{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T15:27:40Z","timestamp":1767713260665},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747644","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"141-145","source":"Crossref","is-referenced-by-count":9,"title":["Urban Sound & Sight: Dataset And Benchmark For Audio-Visual Urban Scene Understanding"],"prefix":"10.1109","author":[{"given":"Magdalena","family":"Fuentes","sequence":"first","affiliation":[{"name":"New York University,New York,NY"}]},{"given":"Bea","family":"Steers","sequence":"additional","affiliation":[{"name":"New York University,New York,NY"}]},{"given":"Pablo","family":"Zinemanas","sequence":"additional","affiliation":[{"name":"Universitat Pompeu Fabra,Barcelona,Spain"}]},{"given":"Martin","family":"Rocamora","sequence":"additional","affiliation":[{"name":"Universidad de la República,Montevideo,Uruguay"}]},{"given":"Luca","family":"Bondi","sequence":"additional","affiliation":[{"name":"Bosch Research,Pittsburgh,PA,USA"}]},{"given":"Julia","family":"Wilkins","sequence":"additional","affiliation":[{"name":"New York University,New York,NY"}]},{"given":"Qianyi","family":"Shi","sequence":"additional","affiliation":[{"name":"New York University,New York,NY"}]},{"given":"Yao","family":"Hou","sequence":"additional","affiliation":[{"name":"New York University,New York,NY"}]},{"given":"Samarjit","family":"Das","sequence":"additional","affiliation":[{"name":"Bosch Research,Pittsburgh,PA,USA"}]},{"given":"Xavier","family":"Serra","sequence":"additional","affiliation":[{"name":"Universitat Pompeu Fabra,Barcelona,Spain"}]},{"given":"Juan Pablo","family":"Bello","sequence":"additional","affiliation":[{"name":"New York University,New York,NY"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2015.96"},{"key":"ref11","article-title":"Objects that sound","author":"arandjelovic","year":"2018","journal-title":"The European Conference on Computer Vision"},{"key":"ref12","first-page":"570","article-title":"The sound of pixels","author":"zhao","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision"},{"article-title":"Into the wild with audioscope: Unsupervised audio-visual separation of on-screen sounds","year":"2020","author":"tzinis","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01659"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682475"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00715"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2016.7760424"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2657381"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2017.07.007"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO54536.2021.9616168"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2021.3090678"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2018.2885636"},{"article-title":"YOLOv3: An incremental improvement","year":"2018","author":"redmon","key":"ref2"},{"article-title":"Unsupervised visual representation learning by context prediction","year":"2016","author":"doersch","key":"ref9"},{"key":"ref1","first-page":"21","article-title":"SSD: Single shot multibox detector","author":"liu","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.33682\/kfmf-zv94"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8170052"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415085"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350535"},{"key":"ref23","first-page":"102","article-title":"Playing for data: Ground truth from computer games","author":"richter","year":"2016","journal-title":"European Conference on Computer Vision (ECCV)"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2018.2885636"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937220"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2022,5,23]]},"location":"Singapore, Singapore","end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09747644.pdf?arnumber=9747644","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T20:10:24Z","timestamp":1661199024000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747644\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747644","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}