{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:22:25Z","timestamp":1772907745825,"version":"3.50.1"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9053895","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"4372-4376","source":"Crossref","is-referenced-by-count":56,"title":["What Makes the Sound?: A Dual-Modality Interacting Network for Audio-Visual Event Localization"],"prefix":"10.1109","author":[{"given":"Janani","family":"Ramaswamy","sequence":"first","affiliation":[]}],"member":"263","reference":[{"key":"ref10","article-title":"End-to-end audio visual scene-aware dialog using mul-timodal attention-based video features","author":"hori","year":"2019","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01283"},{"key":"ref12","article-title":"An attempt towards interpretable audio-visual video captioning","author":"tian","year":"2018"},{"key":"ref13","article-title":"See, hear, and read: Deep aligned representations","author":"aytar","year":"2017"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref15","article-title":"Objects that sound","author":"arandjelovic","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00458"},{"key":"ref17","article-title":"Audio-visual event localization in unconstrained videos","author":"tian","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683226"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"},{"key":"ref4","article-title":"Audio-visual scene analysis with self-supervised multisensory features","author":"owens","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.264"},{"key":"ref5","article-title":"The sound of pixels","author":"zhao","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref8","article-title":"Out of time: automated lip sync in the wild","author":"chung","year":"2016","journal-title":"Asian Conference on Computer Vision"},{"key":"ref7","article-title":"Ambient sound provides supervision for visual learning","author":"owens","year":"2016","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref1","article-title":"Soundnet: Learning sound representations from unlabeled video","author":"aytar","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00774"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2911488"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298968"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Barcelona, Spain","start":{"date-parts":[[2020,5,4]]},"end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09053895.pdf?arnumber=9053895","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:19:11Z","timestamp":1656375551000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053895\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053895","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}