{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:17:42Z","timestamp":1740100662258,"version":"3.37.3"},"reference-count":24,"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"}],"funder":[{"DOI":"10.13039\/501100001321","name":"National Research Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747073","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"1970-1974","source":"Crossref","is-referenced-by-count":1,"title":["Deep Video Inpainting Guided by Audio-Visual Self-Supervision"],"prefix":"10.1109","author":[{"given":"Kyuyeon","family":"Kim","sequence":"first","affiliation":[{"name":"Korea Advanced Institute of Science and Technology (KAIST),School of Computing"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junsik","family":"Jung","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology (KAIST),School of Computing"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Woo Jae","family":"Kim","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology (KAIST),School of Computing"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sung-Eui","family":"Yoon","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology (KAIST),School of Computing"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_42"},{"key":"ref11","article-title":"Learnable gated temporal shift module for deep video inpainting","author":"chang","year":"2019","journal-title":"British Machine Vision Conference (BMVC)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00450"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_31"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00451"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00916"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682383"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01150-y"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053184"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00144"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_35"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01659"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00594"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.1145\/3197517.3201357","article-title":"Looking to listen at the cocktail party: A speaker-independent audio-visual model for speech separation","volume":"37","author":"ephrat","year":"2018","journal-title":"ACM Transactions on Graphics"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2980179.2982398"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015232"},{"key":"ref2","first-page":"435","article-title":"Objects that sound","author":"arandjelovic","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00384"},{"key":"ref20","article-title":"Discriminative sounding objects localization via self-supervised audiovisual matching","volume":"33","author":"hu","year":"2020","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref22","first-page":"247","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":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref23","article-title":"Image inpainting for irregular holes using partial convolutions","author":"liu","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"}],"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\/09747073.pdf?arnumber=9747073","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T20:13:50Z","timestamp":1661199230000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747073\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747073","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}