{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T17:15:20Z","timestamp":1791911720722,"version":"4.3.4"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tip.2022.3219228","type":"journal-article","created":{"date-parts":[[2022,11,8]],"date-time":"2022-11-08T20:36:19Z","timestamp":1667939779000},"page":"7102-7115","source":"Crossref","is-referenced-by-count":10,"title":["Unsupervised Synthetic Acoustic Image Generation for Audio-Visual Scene Understanding"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7995-6205","authenticated-orcid":false,"given":"Valentina","family":"Sanguineti","sequence":"first","affiliation":[{"name":"Department of Pattern Analysis & Computer Vision (PAVIS), Istituto Italiano di Tecnologia, Genova, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5259-1496","authenticated-orcid":false,"given":"Pietro","family":"Morerio","sequence":"additional","affiliation":[{"name":"Department of Pattern Analysis & Computer Vision (PAVIS), Istituto Italiano di Tecnologia, Genova, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2262-4872","authenticated-orcid":false,"given":"Alessio Del","family":"Bue","sequence":"additional","affiliation":[{"name":"Department of Pattern Analysis & Computer Vision (PAVIS), Istituto Italiano di Tecnologia, Genova, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8645-2328","authenticated-orcid":false,"given":"Vittorio","family":"Murino","sequence":"additional","affiliation":[{"name":"Department of Pattern Analysis & Computer Vision (PAVIS), Istituto Italiano di Tecnologia, Genova, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/T-C.1974.223784"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_14"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163420"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3009820"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"ref38","article-title":"Conditional generative adversarial nets","author":"mirza","year":"2014","journal-title":"arXiv 1411 1784"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.55"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"649","DOI":"10.1007\/978-3-319-46487-9_40","article-title":"Colorful image colorization","author":"zhang","year":"2016","journal-title":"Computer Vision—ECCV 2016"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_20"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00163"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.18"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00393"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_18"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_13"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref28","article-title":"A neural algorithm of artistic style","author":"gatys","year":"2015","journal-title":"arXiv 1508 06576"},{"key":"ref64","first-page":"1","article-title":"A statistical model of timbre perception","author":"terasawa","year":"2006","journal-title":"Proc SAPA INTERSPEECH"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.19"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-03116-3"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.265"},{"key":"ref67","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-64583-0_28"},{"key":"ref69","article-title":"beta-VAE: Learning basic visual concepts with a constrained variational framework","author":"higgins","year":"2017","journal-title":"Proc 5th Int Conf Learn Represent (ICLR)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2966082"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1093\/jrma\/2.1.75"},{"key":"ref20","first-page":"689","article-title":"Multimodal deep learning","author":"ngiam","year":"2011","journal-title":"Proc 28th Int Conf Mach Learn"},{"key":"ref22","first-page":"5580","article-title":"Multimodal generative models for scalable weakly-supervised learning","author":"wu","year":"2018","journal-title":"Proc 32nd Int Conf Neural Inf Process Syst"},{"key":"ref21","first-page":"1","article-title":"Joint multimodal learning with deep generative models","author":"suzuki","year":"2017","journal-title":"Proc ICLR"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00017"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2017.8168111"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2439281"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6778"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00458"},{"key":"ref51","first-page":"813","article-title":"Audio-vision: Using audio-visual synchrony to locate sounds","author":"hershey","year":"1999","journal-title":"Proc 12th Int Conf Neural Inf Process Syst"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093616"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_40"},{"key":"ref57","first-page":"4733","article-title":"Learning representations from audio-visual spatial alignment","author":"morgado","year":"2020","journal-title":"Proc NIPS"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2957889"},{"key":"ref55","first-page":"10077","article-title":"Discriminative sounding objects localization via self-supervised audiovisual matching","author":"hu","year":"2020","journal-title":"Proc NIPS"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00947"},{"key":"ref53","article-title":"Curriculum audiovisual learning","author":"hu","year":"2020","journal-title":"arXiv 2001 09414"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2009.2032182"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.1002\/0471221104","author":"trees","year":"2002","journal-title":"Detection Estimation and Modulation Theory Optimum Array Processing"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093307"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_8"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2015.95"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2017.2711497"},{"key":"ref15","first-page":"1","article-title":"Auto-encoding variational Bayes","author":"kingma","year":"2014","journal-title":"Proc ICLR"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","article-title":"U-Net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"2015","journal-title":"Medical Image Computing and Computer-Assisted Intervention—MICCAI 2015"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16354"},{"key":"ref18","first-page":"2672","article-title":"Generative adversarial nets","volume":"27","author":"goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref19","first-page":"360","article-title":"Self-supervised generation of spatial audio for 360° video","author":"morgado","year":"2018","journal-title":"Proc NeurIPS"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00995"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_37"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00715"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00041"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2193391"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_2"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/83.743860"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1083-5"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201357"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_27"},{"key":"ref42","first-page":"1858","article-title":"Unsupervised learning of spoken language with visual context","author":"harwath","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref41","first-page":"892","article-title":"SoundNet: Learning sound representations from unlabeled video","author":"aytar","year":"2016","journal-title":"Proc 30th Int Conf Neural Inf Process Syst"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.264"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_48"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9626658\/09942928.pdf?arnumber=9942928","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,30]],"date-time":"2023-11-30T12:57:19Z","timestamp":1701349039000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9942928\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":76,"URL":"https:\/\/doi.org\/10.1109\/tip.2022.3219228","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}