{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T19:24:23Z","timestamp":1777058663765,"version":"3.51.4"},"reference-count":45,"publisher":"Association for Computing Machinery (ACM)","issue":"1","license":[{"start":{"date-parts":[[2020,9,9]],"date-time":"2020-09-09T00:00:00Z","timestamp":1599609600000},"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":["ACM Trans. Graph."],"published-print":{"date-parts":[[2021,2,28]]},"abstract":"<jats:p>Many important physical phenomena involve subtle signals that are difficult to observe with the unaided eye, yet visualizing them can be very informative. Current motion magnification techniques can reveal these small temporal variations in video, but require precise prior knowledge about the target signal, and cannot deal with interference motions at a similar frequency. We present DeepMag, an end-to-end deep neural video-processing framework based on gradient ascent that enables automated magnification of subtle color and motion signals from a specific source, even in the presence of large motions of various velocities. The advantages of DeepMag are highlighted via the task of video-based physiological visualization. Through systematic quantitative and qualitative evaluation of the approach on videos with different levels of head motion, we compare the magnification of pulse and respiration to existing state-of-the-art methods. Our method produces magnified videos with substantially fewer artifacts and blurring whilst magnifying the physiological changes by a similar degree.<\/jats:p>","DOI":"10.1145\/3408865","type":"journal-article","created":{"date-parts":[[2020,9,11]],"date-time":"2020-09-11T03:24:11Z","timestamp":1599794651000},"page":"1-14","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":15,"title":["DeepMag"],"prefix":"10.1145","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9550-2553","authenticated-orcid":false,"given":"Weixuan","family":"Chen","sequence":"first","affiliation":[{"name":"Massachusetts Institute of Technology, Cambridge, Massachusetts"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7313-0082","authenticated-orcid":false,"given":"Daniel","family":"McDuff","sequence":"additional","affiliation":[{"name":"Microsoft Research, Redmond, Washington"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2020,9,9]]},"reference":[{"key":"e_1_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.440"},{"key":"e_1_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1161\/JAHA.116.003428"},{"key":"e_1_2_2_3_1","volume-title":"DeepPhys: Video-based physiological measurement using convolutional attention networks. arXiv preprint arXiv:1805.07888","author":"Chen Weixuan","year":"2018"},{"key":"e_1_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2013.2266196"},{"key":"e_1_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1088\/0967-3334\/35\/9\/1913"},{"key":"e_1_2_2_6_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 4119--4127","author":"Elgharib Mohamed"},{"key":"e_1_2_2_7_1","first-page":"1","article-title":"Visualizing higher-layer features of a deep network","volume":"1341","author":"Erhan Dumitru","year":"2009","journal-title":"University of Montreal"},{"key":"e_1_2_2_8_1","volume-title":"Proceedings of the 2014 IEEE International Conference on Systems, Man and Cybernetics (SMC). IEEE, 1462--1469","author":"Estepp Justin R."},{"key":"e_1_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1001\/archderm.1988.01670060015008"},{"key":"e_1_2_2_10_1","volume-title":"Lensch","author":"Fuchs Martin","year":"2010"},{"key":"e_1_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2002.1031944"},{"key":"e_1_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1088\/0967-3334\/37\/1\/100"},{"key":"e_1_2_2_13_1","unstructured":"G\u00fcnter Klambauer Thomas Unterthiner Andreas Mayr and Sepp Hochreiter. 2017. Self-normalizing neural networks. In Advances in Neural Information Processing Systems. 972--981.  G\u00fcnter Klambauer Thomas Unterthiner Andreas Mayr and Sepp Hochreiter. 2017. Self-normalizing neural networks. In Advances in Neural Information Processing Systems. 972--981."},{"key":"e_1_2_2_14_1","volume-title":"Proceedings of the European Conference on Computer Vision. Springer, 467--482","author":"Julian F."},{"key":"e_1_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.415"},{"key":"e_1_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/1073204.1073223"},{"key":"e_1_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00185"},{"key":"e_1_2_2_18_1","volume-title":"Proceedings of the 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). IEEE, 6398--6404","author":"McDuff Daniel"},{"key":"e_1_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2014.2323695"},{"key":"e_1_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2013.2291900"},{"key":"e_1_2_2_21_1","volume-title":"Deepdream-a code example for visualizing neural networks. Google Res 2","author":"Mordvintsev Alexander","year":"2015"},{"key":"e_1_2_2_22_1","first-page":"33","article-title":"The uncanny valley","volume":"7","author":"Mori Masahiro","year":"1970","journal-title":"Energy"},{"key":"e_1_2_2_23_1","volume-title":"Learning-based video motion magnification. arXiv preprint arXiv:1804.02684","author":"Oh Tae-Hyun","year":"2018"},{"key":"e_1_2_2_24_1","volume-title":"Feature visualization. Distill 2, 11","author":"Olah Chris","year":"2017"},{"key":"e_1_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2015.7163150"},{"key":"e_1_2_2_26_1","volume-title":"Proceedings of the European Conference on Computer Vision. Springer, 55--64","author":"Silvia"},{"key":"e_1_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1364\/OE.18.010762"},{"key":"e_1_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2010.2086456"},{"key":"e_1_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1026553619983"},{"key":"e_1_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/18.119725"},{"key":"e_1_2_2_31_1","volume-title":"Deep inside convolutional networks: Visualising image classification models and saliency maps. arXiv preprint arXiv:1312.6034","author":"Simonyan Karen","year":"2013"},{"key":"e_1_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073640"},{"key":"e_1_2_2_33_1","volume-title":"Heart rate measurement based on a time-lapse image. Medical Engineering 8 Physics 29, 8","author":"Takano Chihiro","year":"2007"},{"key":"e_1_2_2_34_1","volume-title":"Proceedings of the 7th International Symposium on Communication Systems Networks and Digital Signal Processing (CSNDSP)","author":"Tan K. S.","year":"2010"},{"key":"e_1_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1088\/0967-3334\/35\/5\/807"},{"key":"e_1_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.263"},{"key":"e_1_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1364\/OE.16.021434"},{"key":"e_1_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/2461912.2461966"},{"key":"e_1_2_2_39_1","volume-title":"Proceedings of the 2014 IEEE International Conference on Computational Photography (ICCP). IEEE, 1--10","author":"Wadhwa Neal"},{"key":"e_1_2_2_40_1","volume-title":"Cohen","author":"Wang Jue","year":"2006"},{"key":"e_1_2_2_41_1","first-page":"1","article-title":"Algorithmic principles of remote-PPG","volume":"99","author":"Wang Wenjin","year":"2016","journal-title":"IEEE Transactions on Biomedical Engineering PP"},{"key":"e_1_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2014.2356291"},{"key":"e_1_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2185561"},{"key":"e_1_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1364\/BOE.5.001124"},{"key":"e_1_2_2_45_1","volume-title":"Proceedings of the 30th IEEE Conference on Computer Vision and Pattern Recognition","author":"Zhang Yichao","year":"2017"}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3408865","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3408865","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T21:31:36Z","timestamp":1750195896000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3408865"}},"subtitle":["Source-Specific Change Magnification Using Gradient Ascent"],"short-title":[],"issued":{"date-parts":[[2020,9,9]]},"references-count":45,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,2,28]]}},"alternative-id":["10.1145\/3408865"],"URL":"https:\/\/doi.org\/10.1145\/3408865","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,9,9]]},"assertion":[{"value":"2018-07-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2020-05-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2020-09-09","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}