{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T22:39:22Z","timestamp":1764715162105,"version":"3.41.2"},"reference-count":108,"publisher":"Association for Computing Machinery (ACM)","issue":"3","license":[{"start":{"date-parts":[[2023,9,27]],"date-time":"2023-09-27T00:00:00Z","timestamp":1695772800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["SaTC-1801472, CSR-1526237"],"award-info":[{"award-number":["SaTC-1801472, CSR-1526237"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Proc. ACM Interact. Mob. Wearable Ubiquitous Technol."],"published-print":{"date-parts":[[2023,9,27]]},"abstract":"<jats:p>The use of audio and video modalities for Human Activity Recognition (HAR) is common, given the richness of the data and the availability of pre-trained ML models using a large corpus of labeled training data. However, audio and video sensors also lead to significant consumer privacy concerns. Researchers have thus explored alternate modalities that are less privacy-invasive such as mmWave doppler radars, IMUs, motion sensors. However, the key limitation of these approaches is that most of them do not readily generalize across environments and require significant in-situ training data. Recent work has proposed cross-modality transfer learning approaches to alleviate the lack of trained labeled data with some success. In this paper, we generalize this concept to create a novel system called VAX (Video\/Audio to 'X'), where training labels acquired from existing Video\/Audio ML models are used to train ML models for a wide range of 'X' privacy-sensitive sensors. Notably, in VAX, once the ML models for the privacy-sensitive sensors are trained, with little to no user involvement, the Audio\/Video sensors can be removed altogether to protect the user's privacy better. We built and deployed VAX in ten participants' homes while they performed 17 common activities of daily living. Our evaluation results show that after training, VAX can use its onboard camera and microphone to detect approximately 15 out of 17 activities with an average accuracy of 90%. For these activities that can be detected using a camera and a microphone, VAX trains a per-home model for the privacy-preserving sensors. These models (average accuracy = 84%) require no in-situ user input. In addition, when VAX is augmented with just one labeled instance for the activities not detected by the VAX A\/V pipeline (~2 out of 17), it can detect all 17 activities with an average accuracy of 84%. Our results show that VAX is significantly better than a baseline supervised-learning approach of using one labeled instance per activity in each home (average accuracy of 79%) since VAX reduces the user burden of providing activity labels by 8x (~2 labels vs. 17 labels).<\/jats:p>","DOI":"10.1145\/3610907","type":"journal-article","created":{"date-parts":[[2023,9,27]],"date-time":"2023-09-27T15:45:03Z","timestamp":1695829503000},"page":"1-24","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["VAX"],"prefix":"10.1145","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0034-2767","authenticated-orcid":false,"given":"Prasoon","family":"Patidar","sequence":"first","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1237-7545","authenticated-orcid":false,"given":"Mayank","family":"Goel","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9304-6080","authenticated-orcid":false,"given":"Yuvraj","family":"Agarwal","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,9,27]]},"reference":[{"key":"e_1_2_2_1_1","volume-title":"Fifteenth Symposium on Usable Privacy and Security (SOUPS 2019","author":"Abdi Noura","year":"2019","unstructured":"Noura Abdi, Kopo M. Ramokapane, and Jose M. Such. 2019. More than Smart Speakers: Security and Privacy Perceptions of Smart Home Personal Assistants. In Fifteenth Symposium on Usable Privacy and Security (SOUPS 2019). USENIX Association, Santa Clara, CA, 451--466. https:\/\/www.usenix.org\/conference\/soups2019\/presentation\/abdi"},{"key":"e_1_2_2_2_1","unstructured":"Sami Abu-El-Haija Nisarg Kothari Joonseok Lee Paul Natsev George Toderici Balakrishnan Varadarajan and Sudheendra Vijayanarasimhan. 2016. YouTube-8M: A Large-Scale Video Classification Benchmark. arXiv:1609.08675 [cs.CV]"},{"key":"e_1_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.3390\/rs12213591"},{"key":"e_1_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.3390\/s19173808"},{"key":"e_1_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445138"},{"key":"e_1_2_2_6_1","unstructured":"Reed Albergotti. 2019. How Nest designed to keep intruders out of people's homes effectively allowed hackers to get in researchers claim. https:\/\/www.washingtonpost.com\/technology\/2019\/04\/23\/how-nest-designed-keep-intruders-out-peoples-homes-effectively-allowed-hackers-get\/?noredirect=on."},{"key":"e_1_2_2_7_1","unstructured":"India Ashok. 2016. Hackers leave Finnish residents cold after DDoS attack knocks out heating systems. https:\/\/www.ibtimes.co.uk\/hackers-leave-finnish-residents-cold-after-ddos-attack-knocks-out-heating-systems-1590639."},{"key":"e_1_2_2_8_1","volume-title":"Proceedings of the 30th International Conference on Neural Information Processing Systems","author":"Aytar Yusuf","year":"2016","unstructured":"Yusuf Aytar, Carl Vondrick, and Antonio Torralba. 2016. SoundNet: Learning Sound Representations from Unlabeled Video. In Proceedings of the 30th International Conference on Neural Information Processing Systems (Barcelona, Spain) (NIPS'16). Curran Associates Inc., Red Hook, NY, USA, 892--900."},{"key":"e_1_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2971648.2971719"},{"key":"e_1_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2528282.2528301"},{"key":"e_1_2_2_11_1","unstructured":"Gedas Bertasius Heng Wang and Lorenzo Torresani. 2021. Is Space-Time Attention All You Need for Video Understanding? arXiv:2102.05095 [cs.CV]"},{"key":"e_1_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3494994"},{"key":"e_1_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580865"},{"key":"e_1_2_2_14_1","unstructured":"Bosch. 2022. Cross Domain Development Kit | XDK. https:\/\/www.bosch-connectivity.com\/media\/downloads\/xdk\/xdk_node_110_combined_datasheet.pdf."},{"key":"e_1_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3432224"},{"key":"e_1_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1177\/154193120605000203"},{"key":"e_1_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/asaa011"},{"key":"e_1_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7899664"},{"key":"e_1_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3380985"},{"key":"e_1_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3380985"},{"key":"e_1_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.5555\/1622407.1622416"},{"key":"e_1_2_2_23_1","volume-title":"Chen Change Loy, and Dahua Lin","author":"Chen Kai","year":"2019","unstructured":"Kai Chen, Jiaqi Wang, Jiangmiao Pang, Yuhang Cao, Yu Xiong, Xiaoxiao Li, Shuyang Sun, Wansen Feng, Ziwei Liu, Jiarui Xu, Zheng Zhang, Dazhi Cheng, Chenchen Zhu, Tianheng Cheng, Qijie Zhao, Buyu Li, Xin Lu, Rui Zhu, Yue Wu, Jifeng Dai, Jingdong Wang, Jianping Shi, Wanli Ouyang, Chen Change Loy, and Dahua Lin. 2019. MMDetection: Open MMLab Detection Toolbox and Benchmark. arXiv:1906.07155 [cs.CV]"},{"key":"e_1_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/HealthCom.2016.7749457"},{"key":"e_1_2_2_25_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3478119","article-title":"Sensecollect: We need efficient ways to collect on-body sensor-based human activity data! Proceedings of the ACM on Interactive","volume":"5","author":"Chen Wenqiang","year":"2021","unstructured":"Wenqiang Chen, Shupei Lin, Elizabeth Thompson, and John Stankovic. 2021. Sensecollect: We need efficient ways to collect on-body sensor-based human activity data! Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 5, 3 (2021), 1--27.","journal-title":"Mobile, Wearable and Ubiquitous Technologies"},{"key":"e_1_2_2_26_1","volume-title":"Salim","author":"Deldari Shohreh","year":"2022","unstructured":"Shohreh Deldari, Hao Xue, Aaqib Saeed, Jiayuan He, Daniel V. Smith, and Flora D. Salim. 2022. Beyond Just Vision: A Review on Self-Supervised Representation Learning on Multimodal and Temporal Data. arXiv:2206.02353 [cs.LG]"},{"key":"e_1_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3550316"},{"key":"e_1_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020"},{"key":"e_1_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207532"},{"key":"e_1_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548546"},{"key":"e_1_2_2_31_1","volume-title":"Revisiting Skeleton-based Action Recognition. In 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE","author":"Duan Haodong","year":"2022","unstructured":"Haodong Duan, Yue Zhao, Kai Chen, Dahua Lin, and Bo Dai. 2022. Revisiting Skeleton-based Action Recognition. In 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, New Orleans, LA, USA, 2959--2968. https:\/\/doi.org\/10.1109\/ CVPR52688.2022.00298"},{"key":"e_1_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP40001.2021.00112"},{"key":"e_1_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300764"},{"key":"e_1_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/RADAR.2019.8835589"},{"key":"e_1_2_2_35_1","doi-asserted-by":"crossref","unstructured":"Christoph Feichtenhofer. 2020. X3D: Expanding Architectures for Efficient Video Recognition. arXiv:2004.04730 [cs.CV]","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"e_1_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"e_1_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"e_1_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01232"},{"key":"e_1_2_2_39_1","unstructured":"Emily Green. 2018. Hacker terrorizes family by hijacking baby monitor. https:\/\/nordvpn.com\/blog\/baby-monitor-iot-hacking\/."},{"key":"e_1_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00633"},{"key":"e_1_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/PERCOM56429.2023.10099197"},{"key":"e_1_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"e_1_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2020.102738"},{"key":"e_1_2_2_44_1","unstructured":"Texas Instruments. 2017. Awr1642 single-chip 77-and 79-ghz fmcw radar sensor. 60 pages."},{"key":"e_1_2_2_45_1","volume-title":"Dca1000evm data capture card. Retrieved May 17","author":"Instruments Texas","year":"2018","unstructured":"Texas Instruments. 2018. Dca1000evm data capture card. Retrieved May 17 (2018), 2022."},{"key":"e_1_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/AFGR.1998.670996"},{"key":"e_1_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3517246"},{"key":"e_1_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3517602"},{"key":"e_1_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2019.08.100"},{"key":"e_1_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-72957-8_3"},{"key":"e_1_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.3390\/computers2020088"},{"key":"e_1_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"e_1_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411841"},{"key":"e_1_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3242587.3242609"},{"key":"e_1_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300559"},{"key":"e_1_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3025453.3025773"},{"key":"e_1_2_2_57_1","volume-title":"A survey on human activity recognition using wearable sensors","author":"Lara Oscar D","year":"2012","unstructured":"Oscar D Lara and Miguel A Labrador. 2012. A survey on human activity recognition using wearable sensors. IEEE communications surveys & tutorials 15, 3 (2012), 1192--1209."},{"key":"e_1_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2948102"},{"key":"e_1_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.3390\/rs11091068"},{"key":"e_1_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544794.3558471"},{"key":"e_1_2_2_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"e_1_2_2_62_1","doi-asserted-by":"publisher","DOI":"10.3390\/a13110301"},{"key":"e_1_2_2_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2916873"},{"key":"e_1_2_2_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3369816"},{"key":"e_1_2_2_65_1","volume-title":"TAM: Temporal Adaptive Module for Video Recognition. arXiv:2005.06803 [cs.CV]","author":"Liu Zhaoyang","year":"2021","unstructured":"Zhaoyang Liu, Limin Wang, Wayne Wu, Chen Qian, and Tong Lu. 2021. TAM: Temporal Adaptive Module for Video Recognition. arXiv:2005.06803 [cs.CV]"},{"volume-title":"OpenPose: Whole-body pose estimation. Ph. D. Dissertation. Master's Thesis","author":"Mart\u0131nez Gin\u00e9s Hidalgo","key":"e_1_2_2_66_1","unstructured":"Gin\u00e9s Hidalgo Mart\u0131nez. 2019. OpenPose: Whole-body pose estimation. Ph. D. Dissertation. Master's Thesis, Carnegie Mellon University."},{"key":"e_1_2_2_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/3427477.3429463"},{"key":"e_1_2_2_68_1","unstructured":"Mites.io. 2020. Mites.io: a full-stack ubiquitous sensing platform. https:\/\/mites.io\/."},{"key":"e_1_2_2_69_1","unstructured":"MMAction2. 2020. OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark. https:\/\/github.com\/open-mmlab\/mmaction2."},{"key":"e_1_2_2_70_1","unstructured":"MMPose. 2020. OpenMMLab Pose Estimation Toolbox and Benchmark. https:\/\/github.com\/open-mmlab\/mmpose."},{"key":"e_1_2_2_71_1","doi-asserted-by":"publisher","DOI":"10.1145\/3550284"},{"key":"e_1_2_2_72_1","volume-title":"Andreu Catal\u00e0 Mallofr\u00e9, and Matthias P\u00e4tzold.","author":"Muaaz Muhammad","year":"2020","unstructured":"Muhammad Muaaz, Ali Chelli, Ahmed Abdelmonem Abdelgawwad, Andreu Catal\u00e0 Mallofr\u00e9, and Matthias P\u00e4tzold. 2020. WiWeHAR: Multimodal human activity recognition using Wi-Fi and wearable sensing modalities. IEEE access 8 (2020), 164453--164470."},{"key":"e_1_2_2_73_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123021.3123046"},{"key":"e_1_2_2_74_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.12125"},{"key":"e_1_2_2_75_1","doi-asserted-by":"publisher","DOI":"10.3390\/s16010115"},{"key":"e_1_2_2_76_1","doi-asserted-by":"publisher","DOI":"10.1145\/3360322.3360851"},{"key":"e_1_2_2_77_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-020-09904-8"},{"key":"e_1_2_2_78_1","doi-asserted-by":"publisher","DOI":"10.1145\/3214277"},{"key":"e_1_2_2_79_1","doi-asserted-by":"publisher","DOI":"10.1509\/jppm.19.1.27.16941"},{"key":"e_1_2_2_80_1","volume-title":"VAX: Open-source repository for the VAX system. https:\/\/github.com\/synergylabs\/vax.","author":"Patidar Prasoon","year":"2023","unstructured":"Prasoon Patidar, Mayank Goel, Yuvraj Agarwal. 2023. VAX: Open-source repository for the VAX system. https:\/\/github.com\/synergylabs\/vax."},{"key":"e_1_2_2_81_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.pmcj.2022.101726"},{"key":"e_1_2_2_82_1","doi-asserted-by":"publisher","DOI":"10.1145\/3351242"},{"key":"e_1_2_2_83_1","doi-asserted-by":"publisher","DOI":"10.1109\/MPRV.2012.17"},{"key":"e_1_2_2_84_1","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1254"},{"key":"e_1_2_2_85_1","doi-asserted-by":"publisher","DOI":"10.1177\/1550147716665520"},{"key":"e_1_2_2_86_1","volume-title":"You Know Too Much: Investigating Users' Perceptions and Privacy Concerns Towards Thermal Imaging. In Privacy Symposium","author":"Sahoo Lipsarani","year":"2022","unstructured":"Lipsarani Sahoo, Nazmus Sakib Miazi, Mohamed Shehab, Florian Alt, and Yomna Abdelrahman. 2022. You Know Too Much: Investigating Users' Perceptions and Privacy Concerns Towards Thermal Imaging. In Privacy Symposium 2022, Stefan Schiffner, Sebastien Ziegler, and Adrian Quesada Rodriguez (Eds.). Springer International Publishing, Cham, 207--229."},{"key":"e_1_2_2_87_1","unstructured":"Alex Schiffer. 2017. How a fish tank helped hack a casino. https:\/\/www.washingtonpost.com\/news\/innovations\/wp\/2017\/07\/21\/how-a-fish-tank-helped-hack-a-casino\/?noredirect=on."},{"key":"e_1_2_2_88_1","doi-asserted-by":"crossref","unstructured":"Amir Shahroudy Jun Liu Tian-Tsong Ng and Gang Wang. 2016. NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis. arXiv:1604.02808 [cs.CV]","DOI":"10.1109\/CVPR.2016.115"},{"key":"e_1_2_2_89_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6872"},{"key":"e_1_2_2_90_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01230"},{"key":"e_1_2_2_91_1","doi-asserted-by":"publisher","DOI":"10.1145\/3349624.3356768"},{"key":"e_1_2_2_92_1","volume-title":"Amir Roshan Zamir, and Mubarak Shah","author":"Soomro Khurram","year":"2012","unstructured":"Khurram Soomro, Amir Roshan Zamir, and Mubarak Shah. 2012. UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild. arXiv:1212.0402 [cs.CV]"},{"key":"e_1_2_2_93_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_20"},{"key":"e_1_2_2_94_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00584"},{"key":"e_1_2_2_95_1","doi-asserted-by":"publisher","DOI":"10.1109\/AISP53593.2022"},{"key":"e_1_2_2_96_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"e_1_2_2_97_1","doi-asserted-by":"publisher","DOI":"10.1109\/RADAR42522.2020.9114643"},{"key":"e_1_2_2_98_1","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2015.00028"},{"key":"e_1_2_2_99_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"e_1_2_2_100_1","doi-asserted-by":"publisher","unstructured":"Pete Warden Matthew Stewart Brian Plancher Colby Banbury Shvetank Prakash Emma Chen Zain Asgar Sachin Katti and Vijay Janapa Reddi. 2022. Machine Learning Sensors. https:\/\/doi.org\/10.48550\/ARXIV.2206.03266","DOI":"10.48550\/ARXIV.2206.03266"},{"key":"e_1_2_2_101_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00037"},{"key":"e_1_2_2_102_1","doi-asserted-by":"publisher","DOI":"10.1145\/3486611.3492234"},{"key":"e_1_2_2_103_1","doi-asserted-by":"crossref","unstructured":"Sijie Yan Yuanjun Xiong and Dahua Lin. 2018. Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition. In Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence and Thirtieth Innovative Applications of Artificial Intelligence Conference and Eighth AAAI Symposium on Educational Advances in Artificial Intelligence (AAAI'18\/IAAI'18\/EAAI'18). AAAI Press New Orleans Louisiana USA Article 912 9 pages.","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"e_1_2_2_104_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00067"},{"key":"e_1_2_2_105_1","volume-title":"An Intelligent Voice Interaction System Based on Raspberry Pi. In 2019 11th International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC)","volume":"1","author":"Yang Deju","year":"2019","unstructured":"Deju Yang, Liangli Ma, and Fei Liao. 2019. An Intelligent Voice Interaction System Based on Raspberry Pi. In 2019 11th International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC), Vol. 1. IEEE, Hangzhou, China, 237--240. https:\/\/doi.org\/10. 1109\/IHMSC.2019.00062"},{"key":"e_1_2_2_106_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.07.030"},{"key":"e_1_2_2_107_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207686"},{"key":"e_1_2_2_108_1","doi-asserted-by":"crossref","unstructured":"Bolei Zhou Alex Andonian Aude Oliva and Antonio Torralba. 2018. Temporal Relational Reasoning in Videos. arXiv:1711.08496 [cs.CV]","DOI":"10.1007\/978-3-030-01246-5_49"}],"container-title":["Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3610907","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3610907","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3610907","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,28]],"date-time":"2025-07-28T16:29:30Z","timestamp":1753720170000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3610907"}},"subtitle":["Using Existing Video and Audio-based Activity Recognition Models to Bootstrap Privacy-Sensitive Sensors"],"short-title":[],"issued":{"date-parts":[[2023,9,27]]},"references-count":108,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2023,9,27]]}},"alternative-id":["10.1145\/3610907"],"URL":"https:\/\/doi.org\/10.1145\/3610907","relation":{},"ISSN":["2474-9567"],"issn-type":[{"type":"electronic","value":"2474-9567"}],"subject":[],"published":{"date-parts":[[2023,9,27]]},"assertion":[{"value":"2023-09-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}