{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T15:35:28Z","timestamp":1784820928485,"version":"3.55.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[],"published-print":{"date-parts":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8682467","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T20:01:56Z","timestamp":1555531316000},"page":"2357-2361","source":"Crossref","is-referenced-by-count":64,"title":["Self-supervised Audio-visual Co-segmentation"],"prefix":"10.1109","author":[{"given":"Andrew","family":"Rouditchenko","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hang","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuang","family":"Gan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Josh","family":"McDermott","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Antonio","family":"Torralba","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref11","article-title":"Audio-visual scene analysis with self-supervised multisensory features","author":"owens","year":"2018","journal-title":"arXiv preprint arXiv 1804 02671"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952687"},{"key":"ref13","first-page":"4358","article-title":"Learning to localize sound source in visual scenes","author":"senocak","year":"2018","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2872106"},{"key":"ref15","first-page":"649","article-title":"Jointly discovering visual objects and spoken words from raw sensory input","author":"harwath","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref16","article-title":"Looking to listen at the cocktail party: A speaker-independent audio-visual model for speech separation","author":"ephrat","year":"2018","journal-title":"arXiv preprint arXiv 1804 02671"},{"key":"ref17","article-title":"Representations of language in a model of visually grounded speech signal","author":"chrupa?a","year":"2017","journal-title":"arXiv preprint arXiv 1702 08502"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268967"},{"key":"ref19","article-title":"Audio-visual event localization in unconstrained videos","author":"tian","year":"2018","journal-title":"ECCV"},{"key":"ref4","author":"bregman","year":"1994","journal-title":"Auditory Scene Analysis The Perceptual Organization of Sound"},{"key":"ref27","article-title":"mir_eval: A transparent implementation of common mir metrics","author":"raffel","year":"2014","journal-title":"In Proceedings of the 15th International Society for Music Information Retrieval Conference ISMIR"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.cub.2009.09.005"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.885253"},{"key":"ref8","first-page":"892","article-title":"Sound-net: Learning sound representations from unlabeled video","author":"aytar","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref9","first-page":"801","article-title":"Ambient sound provides supervision for visual learning","author":"owens","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref1","article-title":"The sound of pixels","author":"zhao","year":"2018","journal-title":"the European Conference on Computer Vision (ECCV)"},{"key":"ref20","article-title":"beta-vae: Learning basic visual concepts with a constrained variational framework","author":"higgins","year":"2017","journal-title":"International Conference on Learning Representations"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref21","article-title":"Categorical reparameterization with gumbel-softmax","author":"jang","year":"2016","journal-title":"arXiv preprint arXiv 1611 01144"},{"key":"ref24","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"2015","journal-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1126\/science.287.5456.1273"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Brighton, United Kingdom","start":{"date-parts":[[2019,5,12]]},"end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08682467.pdf?arnumber=8682467","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:17:43Z","timestamp":1657855063000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8682467\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8682467","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}