{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,10]],"date-time":"2026-10-10T16:56:09Z","timestamp":1791651369879,"version":"4.3.4"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Open Cloud Institute"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tmm.2020.3005033","type":"journal-article","created":{"date-parts":[[2020,6,25]],"date-time":"2020-06-25T20:10:41Z","timestamp":1593115841000},"page":"1895-1907","source":"Crossref","is-referenced-by-count":44,"title":["AutoFoley: Artificial Synthesis of Synchronized Sound Tracks for Silent Videos With Deep Learning"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0883-5718","authenticated-orcid":false,"given":"Sanchita","family":"Ghose","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2303-599X","authenticated-orcid":false,"given":"John Jeffrey","family":"Prevost","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.37"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2613641"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1518\/001872099779656789"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3758\/BF03198830"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3758\/APP.72.2.454"},{"key":"ref30","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2907060"},{"key":"ref36","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00458"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1518\/001872096778827260"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1990.115767"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1207\/s15326969eco0501_1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2371240"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref22","first-page":"801","article-title":"Ambient sound provides supervision for visual learning","author":"owens","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref24","first-page":"2654","article-title":"Do deep nets really need to be deep?","author":"ba","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref23","first-page":"892","article-title":"SoundNet: Learning sound representations from unlabeled video","author":"aytar","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2829187"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.309"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2011.06.032"},{"key":"ref11","first-page":"827","article-title":"Pattern playback in the 90s","author":"slaney","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21236\/ADA623249"},{"key":"ref12","author":"ghose","year":"0","journal-title":"AutoFoley Sound Examples"},{"key":"ref13","first-page":"537","article-title":"Foleyautomatic: Physically-based sound effects for interactive simulation and animation","author":"doel","year":"0","journal-title":"Proc 28th Annu Conf Comput Graph Interactive Techn"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1162\/105474698565532"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.321"},{"key":"ref16","first-page":"689","article-title":"Multimodal deep learning","author":"ngiam","year":"0","journal-title":"Proc 28th Int Conf Mach Learn"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639140"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3126686.3126723"},{"key":"ref19","article-title":"Visually indicated sound generation by perceptually optimized classification","author":"zhang","year":"0","journal-title":"Proc Eur Conf Comput Vision Workshops"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1083-5"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.264"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2751969"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00374"},{"key":"ref8","first-page":"803","article-title":"Temporal relational reasoning in videos","author":"zhou","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.478"},{"key":"ref49","article-title":"Recurrent neural network regularization","author":"zaremba","year":"2014"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163353"},{"key":"ref46","article-title":"Layer normalization","author":"ba","year":"0","journal-title":"Proc NIPS Deep Learn Smp"},{"key":"ref45","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"soomro","year":"2012","journal-title":"CoRR"},{"key":"ref48","article-title":"Zoneout: Regularizing rnns by randomly preserving hidden activations","author":"krueger","year":"0","journal-title":"Proc 5th Int Conf Learn Representations (ICLR'17)"},{"key":"ref47","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"hinton","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref42","first-page":"5915","article-title":"Fast-slow recurrent neural networks","author":"mujika","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/9296985\/09126216.pdf?arnumber=9126216","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:51:27Z","timestamp":1652194287000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9126216\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/tmm.2020.3005033","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}