{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,4]],"date-time":"2025-10-04T08:02:25Z","timestamp":1759564945479,"version":"3.44.0"},"reference-count":15,"publisher":"IEEE","license":[{"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.2019.8683142","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T16:01:56Z","timestamp":1555516916000},"page":"3961-3964","source":"Crossref","is-referenced-by-count":12,"title":["Seeing through Sounds: Predicting Visual Semantic Segmentation Results from Multichannel Audio Signals"],"prefix":"10.1109","author":[{"given":"Go","family":"Irie","sequence":"first","affiliation":[{"name":"NTT Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mirela","family":"Ostrek","sequence":"additional","affiliation":[{"name":"The University of Zagreb"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haochen","family":"Wang","sequence":"additional","affiliation":[{"name":"The University of British Columbia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hirokazu","family":"Kameoka","sequence":"additional","affiliation":[{"name":"NTT Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Akisato","family":"Kimura","sequence":"additional","affiliation":[{"name":"NTT Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takahito","family":"Kawanishi","sequence":"additional","affiliation":[{"name":"NTT Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kunio","family":"Kashino","sequence":"additional","affiliation":[{"name":"NTT Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1976.1162830"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2572683"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref13","article-title":"Bilinear cnns for fine-grained visual recognition","author":"lin","year":"2017","journal-title":"Proc BMVC"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.285"},{"key":"ref15","article-title":"ESC: Dataset for environmental sound classifi-cation","author":"piczak","year":"2015","journal-title":"Proc ACM Multimedia"},{"key":"ref4","article-title":"Look, listen and learn","author":"arandjelovi?","year":"2017","journal-title":"Proc ICCV"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_48"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3126686.3126723"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.264"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00458"},{"key":"ref7","article-title":"SoundNet: Learning ssound representations from unlabeled video","author":"aytar","year":"2016","journal-title":"Proc NIPS"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1207\/s15326969eco0501_1"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/1486.001.0001"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.conb.2006.06.008"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2019,5,12]]},"location":"Brighton, UK","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\/08683142.pdf?arnumber=8683142","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T18:18:52Z","timestamp":1755800332000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8683142\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":15,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8683142","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}