{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T08:00:49Z","timestamp":1780473649538,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":57,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,13]]},"DOI":"10.1145\/3589334.3645346","type":"proceedings-article","created":{"date-parts":[[2024,5,8]],"date-time":"2024-05-08T07:08:13Z","timestamp":1715152093000},"page":"2795-2806","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":17,"title":["FreqMAE: Frequency-Aware Masked Autoencoder for Multi-Modal IoT Sensing"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-2520-4941","authenticated-orcid":false,"given":"Denizhan","family":"Kara","sequence":"first","affiliation":[{"name":"University of Illinois Urbana-Champaign, Urbana, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4297-5865","authenticated-orcid":false,"given":"Tomoyoshi","family":"Kimura","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign, Urbana, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7643-7239","authenticated-orcid":false,"given":"Shengzhong","family":"Liu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9285-9872","authenticated-orcid":false,"given":"Jinyang","family":"Li","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign, Urbana, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1288-9734","authenticated-orcid":false,"given":"Dongxin","family":"Liu","sequence":"additional","affiliation":[{"name":"Meta Platforms, Inc, Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3085-1434","authenticated-orcid":false,"given":"Tianshi","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign, Urbana, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1368-1688","authenticated-orcid":false,"given":"Ruijie","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign, Urbana, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8178-8316","authenticated-orcid":false,"given":"Yizhuo","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign, Urbana, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5320-9439","authenticated-orcid":false,"given":"Yigong","family":"Hu","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign, Urbana, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3883-7220","authenticated-orcid":false,"given":"Tarek","family":"Abdelzaher","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign, Urbana, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,5,13]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/0021-9290(85)90043-0"},{"key":"e_1_3_2_2_2_1","volume-title":"Layer normalization. arXiv preprint arXiv:1607.06450","author":"Ba J. L.","year":"2016","unstructured":"J. L. Ba, J. R. Kiros, and G. E. Hinton. Layer normalization. arXiv preprint arXiv:1607.06450, 2016."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00665-5_110"},{"key":"e_1_3_2_2_4_1","volume-title":"International Conference on Learning Representations.","author":"Bao H.","unstructured":"H. Bao, L. Dong, S. Piao, and F.Wei. Beit: Bert pre-training of image transformers. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485730.3485944"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458864.3467885"},{"key":"e_1_3_2_2_7_1","first-page":"1597","volume-title":"International conference on machine learning","author":"Chen T.","year":"2020","unstructured":"T. Chen, S. Kornblith, M. Norouzi, and G. Hinton. A simple framework for contrastive learning of visual representations. In International conference on machine learning, pages 1597--1607. PMLR, 2020."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/WSC52266.2021.9715532"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3550316"},{"issue":"5","key":"e_1_3_2_2_10_1","first-page":"2022","article-title":"Wearable sensor-based human activity recognition with transformer model","volume":"22","author":"Lupt\u00e1kov\u00e1 I. Dirgov\u00e1","year":"1911","unstructured":"I. Dirgov\u00e1 Lupt\u00e1kov\u00e1, M. Kubovc\u00edk, and J. Posp\u00edchal. Wearable sensor-based human activity recognition with transformer model. Sensors, 22(5):1911, 2022.","journal-title":"Sensors"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/324"},{"key":"e_1_3_2_2_12_1","volume-title":"First Workshop on Pre-training: Perspectives, Pitfalls, and Paths Forward at ICML","author":"Geng X.","year":"2022","unstructured":"X. Geng, H. Liu, L. Lee, D. Schuurmans, S. Levine, and P. Abbeel. Multimodal masked autoencoders learn transferable representations. In First Workshop on Pre-training: Perspectives, Pitfalls, and Paths Forward at ICML 2022."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21315"},{"key":"e_1_3_2_2_14_1","volume-title":"The Eleventh International Conference on Learning Representations","author":"Gong Y.","year":"2023","unstructured":"Y. Gong, A. Rouditchenko, A. H. Liu, D. Harwath, L. Karlinsky, H. Kuehne, and J. R. Glass. Contrastive audio-visual masked autoencoder. In The Eleventh International Conference on Learning Representations, 2023."},{"key":"e_1_3_2_2_15_1","first-page":"21271","article-title":"Bootstrap your own latent-a new approach to self-supervised learning","volume":"33","author":"Grill J.-B.","year":"2020","unstructured":"J.-B. Grill, F. Strub, F. Altch\u00e9, C. Tallec, P. Richemond, E. Buchatskaya, C. Doersch, B. Avila Pires, Z. Guo, M. Gheshlaghi Azar, et al. Bootstrap your own latent-a new approach to self-supervised learning. Advances in Neural Information Processing Systems, 33:21271--21284, 2020.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.579"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPSN54338.2022.00028"},{"key":"e_1_3_2_2_19_1","volume-title":"Masked autoencoders that listen. arXiv preprint arXiv:2207.06405","author":"Huang P.-Y.","year":"2022","unstructured":"P.-Y. Huang, H. Xu, J. Li, A. Baevski, M. Auli, W. Galuba, F. Metze, and C. Feichtenhofer. Masked autoencoders that listen. arXiv preprint arXiv:2207.06405, 2022."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412812"},{"key":"e_1_3_2_2_21_1","volume-title":"Fine-tuning can distort pretrained features and underperform out-of-distribution. arXiv preprint arXiv:2202.10054","author":"Kumar A.","year":"2022","unstructured":"A. Kumar, A. Raghunathan, R. Jones, T. Ma, and P. Liang. Fine-tuning can distort pretrained features and underperform out-of-distribution. arXiv preprint arXiv:2202.10054, 2022."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485730.3485942"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485730.3485942"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"crossref","unstructured":"D. Liu. Self-supervised learning frameworks for IoT applications. PhD thesis 2022.","DOI":"10.1007\/978-3-031-40787-1_2"},{"key":"e_1_3_2_2_25_1","first-page":"1","volume-title":"2021 International Conference on Computer Communications and Networks (ICCCN)","author":"Liu D.","year":"2021","unstructured":"D. Liu, T. Wang, S. Liu, R. Wang, S. Yao, and T. Abdelzaher. Contrastive selfsupervised representation learning for sensing signals from the time-frequency perspective. In 2021 International Conference on Computer Communications and Networks (ICCCN), pages 1--10. IEEE, 2021."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485730.3485945"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_2_28_1","volume-title":"Retromae: Pre-training retrieval-oriented transformers via masked auto-encoder. arXiv preprint arXiv:2205.12035","author":"Liu Z.","year":"2022","unstructured":"Z. Liu and Y. Shao. Retromae: Pre-training retrieval-oriented transformers via masked auto-encoder. arXiv preprint arXiv:2205.12035, 2022."},{"key":"e_1_3_2_2_29_1","volume-title":"Masked spectrogram modeling using masked autoencoders for learning general-purpose audio representation. arXiv preprint arXiv:2204.12260","author":"Niizumi D.","year":"2022","unstructured":"D. Niizumi, D. Takeuchi, Y. Ohishi, N. Harada, and K. Kashino. Masked spectrogram modeling using masked autoencoders for learning general-purpose audio representation. arXiv preprint arXiv:2204.12260, 2022."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3495243.3560519"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3360322.3360851"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511624148.006"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.3390\/app10041376"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1002\/9781118287422"},{"key":"e_1_3_2_2_35_1","first-page":"17782","volume-title":"International Conference on Machine Learning","author":"Poklukar P.","year":"2022","unstructured":"P. Poklukar, M. Vasco, H. Yin, F. S. Melo, A. Paiva, and D. Kragic. Geometric multimodal contrastive representation learning. In International Conference on Machine Learning, pages 17782--17800, 2022."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISWC.2012.13"},{"key":"e_1_3_2_2_37_1","volume-title":"Human activity recognition with smartphone sensors using deep learning neural networks. Expert systems with applications, 59:235--244","author":"Ronao C. A.","year":"2016","unstructured":"C. A. Ronao and S.-B. Cho. Human activity recognition with smartphone sensors using deep learning neural networks. Expert systems with applications, 59:235--244, 2016."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.4236\/jcc.2019.73002"},{"key":"e_1_3_2_2_39_1","first-page":"55","volume-title":"SAD\/CrowdBias@ HCOMP","author":"Schaekermann M.","year":"2018","unstructured":"M. Schaekermann, E. Law, K. Larson, and A. Lim. Expert disagreement in sequential labeling: A case study on adjudication in medical time series analysis. In SAD\/CrowdBias@ HCOMP, pages 55--66, 2018."},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/PERCOM.2016.7456521"},{"key":"e_1_3_2_2_41_1","volume-title":"Exploring contrastive learning in human activity recognition for healthcare. arXiv preprint arXiv:2011.11542","author":"Tang C. I.","year":"2020","unstructured":"C. I. Tang, I. Perez-Pozuelo, D. Spathis, and C. Mascolo. Exploring contrastive learning in human activity recognition for healthcare. arXiv preprint arXiv:2011.11542, 2020."},{"key":"e_1_3_2_2_42_1","first-page":"776","volume-title":"Proceedings, Part XI 16","author":"Tian Y.","year":"2020","unstructured":"Y. Tian, D. Krishnan, and P. Isola. Contrastive multiview coding. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part XI 16, pages 776--794. Springer, 2020."},{"key":"e_1_3_2_2_43_1","volume-title":"International Conference on Learning Representations","author":"Tonekaboni S.","year":"2021","unstructured":"S. Tonekaboni, D. Eytan, and A. Goldenberg. Unsupervised representation learning for time series with temporal neighborhood coding. In International Conference on Learning Representations, 2021."},{"key":"e_1_3_2_2_44_1","volume-title":"Visualizing data using t-sne. Journal of machine learning research, 9(11)","author":"der Maaten L. Van","year":"2008","unstructured":"L. Van der Maaten and G. Hinton. Visualizing data using t-sne. Journal of machine learning research, 9(11), 2008."},{"key":"e_1_3_2_2_45_1","volume-title":"Attention is all you need. Advances in neural information processing systems, 30","author":"Vaswani A.","year":"2017","unstructured":"A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin. Attention is all you need. Advances in neural information processing systems, 30, 2017."},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11036-019-01445-x"},{"key":"e_1_3_2_2_47_1","volume-title":"v. d. Oord. Multimodal self-supervised learning of general audio representations. arXiv preprint arXiv:2104.12807","author":"Wang L.","year":"2021","unstructured":"L. Wang, P. Luc, A. Recasens, J.-B. Alayrac, and A. v. d. Oord. Multimodal self-supervised learning of general audio representations. arXiv preprint arXiv:2104.12807, 2021."},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/MILCOM55135.2022.10017612"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3203630"},{"key":"e_1_3_2_2_50_1","volume-title":"Contrastive learning rivals masked image modeling in fine-tuning via feature distillation. arXiv preprint arXiv:2205.14141","author":"Wei Y.","year":"2022","unstructured":"Y. Wei, H. Hu, Z. Xie, Z. Zhang, Y. Cao, J. Bao, D. Chen, and B. Guo. Contrastive learning rivals masked image modeling in fine-tuning via feature distillation. arXiv preprint arXiv:2205.14141, 2022."},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2006.889760"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485730.3485937"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052577"},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20881"},{"key":"e_1_3_2_2_56_1","volume-title":"Proceedings of Neural Information Processing Systems, NeurIPS","author":"Zhang X.","year":"2022","unstructured":"X. Zhang, Z. Zhao, T. Tsiligkaridis, and M. Zitnik. Self-supervised contrastive pre-training for time series via time-frequency consistency. In Proceedings of Neural Information Processing Systems, NeurIPS, 2022."},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583120.3586960"}],"event":{"name":"WWW '24: The ACM Web Conference 2024","location":"Singapore Singapore","acronym":"WWW '24","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2024"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3589334.3645346","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3589334.3645346","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:23:31Z","timestamp":1755822211000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3589334.3645346"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":57,"alternative-id":["10.1145\/3589334.3645346","10.1145\/3589334"],"URL":"https:\/\/doi.org\/10.1145\/3589334.3645346","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]},"assertion":[{"value":"2024-05-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}