{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T00:12:49Z","timestamp":1730247169797,"version":"3.28.0"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,9,19]],"date-time":"2021-09-19T00:00:00Z","timestamp":1632009600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,9,19]],"date-time":"2021-09-19T00:00:00Z","timestamp":1632009600000},"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":[[2021,9,19]]},"DOI":"10.1109\/icip42928.2021.9506019","type":"proceedings-article","created":{"date-parts":[[2021,8,23]],"date-time":"2021-08-23T17:08:41Z","timestamp":1629738521000},"page":"2568-2572","source":"Crossref","is-referenced-by-count":1,"title":["Listen To The Pixels"],"prefix":"10.1109","author":[{"given":"Sanjoy","family":"Chowdhury","sequence":"first","affiliation":[{"name":"IIIT,Hyderabad"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Subhrajyoti","family":"Dasgupta","sequence":"additional","affiliation":[{"name":"ISI,Kolkata"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sudip","family":"Das","sequence":"additional","affiliation":[{"name":"ISI,Kolkata"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ujjwal","family":"Bhattacharya","sequence":"additional","affiliation":[{"name":"ISI,Kolkata"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"35","article-title":"Learning to separate object sounds by watching unlabeled video","author":"gao","year":"2018","journal-title":"ECCV"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00458"},{"key":"ref12","first-page":"435","article-title":"Objects that sound","author":"arandjelovic","year":"2018","journal-title":"ECCV"},{"key":"ref13","first-page":"631","article-title":"Audio-visual scene analysis with self-supervised multisensory features","author":"owens","year":"2018","journal-title":"ECCV"},{"key":"ref14","first-page":"2002","article-title":"Dual-modality seq2seq network for audio-visual event localization","author":"lin","year":"2019","journal-title":"ICASSP"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref16","first-page":"247","article-title":"Audio-visual event localization in unconstrained videos","author":"tian","year":"2018","journal-title":"ECCV"},{"key":"ref17","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 03583"},{"key":"ref18","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NIPS"},{"key":"ref19","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"2015","journal-title":"MICCAI"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.2307\/1165922"},{"journal-title":"Development in Infancy","year":"1974","author":"bower","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682467"},{"key":"ref5","first-page":"570","article-title":"The sound of pixels","author":"zhao","year":"2018","journal-title":"ECCV"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1002\/ima.20035","article-title":"Survey of sparse and non-sparse methods in source separation","volume":"15","author":"paul","year":"2005","journal-title":"International Journal of Imaging Systems and Technology"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.02.003"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1126\/science.134.3491.1692"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.885253"},{"journal-title":"Neural Darwinism The Theory of Neuronal Group Selection","year":"1987","author":"edelman","key":"ref1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2013.03.043"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1988.196633"}],"event":{"name":"2021 IEEE International Conference on Image Processing (ICIP)","start":{"date-parts":[[2021,9,19]]},"location":"Anchorage, AK, USA","end":{"date-parts":[[2021,9,22]]}},"container-title":["2021 IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9506008\/9506009\/09506019.pdf?arnumber=9506019","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,6]],"date-time":"2022-12-06T18:46:43Z","timestamp":1670352403000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9506019\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,19]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icip42928.2021.9506019","relation":{},"subject":[],"published":{"date-parts":[[2021,9,19]]}}}