{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T16:55:13Z","timestamp":1767113713317,"version":"3.48.0"},"publisher-location":"New York, NY, USA","reference-count":27,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,12]]},"DOI":"10.1145\/3714394.3756246","type":"proceedings-article","created":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T21:13:49Z","timestamp":1767042829000},"page":"1262-1266","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["MARS: Robust Multi-View Acoustic Learning for Unsupervised Gesture Sensing in VR\/AR Headsets"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-1697-8646","authenticated-orcid":false,"given":"Jiajun","family":"Yu","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7749-6836","authenticated-orcid":false,"given":"Bingzhi","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3549-9035","authenticated-orcid":false,"given":"Yong","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Jiangxi Normal University, Nanchang, Jiangxi, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2716-5369","authenticated-orcid":false,"given":"Yongzhao","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8244-2181","authenticated-orcid":false,"given":"Jie","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan, China"}]}],"member":"320","published-online":{"date-parts":[[2025,12,29]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"34","article-title":"Kernel cca for multi-view learning of acoustic features using articulatory measurements","author":"Arora R.","year":"2012","unstructured":"R. Arora, K. Livescu et al., ''Kernel cca for multi-view learning of acoustic features using articulatory measurements.'' in MLSLP, 2012, pp. 34-37.","journal-title":"MLSLP"},{"key":"e_1_3_2_1_2_1","volume-title":"Spectral networks and locally connected networks on graphs allowbreak,'' arXiv preprint arXiv:1312.6203","author":"Bruna J.","year":"2013","unstructured":"J. Bruna, W. Zaremba, A. Szlam, and Y. LeCun, ''Spectral networks and locally connected networks on graphs allowbreak,'' arXiv preprint arXiv:1312.6203, 2013."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2207676.2208331"},{"key":"e_1_3_2_1_4_1","first-page":"9729","article-title":"Momentum contrast for unsupervised visual representation learning","author":"He K.","year":"2020","unstructured":"K. He, H. Fan, Y. Wu, S. Xie, and R. Girshick, ''Momentum contrast for unsupervised visual representation learning,'' in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 9729-9738.","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403049"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2887094"},{"key":"e_1_3_2_1_7_1","first-page":"0","article-title":"Multi-view representation learning via canonical correlation analysis for dysarthric speech recognition","author":"Kim M.","year":"2018","unstructured":"M. Kim, B. Cao, and J. Wang, ''Multi-view representation learning via canonical correlation analysis for dysarthric speech recognition,'' in Recent Developments in Mechatronics and Intelligent Robotics: Proceedings of International Conference on Mechatronics and Intelligent Robotics (ICMIR2018). hskip 1em plus 0.5em minus 0.4emrelax Springer, 2019, pp. 1085-1095.","journal-title":"Recent Developments in Mechatronics and Intelligent Robotics: Proceedings of International Conference on Mechatronics and Intelligent Robotics (ICMIR"},{"key":"e_1_3_2_1_8_1","first-page":"1","article-title":"approach for few-shot hand gesture recognition","author":"Kimura N.","year":"2022","unstructured":"N. Kimura, ''Self-supervised approach for few-shot hand gesture recognition,'' in Adjunct Proceedings of the 35th Annual ACM Symposium on User Interface Software and Technology, 2022, pp. 1-4.","journal-title":"Adjunct Proceedings of the 35th Annual ACM Symposium on User Interface Software and Technology"},{"key":"e_1_3_2_1_9_1","first-page":"1","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf T. N.","year":"2017","unstructured":"T. N. Kipf and M. Welling, ''Semi-supervised classification with graph convolutional networks,'' in International Conference on Learning Representations, 2017, pp. 1-14.","journal-title":"International Conference on Learning Representations"},{"key":"e_1_3_2_1_10_1","first-page":"3288","article-title":"Unsupervised learning for human sensing using radio signals","author":"Li T.","year":"2022","unstructured":"T. Li, L. Fan, Y. Yuan, and D. Katabi, ''Unsupervised learning for human sensing using radio signals,'' in Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2022, pp. 3288-3297.","journal-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3636534.3649376"},{"issue":"7","key":"e_1_3_2_1_12_1","first-page":"2620","article-title":"Fine-grained gesture sensing and recognition","volume":"21","author":"Ling K.","year":"2020","unstructured":"K. Ling, H. Dai, Y. Liu, A. X. Liu, W. Wang, and Q. Gu, ''Ultragesture: Fine-grained gesture sensing and recognition,'' IEEE Transactions on Mobile Computing, vol. 21, no. 7, pp. 2620-2636, 2020.","journal-title":"IEEE Transactions on Mobile Computing"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2789168.2790122"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3432195"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-020-00180-6"},{"key":"e_1_3_2_1_16_1","first-page":"1","article-title":"Beepbeep: a high accuracy acoustic ranging system using cots mobile devices","author":"Peng C.","year":"2007","unstructured":"C. Peng, G. Shen, Y. Zhang, Y. Li, and K. Tan, ''Beepbeep: a high accuracy acoustic ranging system using cots mobile devices,'' in Proceedings of the 5th International Conference on Embedded Networked Sensor Systems, 2007, pp. 1-14.","journal-title":"Proceedings of the 5th International Conference on Embedded Networked Sensor Systems"},{"key":"e_1_3_2_1_17_1","first-page":"27","article-title":"Av-rir: Audio-visual room impulse response estimation","author":"Ratnarajah A.","year":"2024","unstructured":"A. Ratnarajah, S. Ghosh, S. Kumar, P. Chiniya, and D. Manocha, ''Av-rir: Audio-visual room impulse response estimation,'' in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 27,164-27,175.","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"e_1_3_2_1_18_1","first-page":"31","article-title":"Beyond redundancy: allowbreak information-aware unsupervised multiplex graph structure learning","volume":"37","author":"Shen Z.","year":"2024","unstructured":"Z. Shen, S. Wang, and Z. Kang, ''Beyond redundancy: allowbreak information-aware unsupervised multiplex graph structure learning,'' in Advances in Neural Information Processing Systems, vol. 37, 2024, pp. 31,629-31,658.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"A. Singh P. Rajan and A. Bhavsar ''Deep multi-view features from raw audio for acoustic scene classification '' in Detection and Classification of Acoustic Scenes and Events 2019 Workshop (DCASE2019). hskip 1em plus 0.5em minus 0.4emrelax IEEE 2019 pp. 32-36.","DOI":"10.33682\/05gk-pd08"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102460"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3013166"},{"issue":"4","key":"e_1_3_2_1_22_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3597498","article-title":"Contrastive representation learning framework for ultrasound-based sensing","volume":"20","author":"Wang X.","year":"2024","unstructured":"X. Wang, Z. Yang, W. Wang, H. Dai, S. Shi, and Q. Gu, ''Ultraclr: Contrastive representation learning framework for ultrasound-based sensing,'' ACM Transactions on Sensor Networks, vol. 20, no. 4, pp. 1-23, 2024.","journal-title":"ACM Transactions on Sensor Networks"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102181"},{"issue":"1","key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3643510","article-title":"Aface: Range-flexible anti-spoofing face authentication via smartphone acoustic sensing","volume":"8","author":"Xu Z.","year":"2024","unstructured":"Z. Xu, T. Liu, R. Jiang, P. Hu, Z. Guo, and C. Liu, ''Aface: Range-flexible anti-spoofing face authentication via smartphone acoustic sensing,'' Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, vol. 8, no. 1, pp. 1-33, 2024.","journal-title":"Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies"},{"key":"e_1_3_2_1_25_1","first-page":"1","volume-title":"Soundr: Head position and orientation prediction using a microphone array,'' in Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems","author":"Yang J.","year":"2020","unstructured":"J. Yang, G. Banerjee, V. Gupta, M. S. Lam, and J. A. Landay, ''Soundr: Head position and orientation prediction using a microphone array,'' in Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems, 2020, pp. 1-12."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3659614"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.02.028"}],"event":{"name":"UbiComp '25:The 2025 ACM International Joint Conference on Pervasive and Ubiquitous Computing \/ ISWC ACM International Symposium on Wearable Computers","sponsor":["SIGMOBILE ACM Special Interest Group on Mobility of Systems, Users, Data and Computing","SIGCHI ACM Special Interest Group on Computer-Human Interaction","SIGSPATIAL ACM Special Interest Group on Spatial Information"],"location":"Espoo Finland"},"container-title":["Companion of the 2025 ACM International Joint Conference on Pervasive and Ubiquitous Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3714394.3756246","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T16:53:09Z","timestamp":1767113589000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3714394.3756246"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,12]]},"references-count":27,"alternative-id":["10.1145\/3714394.3756246","10.1145\/3714394"],"URL":"https:\/\/doi.org\/10.1145\/3714394.3756246","relation":{},"subject":[],"published":{"date-parts":[[2025,10,12]]},"assertion":[{"value":"2025-12-29","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}