{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:28:56Z","timestamp":1775230136089,"version":"3.50.1"},"reference-count":33,"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\/501100020950","name":"National Science and Technology Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020950","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\/icassp48485.2024.10446372","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"7755-7759","source":"Crossref","is-referenced-by-count":6,"title":["Multimodal Transformer Distillation for Audio-Visual Synchronization"],"prefix":"10.1109","author":[{"given":"Xuanjun","family":"Chen","sequence":"first","affiliation":[{"name":"National Taiwan University,Graduate Institute of Communication Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haibin","family":"Wu","sequence":"additional","affiliation":[{"name":"National Taiwan University,Graduate Institute of Communication Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chung-Che","family":"Wang","sequence":"additional","affiliation":[{"name":"National Taiwan University,Department of Computer Science and Information Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hung-Yi","family":"Lee","sequence":"additional","affiliation":[{"name":"National Taiwan University,Department of Computer Science and Information Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jyh-Shing Roger","family":"Jang","sequence":"additional","affiliation":[{"name":"National Taiwan University,Department of Computer Science and Information Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-196"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682524"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475587"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022646"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_13"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00223"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3153258"},{"key":"ref10","first-page":"251","article-title":"Out of time: automated lip sync in the wild","volume-title":"Asian conference on computer vision","author":"Chung"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2987720"},{"key":"ref12","article-title":"Audio-visual synchronisation in the wild","author":"Chen","year":"2021"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10861"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"issue":"7","key":"ref15","article-title":"Distilling the knowledge in a neural network","volume":"2","author":"Hinton","year":"2015"},{"key":"ref16","article-title":"Fitnets: Hints for thin deep nets","author":"Romero","year":"2014"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00409"},{"key":"ref18","article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","author":"Zagoruyko","year":"2016"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00145"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00511"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00938"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_17"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013779"},{"key":"ref24","article-title":"Paraphrasing complex network: Network compression via factor transfer","volume":"31","author":"Kim","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.754"},{"key":"ref26","article-title":"Like what you like: Knowledge distill via neuron selectivity transfer","author":"Huang","year":"2017"},{"key":"ref27","article-title":"Contrastive representation distillation","volume-title":"International Conference on Learning Representations","author":"Tian"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01603"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/SPSC.2022-6"},{"key":"ref30","first-page":"5776","article-title":"Minilm: Deep self-attention distillation for task-agnostic compression of pre-trained transformers","volume":"33","author":"Wang","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref31","article-title":"Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. arxiv","author":"Kendall","year":"2017"},{"key":"ref32","article-title":"Auxiliary tasks in multi-task learning","author":"Liebel","year":"2018"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"}],"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\/10446372.pdf?arnumber=10446372","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:44:27Z","timestamp":1722573867000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446372\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446372","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}