{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T02:49:38Z","timestamp":1771210178185,"version":"3.50.1"},"reference-count":83,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"eSCANFace Project funded by the Spanish Ministry of Science and Innovation","award":["PID2020-114083GB-I00"],"award-info":[{"award-number":["PID2020-114083GB-I00"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Biom. Behav. Identity Sci."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/tbiom.2025.3544647","type":"journal-article","created":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T13:55:39Z","timestamp":1740146139000},"page":"876-889","source":"Crossref","is-referenced-by-count":1,"title":["PulseFormer: Continuous Remote Heart Rate Measurement Through Zoomed Time-Spectral Attention"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-9309-5150","authenticated-orcid":false,"given":"Joaquim","family":"Comas","sequence":"first","affiliation":[{"name":"Department of Information and Communication Technologies, Pompeu Fabra University, Barcelona, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7210-1378","authenticated-orcid":false,"given":"Adri\u00e0","family":"Ruiz","sequence":"additional","affiliation":[{"name":"Seedtag, Madrid, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2029-1576","authenticated-orcid":false,"given":"Federico","family":"Sukno","sequence":"additional","affiliation":[{"name":"Department of Information and Communication Technologies, Pompeu Fabra University, Barcelona, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2393347.2396517"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/BHI.2018.8333392"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2017.10.017"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"key":"ref5","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"arXiv:2005.14165"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_22"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref8","first-page":"1","article-title":"PhysFlow: Skin tone transfer for remote heart rate estimation through conditional normalizing flows","volume-title":"Proc. BMVC","author":"Comas"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00001"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00237"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/FG59268.2024.10581863"},{"key":"ref12","article-title":"Deep pulse-signal magnification for remote heart rate estimation in compressed videos","author":"Comas","year":"2024","journal-title":"arXiv:2405.02652"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2013.2266196"},{"key":"ref14","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00998"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00307"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00396"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-698"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-698"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21315"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00495"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00649"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00306"},{"key":"ref24","article-title":"CogVideo: Large-scale pretraining for text-to-video generation via transformers","author":"Hong","year":"2022","journal-title":"arXiv:2205.15868"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_21"},{"key":"ref26","article-title":"Time-SSM: Simplifying and unifying state space models for time series forecasting","author":"Hu","year":"2024","journal-title":"arXiv:2405.16312"},{"key":"ref27","first-page":"1","article-title":"Time-LLM: Time series forecasting by reprogramming large language models","volume-title":"Proc. ICLR","author":"Jin"},{"issue":"1","key":"ref28","first-page":"96","article-title":"Utilizing deep learning towards multi-modal bio-sensing and vision-based affective computing","volume":"13","author":"Jung","year":"2019","journal-title":"IEEE Trans. Affect. Comput."},{"key":"ref29","first-page":"2","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL-HLT","volume":"1","author":"Kenton"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00309"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58583-9_24"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.543"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00560"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01378"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_6"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3330108"},{"key":"ref37","first-page":"19400","article-title":"Multi-task temporal shift attention networks for on-device contactless vitals measurement","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Liu"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00498"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645434"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3450439.3451870"},{"key":"ref41","article-title":"Deep physiological sensing toolbox","author":"Liu","year":"2022","journal-title":"arXiv:2210.00716"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2021.105146"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01222"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01783"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/BTAS.2017.8272752"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2018.8546321"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2947204"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00491"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00308"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.106592"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.1985.325532"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00583"},{"key":"ref53","first-page":"1","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Paszke et al"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00152"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68796-0_50"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2010.2086456"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1364\/OE.18.010762"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19797-0_15"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TAU.1969.1162034"},{"key":"ref60","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ramesh"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-14771-5_22"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00310"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.3390\/s21051607"},{"key":"ref64","first-page":"785","article-title":"Perceiver-actor: A multi-task transformer for robotic manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Shridhar"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1117\/12.2520589"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2021.3051176"},{"key":"ref67","first-page":"1","article-title":"Visual heart rate estimation with convolutional neural network","volume-title":"Proc. BMVC","author":"\u0160petl\u00edk"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2014.6926392"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1016\/j.medengphy.2006.09.006"},{"key":"ref70","first-page":"34052","article-title":"Real-valued backpropagation is unsuitable for complex-valued neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Tan"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.263"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1364\/OE.16.021434"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2016.2609282"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2015.2508602"},{"key":"ref76","first-page":"30392","article-title":"Early convolutions help transformers see better","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Xiao"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01804"},{"key":"ref78","first-page":"1","article-title":"Remote photoplethysmograph signal measurement from facial videos using spatio-temporal networks","volume-title":"Proc. BMVC","author":"Yu"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00024"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01758-1"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_31"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1145\/3604237.3626905"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.374"}],"container-title":["IEEE Transactions on Biometrics, Behavior, and Identity Science"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8423754\/11180155\/10899865.pdf?arnumber=10899865","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T17:27:26Z","timestamp":1759512446000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10899865\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":83,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tbiom.2025.3544647","relation":{},"ISSN":["2637-6407"],"issn-type":[{"value":"2637-6407","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}