{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T16:26:33Z","timestamp":1781713593035,"version":"3.54.5"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012151","type":"print"},{"value":"9783030012168","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-030-01216-8_22","type":"book-chapter","created":{"date-parts":[[2018,10,8]],"date-time":"2018-10-08T11:10:26Z","timestamp":1538997026000},"page":"356-373","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":520,"title":["DeepPhys: Video-Based Physiological Measurement Using Convolutional Attention Networks"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9550-2553","authenticated-orcid":false,"given":"Weixuan","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7313-0082","authenticated-orcid":false,"given":"Daniel","family":"McDuff","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,10,9]]},"reference":[{"issue":"12","key":"22_CR1","doi-asserted-by":"publisher","first-page":"943","DOI":"10.1016\/j.earlhumdev.2013.09.016","volume":"89","author":"LA Aarts","year":"2013","unstructured":"Aarts, L.A., et al.: Non-contact heart rate monitoring utilizing camera photoplethysmography in the neonatal intensive care unit - a pilot study. Early Hum. Dev. 89(12), 943\u2013948 (2013)","journal-title":"Early Hum. Dev."},{"key":"22_CR2","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)"},{"key":"22_CR3","doi-asserted-by":"crossref","unstructured":"Balakrishnan, G., Durand, F., Guttag, J.: Detecting pulse from head motions in video. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3430\u20133437. IEEE (2013)","DOI":"10.1109\/CVPR.2013.440"},{"key":"22_CR4","unstructured":"Ballas, N., Yao, L., Pal, C., Courville, A.: Delving deeper into convolutional networks for learning video representations. In: International Conference on Learning Representations (ICLR), pp. 1\u201311 (2016)"},{"key":"22_CR5","doi-asserted-by":"crossref","unstructured":"Chaichulee, S., et al.: Multi-task convolutional neural network for patient detection and skin segmentation in continuous non-contact vital sign monitoring. In: 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG), pp. 266\u2013272. IEEE (2017)","DOI":"10.1109\/FG.2017.41"},{"key":"22_CR6","unstructured":"Chen, W., Hernandez, J., Picard, R.W.: Non-contact physiological measurements from near-infrared video of the neck. arXiv preprint arXiv:1805.09511 (2017)"},{"key":"22_CR7","doi-asserted-by":"crossref","unstructured":"Chen, W., Picard, R.W.: Eliminating physiological information from facial videos. In: 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG), pp. 48\u201355. IEEE (2017)","DOI":"10.1109\/FG.2017.15"},{"key":"22_CR8","doi-asserted-by":"publisher","unstructured":"Donahue, J., et al.: Long-term recurrent convolutional networks for visual recognition and description. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2625\u20132634 (2015). https:\/\/doi.org\/10.1109\/CVPR.2015.7298878","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"22_CR9","doi-asserted-by":"crossref","unstructured":"Dosovitskiy, A., et al.: FlowNet: learning optical flow with convolutional networks. In: IEEE International Conference on Computer Vision (ICCV), pp. 2758\u20132766 (2015)","DOI":"10.1109\/ICCV.2015.316"},{"key":"22_CR10","doi-asserted-by":"crossref","unstructured":"Estepp, J.R., Blackford, E.B., Meier, C.M.: Recovering pulse rate during motion artifact with a multi-imager array for non-contact imaging photoplethysmography. In: IEEE International Conference on Systems, Man and Cybernetics (SMC), vol. 940, pp. 1462\u20131469. IEEE (2014)","DOI":"10.1109\/SMC.2014.6974121"},{"key":"22_CR11","unstructured":"Finn, C., Goodfellow, I., Levine, S.: Unsupervised learning for physical interaction through video prediction. In: Advances in Neural Information Processing Systems (NIPS), pp. 64\u201372 (2016)"},{"issue":"9","key":"22_CR12","doi-asserted-by":"publisher","first-page":"1913","DOI":"10.1088\/0967-3334\/35\/9\/1913","volume":"35","author":"G de Haan","year":"2014","unstructured":"de Haan, G., van Leest, A.: Improved motion robustness of remote-PPG by using the blood volume pulse signature. Physiol. Measur. 35(9), 1913 (2014)","journal-title":"Physiol. Measur."},{"issue":"10","key":"22_CR13","doi-asserted-by":"publisher","first-page":"2878","DOI":"10.1109\/TBME.2013.2266196","volume":"60","author":"G de Haan","year":"2013","unstructured":"de Haan, G., Jeanne, V.: Robust pulse rate from chrominance-based rPPG. IEEE Trans. Biomed. Eng. 60(10), 2878\u20132886 (2013)","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"22_CR14","doi-asserted-by":"crossref","unstructured":"Hurter, C., McDuff, D.: Cardiolens: remote physiological monitoring in a mixed reality environment. In: ACM SIGGRAPH 2017 Emerging Technologies, p. 6. ACM (2017)","DOI":"10.1145\/3084822.3084834"},{"key":"22_CR15","doi-asserted-by":"publisher","unstructured":"Ilg, E., Mayer, N., Saikia, T., Keuper, M., Dosovitskiy, A., Brox, T.: FlowNet 2.0: evolution of optical flow estimation with deep networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), vol. 2, p. 6. IEEE (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.179","DOI":"10.1109\/CVPR.2017.179"},{"key":"22_CR16","doi-asserted-by":"crossref","unstructured":"Lam, A., Kuno, Y.: Robust heart rate measurement from video using select random patches. In: IEEE International Conference on Computer Vision (ICCV), pp. 3640\u20133648. IEEE (2015)","DOI":"10.1109\/ICCV.2015.415"},{"key":"22_CR17","doi-asserted-by":"publisher","unstructured":"Li, X., Chen, J., Zhao, G., Pietikainen, M.: Remote heart rate measurement from face videos under realistic situations. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4264\u20134271. IEEE (2014). https:\/\/doi.org\/10.1109\/CVPR.2014.543","DOI":"10.1109\/CVPR.2014.543"},{"key":"22_CR18","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1016\/j.cviu.2017.10.011","volume":"166","author":"Z Li","year":"2018","unstructured":"Li, Z., Gavrilyuk, K., Gavves, E., Jain, M., Snoek, C.G.: Videolstm convolves, attends and flows for action recognition. Comput. Vis. Image Underst. 166, 41\u201350 (2018)","journal-title":"Comput. Vis. Image Underst."},{"issue":"10","key":"22_CR19","doi-asserted-by":"publisher","first-page":"2593","DOI":"10.1109\/TBME.2014.2323695","volume":"61","author":"D McDuff","year":"2014","unstructured":"McDuff, D., Gontarek, S., Picard, R.: Improvements in remote cardio-pulmonary measurement using a five band digital camera. IEEE Trans. Biomed. Eng. 61(10), 2593\u20132601 (2014)","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"22_CR20","doi-asserted-by":"crossref","unstructured":"McDuff, D.J., Estepp, J.R., Piasecki, A.M., Blackford, E.B.: A survey of remote optical photoplethysmographic imaging methods. In: 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 6398\u20136404. IEEE (2015)","DOI":"10.1109\/EMBC.2015.7319857"},{"issue":"4","key":"22_CR21","doi-asserted-by":"publisher","first-page":"1153","DOI":"10.1109\/JBHI.2013.2291900","volume":"18","author":"H Monkaresi","year":"2014","unstructured":"Monkaresi, H., Calvo, R.A., Yan, H.: A machine learning approach to improve contactless heart rate monitoring using a webcam. IEEE J. Biomed. Health Inf. 18(4), 1153\u20131160 (2014)","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"22_CR22","doi-asserted-by":"publisher","unstructured":"Ng, J.Y.H., Hausknecht, M., Vijayanarasimhan, S., Vinyals, O., Monga, R., Toderici, G.: Beyond short snippets: deep networks for video classification. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4694\u20134702 (2015). https:\/\/doi.org\/10.1109\/CVPR.2015.7299101","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"22_CR23","doi-asserted-by":"crossref","unstructured":"Osman, A., Turcot, J., El Kaliouby, R.: Supervised learning approach to remote heart rate estimation from facial videos. In: 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG), vol. 1, pp. 1\u20136. IEEE (2015)","DOI":"10.1109\/FG.2015.7163150"},{"issue":"10","key":"22_CR24","doi-asserted-by":"publisher","first-page":"10762","DOI":"10.1364\/OE.18.010762","volume":"18","author":"MZ Poh","year":"2010","unstructured":"Poh, M.Z., McDuff, D.J., Picard, R.W.: Non-contact, automated cardiac pulse measurements using video imaging and blind source separation. Opt. Express 18(10), 10762\u201310774 (2010)","journal-title":"Opt. Express"},{"issue":"1","key":"22_CR25","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1109\/TBME.2010.2086456","volume":"58","author":"MZ Poh","year":"2011","unstructured":"Poh, M.Z., McDuff, D.J., Picard, R.W.: Advancements in noncontact, multiparameter physiological measurements using a webcam. IEEE Trans. Biomed. Eng. 58(1), 7\u201311 (2011)","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"22_CR26","unstructured":"Sharma, S., Kiros, R., Salakhutdinov, R.: Action recognition using visual attention. arXiv preprint arXiv:1511.04119 (2015)"},{"key":"22_CR27","doi-asserted-by":"publisher","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Advances in Neural Information Processing Systems (NIPS), pp. 568\u2013576 (2014). https:\/\/doi.org\/10.1017\/CBO9781107415324.004","DOI":"10.1017\/CBO9781107415324.004"},{"issue":"1","key":"22_CR28","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1109\/T-AFFC.2011.25","volume":"3","author":"M Soleymani","year":"2012","unstructured":"Soleymani, M., Lichtenauer, J., Pun, T., Pantic, M.: A multimodal database for affect recognition and implicit tagging. IEEE Trans. Affect. Comput. 3(1), 42\u201355 (2012)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"22_CR29","doi-asserted-by":"publisher","first-page":"1929","DOI":"10.1214\/12-AOS1000","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15, 1929\u20131958 (2014). https:\/\/doi.org\/10.1214\/12-AOS1000","journal-title":"J. Mach. Learn. Res."},{"issue":"8","key":"22_CR30","doi-asserted-by":"publisher","first-page":"853","DOI":"10.1016\/j.medengphy.2006.09.006","volume":"29","author":"C Takano","year":"2007","unstructured":"Takano, C., Ohta, Y.: Heart rate measurement based on a time-lapse image. Med. Eng. Phys. 29(8), 853\u2013857 (2007)","journal-title":"Med. Eng. Phys."},{"issue":"5","key":"22_CR31","doi-asserted-by":"publisher","first-page":"807","DOI":"10.1088\/0967-3334\/35\/5\/807","volume":"35","author":"L Tarassenko","year":"2014","unstructured":"Tarassenko, L., Villarroel, M., Guazzi, A., Jorge, J., Clifton, D., Pugh, C.: Non-contact video-based vital sign monitoring using ambient light and auto-regressive models. Physiol. Measur. 35(5), 807 (2014)","journal-title":"Physiol. Measur."},{"key":"22_CR32","doi-asserted-by":"crossref","unstructured":"Tran, A., Cheong, L.F.: Two-stream flow-guided convolutional attention networks for action recognition. arXiv preprint arXiv:1708.09268 (2017)","DOI":"10.1109\/ICCVW.2017.368"},{"key":"22_CR33","doi-asserted-by":"publisher","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 675\u2013678. IEEE (2014). https:\/\/doi.org\/10.1109\/CVPR.2014.223","DOI":"10.1109\/CVPR.2014.223"},{"key":"22_CR34","doi-asserted-by":"crossref","unstructured":"Tulyakov, S., Alameda-Pineda, X., Ricci, E., Yin, L., Cohn, J.F., Sebe, N.: Self-adaptive matrix completion for heart rate estimation from face videos under realistic conditions. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2396\u20132404. IEEE (2016)","DOI":"10.1109\/CVPR.2016.263"},{"issue":"26","key":"22_CR35","doi-asserted-by":"publisher","first-page":"21434","DOI":"10.1364\/OE.16.021434","volume":"16","author":"W Verkruysse","year":"2008","unstructured":"Verkruysse, W., Svaasand, L.O., Nelson, J.S.: Remote plethysmographic imaging using ambient light. Opt. Express 16(26), 21434\u201321445 (2008)","journal-title":"Opt. Express"},{"key":"22_CR36","doi-asserted-by":"crossref","unstructured":"Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), vol. 1, p. I-511. IEEE (2001)","DOI":"10.1109\/CVPR.2001.990517"},{"issue":"2","key":"22_CR37","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1109\/TBME.2014.2356291","volume":"62","author":"W Wang","year":"2015","unstructured":"Wang, W., Stuijk, S., de Haan, G.: Exploiting spatial redundancy of image sensor for motion robust rPPG. IEEE Trans. Biomed. Eng. 62(2), 415\u2013425 (2015)","journal-title":"IEEE Trans. Biomed. Eng."},{"issue":"7","key":"22_CR38","doi-asserted-by":"publisher","first-page":"1479","DOI":"10.1109\/TBME.2016.2609282","volume":"64","author":"W Wang","year":"2017","unstructured":"Wang, W., den Brinker, A.C., Stuijk, S., de Haan, G.: Algorithmic principles of remote PPG. IEEE Trans. Biomed. Eng. 64(7), 1479\u20131491 (2017). https:\/\/doi.org\/10.1109\/TBME.2016.2609282","journal-title":"IEEE Trans. Biomed. Eng."},{"issue":"9","key":"22_CR39","doi-asserted-by":"publisher","first-page":"1974","DOI":"10.1109\/TBME.2015.2508602","volume":"63","author":"W Wang","year":"2016","unstructured":"Wang, W., Stuijk, S., De Haan, G.: A novel algorithm for remote photoplethysmography: spatial subspace rotation. IEEE Trans. Biomed. Eng. 63(9), 1974\u20131984 (2016)","journal-title":"IEEE Trans. Biomed. Eng."},{"issue":"4","key":"22_CR40","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1145\/2185520.2185561","volume":"31","author":"HY Wu","year":"2012","unstructured":"Wu, H.Y., Rubinstein, M., Shih, E., Guttag, J.V., Durand, F., Freeman, W.T.: Eulerian video magnification for revealing subtle changes in the world. ACM Trans. Graph. 31(4), 65 (2012)","journal-title":"ACM Trans. Graph."},{"key":"22_CR41","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning (ICML), pp. 2048\u20132057 (2015)"},{"issue":"4","key":"22_CR42","doi-asserted-by":"publisher","first-page":"1124","DOI":"10.1364\/BOE.5.001124","volume":"5","author":"S Xu","year":"2014","unstructured":"Xu, S., Sun, L., Rohde, G.K.: Robust efficient estimation of heart rate pulse from video. Biomed. Opt. Express 5(4), 1124 (2014). https:\/\/doi.org\/10.1364\/BOE.5.001124","journal-title":"Biomed. Opt. Express"},{"key":"22_CR43","unstructured":"Xue, T., Wu, J., Bouman, K., Freeman, B.: Visual dynamics: probabilistic future frame synthesis via cross convolutional networks. In: Advances in Neural Information Processing Systems (NIPS), pp. 91\u201399 (2016)"},{"key":"22_CR44","unstructured":"Yao, L., et al.: Video description generation incorporating spatio-temporal features and a soft-attention mechanism. arXiv preprint arXiv:1502.08029 (2015)"},{"key":"22_CR45","unstructured":"Zeiler, M.D.: ADADELTA: an adaptive learning rate method. arXiv preprint arXiv:1212.5701 (2012)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01216-8_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T18:57:47Z","timestamp":1775242667000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01216-8_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012151","9783030012168"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01216-8_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"9 October 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2018.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}