{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:26:31Z","timestamp":1753601191912},"reference-count":17,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10097209","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":5,"title":["MODEFORMER: Modality-Preserving Embedding For Audio-Video Synchronization Using Transformers"],"prefix":"10.1109","author":[{"given":"Akash","family":"Gupta","sequence":"first","affiliation":[{"name":"New York University"}]},{"given":"Rohun","family":"Tripathi","sequence":"additional","affiliation":[{"name":"Amazon Studios"}]},{"given":"Wondong","family":"Jang","sequence":"additional","affiliation":[{"name":"Amazon Studios"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682524"},{"key":"ref3","article-title":"Audio-visual synchronization in the wild","author":"Chen","year":"2021","journal-title":"BMVC"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10861"},{"key":"ref5","article-title":"Audio Vision: Using audio-visual synchrony to locate sounds","author":"Hershey","year":"1999","journal-title":"NeurIPS"},{"key":"ref6","article-title":"FaceSync: A linear operator for measuring synchronization of video facial images and audio tracks","author":"Slaney","year":"2000","journal-title":"NeurIPS"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2002.5745053"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1002\/vis.4340020404"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref10","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"article-title":"Lrs3-ted: a large-scale dataset for visual speech recognition","year":"2018","author":"Afouras","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461326"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054253"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10097209.pdf?arnumber=10097209","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T00:18:44Z","timestamp":1705018724000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10097209\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10097209","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}