e_1_3_3_3_73_1","doi-asserted-by":"publisher","DOI":"10.1145\/2628363.2628383"},{"key":"e_1_3_3_3_74_1","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376836"},{"key":"e_1_3_3_3_75_1","doi-asserted-by":"publisher","DOI":"10.1145\/3139131.3139146"},{"key":"e_1_3_3_3_76_1","doi-asserted-by":"publisher","DOI":"10.1145\/3332165.3347950"},{"key":"e_1_3_3_3_77_1","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376810"},{"key":"e_1_3_3_3_78_1","doi-asserted-by":"publisher","DOI":"10.1145\/3351276"},{"key":"e_1_3_3_3_79_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300935"},{"key":"e_1_3_3_3_80_1","doi-asserted-by":"publisher","DOI":"10.1145\/3081333.3081356"},{"key":"e_1_3_3_3_81_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"e_1_3_3_3_82_1","doi-asserted-by":"publisher","DOI":"10.1145\/3381008"}],"event":{"name":"CHI '23: CHI Conference on Human Factors in Computing Systems","location":"Hamburg Germany","acronym":"CHI '23","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3544548.3581008","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3544548.3581008","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:47:55Z","timestamp":1750178875000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3544548.3581008"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,19]]},"references-count":82,"alternative-id":["10.1145\/3544548.3581008","10.1145\/3544548"],"URL":"https:\/\/doi.org\/10.1145\/3544548.3581008","relation":{},"subject":[],"published":{"date-parts":[[2023,4,19]]},"assertion":[{"value":"2023-04-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}