{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T05:20:04Z","timestamp":1772083204351,"version":"3.50.1"},"reference-count":52,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T00:00:00Z","timestamp":1625097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T00:00:00Z","timestamp":1625097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T00:00:00Z","timestamp":1625097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,7]]},"DOI":"10.1109\/icccn52240.2021.9522151","type":"proceedings-article","created":{"date-parts":[[2021,8,31]],"date-time":"2021-08-31T20:31:47Z","timestamp":1630441907000},"page":"1-10","source":"Crossref","is-referenced-by-count":38,"title":["Contrastive Self-Supervised Representation Learning for Sensing Signals from the Time-Frequency Perspective"],"prefix":"10.1109","author":[{"given":"Dongxin","family":"Liu","sequence":"first","affiliation":[]},{"given":"Tianshi","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Shengzhong","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Ruijie","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Shuochao","family":"Yao","sequence":"additional","affiliation":[]},{"given":"Tarek","family":"Abdelzaher","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","article-title":"Cooperative learning of audio and video models from self-supervised synchronization","author":"korbar","year":"2018","journal-title":"arXiv preprint arXiv 1807 00230"},{"key":"ref38","article-title":"Self-supervised generation of spatial audio for 360 video","author":"morgado","year":"2018","journal-title":"arXiv preprint arXiv 1809 02587"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1126\/science.290.5500.2323"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1111\/j.1469-1809.1936.tb02137.x","article-title":"The use of multiple measurements in taxonomic problems","volume":"7","author":"fisher","year":"1936","journal-title":"Annals of Eugenics"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1080\/14786440109462720"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref37","article-title":"Self-supervised co-training for video representation learning","author":"han","year":"2020","journal-title":"arXiv preprint arXiv 2010 00170"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00413"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00658"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.167"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3410531.3414306"},{"key":"ref27","article-title":"Exploring contrastive learning in human activity recognition for healthcare","author":"tang","year":"2020","journal-title":"arXiv preprint arXiv 2011 11204"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfds.2017.05.001"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313426"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3161174"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3274783.3274840"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/2994551.2994564"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390294"},{"key":"ref23","first-page":"69","article-title":"Unsupervised learning of visual representations by solving jigsaw puzzles","author":"noroozi","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3328932"},{"key":"ref25","article-title":"Efficient estimation of word representations in vector space","author":"mikolov","year":"2013","journal-title":"arXiv preprint arXiv 1301 3781"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3241539.3241548"},{"key":"ref51","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv preprint arXiv 1412 6980"},{"key":"ref52","article-title":"Visualizing data using t-sne","volume":"9","author":"van der maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref10","first-page":"2536","article-title":"Context encoders: Feature learning by inpainting","author":"pathak","year":"2016","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref11","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020","journal-title":"arXiv preprint arXiv 2002 05155"},{"key":"ref40","article-title":"A mutual information maximization perspective of language representation learning","author":"kong","year":"2019","journal-title":"arXiv preprint arXiv 1910 01500"},{"key":"ref12","article-title":"Vl-bert: Pre-training of generic visual-linguistic representations","author":"su","year":"2019","journal-title":"arXiv preprint arXiv 1908 00310"},{"key":"ref13","first-page":"318","article-title":"Joint-task self-supervised learning for temporal correspondence","author":"li","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref14","first-page":"2493","article-title":"Natural language processing (almost) from scratch","volume":"12","author":"collobert","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3323679.3326527"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-clinpsy-032816-044949"},{"key":"ref17","article-title":"Speech emotion recognition using deep neural network and extreme learning machine","author":"han","year":"2014","journal-title":"Fifteenth Annual Conference of the International Speech Communication Association"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3090076"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3214277"},{"key":"ref4","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"248","DOI":"10.1109\/CVPR.2009.5206848","article-title":"Imagenet: A large-scale hierarchical image database","author":"deng","year":"2009","journal-title":"2009 IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052577"},{"key":"ref5","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"arXiv preprint arXiv 1810 04805"},{"key":"ref8","article-title":"Unsupervised representation learning by predicting image rotations","author":"gidaris","year":"2018","journal-title":"arXiv preprint arXiv 1803 07728"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3131672.3131675"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/1964897.1964918"},{"key":"ref9","first-page":"649","article-title":"Colorful image colorization","author":"zhang","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref46","first-page":"100","article-title":"Human daily activity and fall recognition using a smartphone’s acceleration sensor","author":"chatzaki","year":"2016","journal-title":"International Conference on Information and Communication Technologies for Ageing Well and e-Health"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/2809695.2809718"},{"key":"ref48","first-page":"3","article-title":"A public domain dataset for human activity recognition using smartphones","volume":"3","author":"anguita","year":"2013","journal-title":"ESANN"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3195258.3195260"},{"key":"ref42","first-page":"1857","article-title":"Improved deep metric learning with multi-class n-pair loss objective","author":"sohn","year":"2016","journal-title":"Proceedings of the 30th International Conference on Neural Information Processing Systems"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref44","article-title":"Robusttad: Robust time series anomaly detection via decomposition and convolutional neural networks","author":"gao","year":"2020","journal-title":"arXiv preprint arXiv 2002 05155"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3390\/s18092892"}],"event":{"name":"2021 International Conference on Computer Communications and Networks (ICCCN)","location":"Athens, Greece","start":{"date-parts":[[2021,7,19]]},"end":{"date-parts":[[2021,7,22]]}},"container-title":["2021 International Conference on Computer Communications and Networks (ICCCN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9521949\/9522143\/09522151.pdf?arnumber=9522151","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:45:22Z","timestamp":1652197522000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9522151\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/icccn52240.2021.9522151","relation":{},"subject":[],"published":{"date-parts":[[2021,7]]}}}