{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,26]],"date-time":"2026-04-26T03:50:32Z","timestamp":1777175432088,"version":"3.51.4"},"reference-count":86,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62036012"],"award-info":[{"award-number":["62036012"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U23A20387"],"award-info":[{"award-number":["U23A20387"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62322212"],"award-info":[{"award-number":["62322212"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072455"],"award-info":[{"award-number":["62072455"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1109\/tpami.2024.3367412","type":"journal-article","created":{"date-parts":[[2024,2,20]],"date-time":"2024-02-20T18:50:02Z","timestamp":1708455002000},"page":"5345-5361","source":"Crossref","is-referenced-by-count":34,"title":["Cross-Modal Federated Human Activity Recognition"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5453-9755","authenticated-orcid":false,"given":"Xiaoshan","family":"Yang","sequence":"first","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9799-2898","authenticated-orcid":false,"given":"Baochen","family":"Xiong","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7819-2247","authenticated-orcid":false,"given":"Yi","family":"Huang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8343-9665","authenticated-orcid":false,"given":"Changsheng","family":"Xu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"24206","article-title":"VATT: Transformers for multimodal self-supervised learning from raw video, audio and text","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Akbari"},{"key":"ref2","article-title":"Federated learning with personalization layers","author":"Arivazhagan","year":"2019"},{"key":"ref3","article-title":"FedDis: Disentangled federated learning for unsupervised brain pathology segmentation","author":"Bercea","year":"2021"},{"key":"ref4","first-page":"343","article-title":"Domain separation networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Bousmalis"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2499621"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3550289"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995707"},{"key":"ref9","first-page":"2089","article-title":"Exploiting shared representations for personalized federated learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Collins"},{"key":"ref10","first-page":"753","article-title":"Scaling egocentric vision: The epic-kitchens dataset","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Damen"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01531-2"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref13","first-page":"21394","article-title":"Personalized federated learning with moreau envelopes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dinh"},{"key":"ref14","first-page":"638","article-title":"Evaluation of federated learning aggregation algorithms: Application to human activity recognition","volume-title":"Proc. ACM Int. Joint Conf. Pervasive Ubiquitous Comput. Proc. ACM Int. Symp. Wearable Comput.","author":"Sannara"},{"key":"ref15","first-page":"3557","article-title":"Personalized federated learning with theoretical guarantees: A model-agnostic meta-learning approach","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Fallah"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref17","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn"},{"issue":"1","key":"ref18","first-page":"11","article-title":"Joint amplitude and frequency analysis of tremor activity","volume":"39","author":"Foerster","year":"1999","journal-title":"Electromyogr Clin Neurophysiol."},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2017.27"},{"key":"ref20","first-page":"1180","article-title":"Unsupervised domain adaptation by backpropagation","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","author":"Ganin"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-09176-6_9"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351053"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref25","first-page":"1","article-title":"beta-VAE: Learning basic visual concepts with a constrained variational framework","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Higgins"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2016.7552937"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-021-00875-6"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3409332"},{"key":"ref29","article-title":"Federated action recognition on heterogeneous embedded devices","author":"Jain","year":"2021"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00559"},{"key":"ref31","article-title":"With a little help from my temporal context: Multimodal egocentric action recognition","volume-title":"Proc. 32nd Brit. Mach. Vis. Conf.","author":"Kazakos"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TITB.2010.2051955"},{"key":"ref33","first-page":"2654","article-title":"Disentangling by factorising","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref34","first-page":"1","article-title":"Auto-encoding variational Bayes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3447993.3488031"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450006"},{"key":"ref37","article-title":"VisualBERT: A simple and performant baseline for vision and language","author":"Li","year":"2019"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01057"},{"key":"ref39","first-page":"429","article-title":"Federated optimization in heterogeneous networks","volume-title":"Proc. Mach. Learn. Syst.","author":"Li"},{"key":"ref40","first-page":"1","article-title":"FedBN: Federated learning on non-IID features via local batch normalization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.10.011"},{"key":"ref42","article-title":"Think locally, act globally: Federated learning with local and global representations","author":"Liang","year":"2020"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299000"},{"key":"ref44","first-page":"13","article-title":"VilBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref45","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. Artif. Intell. Statist.","author":"McMahan"},{"key":"ref46","first-page":"1","article-title":"Long-tail learning via logit adjustment","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Menon"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3390\/s17112556"},{"key":"ref48","first-page":"14200","article-title":"Attention bottlenecks for multimodal fusion","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Nagrani"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.721"},{"key":"ref50","first-page":"2642","article-title":"Conditional image synthesis with auxiliary classifier GANs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Odena"},{"key":"ref51","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Paszke"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00625"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/PerCom53586.2022.9762352"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.621"},{"key":"ref55","first-page":"21554","article-title":"Robust federated learning: The case of affine distribution shifts","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Reisizadeh"},{"key":"ref56","first-page":"1","article-title":"Improved spatio-temporal salient feature detection for action recognition","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"David"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/475"},{"key":"ref58","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Simonyan"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2016.54"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472171"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/BDCloud.2018.00164"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01019"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.341"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"issue":"86","key":"ref66","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2017.2722870"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123326"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref70","first-page":"1","article-title":"Federated learning with matched averaging","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","year":"2020"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299059"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6907"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1177\/1729881417709079"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019005"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107338"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.01.063"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/IJCB48548.2020.9304895"},{"key":"ref78","first-page":"3995","article-title":"Deep convolutional neural networks on multichannel time series for human activity recognition","volume-title":"Proc. Int. Joint Conf. Artif. Intell.","author":"Yang"},{"key":"ref79","first-page":"20","article-title":"Activity recognition: Linking low-level sensors to high-level intelligence","volume-title":"Proc. Int. Joint Conf. Artif. Intell.","author":"Yang"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20213"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2874455"},{"key":"ref82","first-page":"10946","article-title":"Federated learning with only positive labels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yu"},{"key":"ref83","first-page":"1","article-title":"RGB-D camera-based activity analysis","volume-title":"Proc. Asia Pacific Signal Inf. Process. Assoc. Annu. Summit Conf.","author":"Zhang"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01434"},{"key":"ref85","article-title":"Federated learning with non-IID data","author":"Zhao","year":"2018"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462989"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10582780\/10440498.pdf?arnumber=10440498","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,4]],"date-time":"2024-07-04T04:05:42Z","timestamp":1720065942000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10440498\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8]]},"references-count":86,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3367412","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8]]}}}