{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T06:14:44Z","timestamp":1744179284622},"reference-count":21,"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\/icpr56361.2022.9956130","type":"proceedings-article","created":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T19:34:13Z","timestamp":1669750453000},"page":"16-22","source":"Crossref","is-referenced-by-count":1,"title":["Detect Audio-Video Temporal Synchronization Errors in Advertisements (Ads)"],"prefix":"10.1109","author":[{"given":"Zongyi Joe","family":"Liu","sequence":"first","affiliation":[{"name":"Amazon.com,Customer Experience and Business Trends,Seattle,Washington,98121"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Devin","family":"Chen","sequence":"additional","affiliation":[{"name":"Amazon.com,Customer Experience and Business Trends,Seattle,Washington,98121"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yarong","family":"Feng","sequence":"additional","affiliation":[{"name":"Amazon.com,Customer Experience and Business Trends,Seattle,Washington,98121"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan","family":"Ling","sequence":"additional","affiliation":[{"name":"Amazon.com,Customer Experience and Business Trends,Seattle,Washington,98121"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shunyan","family":"Luo","sequence":"additional","affiliation":[{"name":"Amazon.com,Customer Experience and Business Trends,Seattle,Washington,98121"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shujing","family":"Dong","sequence":"additional","affiliation":[{"name":"Amazon.com,Customer Experience and Business Trends,Seattle,Washington,98121"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bruce","family":"Ferry","sequence":"additional","affiliation":[{"name":"Amazon.com,Customer Experience and Business Trends,Seattle,Washington,98121"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"year":"0","key":"ref10","article-title":"Voice frequency"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-11"},{"key":"ref12","article-title":"Voxceleb: Large-scale speaker verification in the wild","author":"nagrani","year":"2019","journal-title":"Computer Science and Language"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-950","article-title":"Voxceleb: a large-scale speaker identification dataset","author":"nagrani","year":"2017","journal-title":"InterSpeech"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"815","DOI":"10.1109\/CVPR.2015.7298682","article-title":"Facenet: A unified embedding for face recognition and clustering","author":"schroff","year":"2015","journal-title":"2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.202"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1064"},{"year":"0","key":"ref19"},{"article-title":"Audiovisual slowfast networks for video recognition","year":"2020","author":"xiao","key":"ref4"},{"key":"ref3","first-page":"7774","article-title":"Cooperative learning of audio and video models from self-supervised synchronization","author":"korbar","year":"2018","journal-title":"Proceedings of the 32Nd International Conference on Neural Information Processing Systems"},{"key":"ref6","article-title":"Out of time: automated lip sync in the wild","author":"chung","year":"2016","journal-title":"Workshop on Multi-view Lip-reading ACCV"},{"year":"2008","key":"ref5","article-title":"Iinternational telecommunications union"},{"key":"ref8","first-page":"374","article-title":"Distance measures for speech recognition, psychological and instrumental","author":"mermelstein","year":"1976","journal-title":"Pattern Recognition and Artificial Intelligence"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163420"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICVRV.2017.00070"},{"article-title":"Detection of audio-video synchronization errors via event detection","year":"2021","author":"ebenezer","key":"ref9"},{"year":"0","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2603342"}],"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\/09956130.pdf?arnumber=9956130","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T20:05:24Z","timestamp":1671480324000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9956130\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,21]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icpr56361.2022.9956130","relation":{},"subject":[],"published":{"date-parts":[[2022,8,21]]}}}