{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T08:17:45Z","timestamp":1725610665966},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"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":[[2022,8,21]]},"DOI":"10.1109\/icpr56361.2022.9956384","type":"proceedings-article","created":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T19:34:13Z","timestamp":1669750453000},"page":"9-15","source":"Crossref","is-referenced-by-count":0,"title":["The Sound of Bounding-Boxes"],"prefix":"10.1109","author":[{"given":"Takashi","family":"Oya","sequence":"first","affiliation":[{"name":"Waseda Research Institute for Science and Engineering,Japan,513-1"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shohei","family":"Iwase","sequence":"additional","affiliation":[{"name":"Waseda Research Institute for Science and Engineering,Japan,513-1"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shigeo","family":"Morishima","sequence":"additional","affiliation":[{"name":"Waseda Research Institute for Science and Engineering,Japan,513-1"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.75"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01659"},{"key":"ref11","article-title":"Do we need sound for sound source localization?","author":"oya","year":"2020","journal-title":"Asian Conference on Computer Vision (ACCV)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00182"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01049"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7951787"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2016.7760220"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_3"},{"key":"ref18","article-title":"Audio\/visual independent components","author":"smaragdis","year":"2003","journal-title":"7th Int Conf Independent Component Analysis Signal Separation (ICA)"},{"key":"ref19","article-title":"Audiovisual object localization and separation using low-rank and sparsity","author":"pu","year":"2017","journal-title":"International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2010.2050650"},{"key":"ref4","article-title":"Audio vision: Using audiovisual synchrony to locate sounds","author":"hershey","year":"1999","journal-title":"Neural Information Processing Systems (NIPS)"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1400"},{"article-title":"Categorical Reparameterization with Gumbel-Softmax","year":"2016","author":"jang","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"ref29","article-title":"Openimages: A public dataset for large-scale multi-label and multi-class image classification","author":"krasin","year":"2017","journal-title":"Dataset"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.274"},{"key":"ref8","article-title":"Objects that sound","author":"arandjelovi?","year":"2018","journal-title":"European Conference on Computer Vision (ECCV)"},{"key":"ref7","article-title":"Cooperative learning of audio and video models from self-supervised synchronization","author":"korbar","year":"2018","journal-title":"Neural Information Processing Systems (NIPS)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00458"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_26"},{"key":"ref20","article-title":"The sound of pixels","author":"zhao","year":"2018","journal-title":"European Conference on Computer Vision (ECCV)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00398"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682467"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00124"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01524"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1955"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201357"}],"event":{"name":"2022 26th International Conference on Pattern Recognition (ICPR)","start":{"date-parts":[[2022,8,21]]},"location":"Montreal, QC, Canada","end":{"date-parts":[[2022,8,25]]}},"container-title":["2022 26th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9956007\/9955631\/09956384.pdf?arnumber=9956384","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T20:05:10Z","timestamp":1671480310000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9956384\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,21]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icpr56361.2022.9956384","relation":{},"subject":[],"published":{"date-parts":[[2022,8,21]]}}}