{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:06:22Z","timestamp":1784268382033,"version":"3.55.0"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002341","name":"Academy of Finland","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002341","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10448489","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"5325-5329","source":"Crossref","is-referenced-by-count":26,"title":["Synchformer: Efficient Synchronization From Sparse Cues"],"prefix":"10.1109","author":[{"given":"Vladimir","family":"Iashin","sequence":"first","affiliation":[{"name":"Tampere University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weidi","family":"Xie","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Esa","family":"Rahtu","sequence":"additional","affiliation":[{"name":"Tampere University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew","family":"Zisserman","sequence":"additional","affiliation":[{"name":"University of Oxford"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682524"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-54427-4_19","article-title":"Out of time: automated lip sync in the wild","volume-title":"Workshop on Multi-view Lipreading, ACCV","author":"Chung"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_13"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_27"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"ref6","article-title":"Audio-visual synchronisation in the wild","volume-title":"BMVC","author":"Chen"},{"key":"ref7","article-title":"Sparse in space and time: Audio-visual synchronisation with trainable selectors","volume-title":"BMVC","author":"Iashin"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref9","article-title":"Audio vision: Using audiovisual synchrony to locate sounds","author":"Hershey","year":"1999","journal-title":"NeurIPS"},{"key":"ref10","article-title":"Facesync: A linear operator for measuring synchronization of video facial images and audio tracks","author":"Slaney","year":"2000","journal-title":"NeurIPS"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54184-6_6"},{"key":"ref12","volume-title":"Fundamentals of speech recognition","author":"Rabiner","year":"1993"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682863"},{"key":"ref14","article-title":"On attention modules for audio-visual synchronization","volume-title":"Workshop on Sight and Sound, CVPR","author":"Khosravan"},{"key":"ref15","article-title":"Endto-end lip synchronisation based on pattern classification","volume-title":"SLT Workshop","author":"Kim"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10861"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097209"},{"key":"ref18","article-title":"VGG-Sound: A large-scale audio-visual dataset","volume-title":"ICASSP","author":"Chen"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-698"},{"key":"ref20","article-title":"Keeping your eye on the ball: Trajectory attention in video transformers","author":"Mandela","year":"2021","journal-title":"NeurIPS"},{"key":"ref21","article-title":"Is spacetime attention all you need for video understanding?","volume-title":"ICML","author":"Bertasius"},{"key":"ref22","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref23","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019","journal-title":"NAACL: HLT"},{"key":"ref24","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford"},{"key":"ref25","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref26","article-title":"LRS3-TED: a large-scale dataset for visual speech recognition","author":"Afouras","year":"2018"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10448489.pdf?arnumber=10448489","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,3]],"date-time":"2024-08-03T04:46:35Z","timestamp":1722660395000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448489\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10448489","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}