{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,16]],"date-time":"2025-11-16T15:51:10Z","timestamp":1763308270057,"version":"build-2065373602"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11209406","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["Learning to Unify Audio, Visual and Text for Audio-Enhanced Visual Answer Localization"],"prefix":"10.1109","author":[{"given":"Zhibin","family":"Wen","sequence":"first","affiliation":[{"name":"Xi’an Jiaotong University,Systems Engineering Institute,Xi’an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Li","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Shenzhen Institutes of Advanced Technology,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.2196\/23656"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3258628"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095026"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3063631"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6627"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096391"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3411045"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612504"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00305"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28304"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref12","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref13","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International conference on machine learning","author":"Radford"},{"article-title":"Debertav3: Improving deberta using electra-style pre-training with gradient-disentangled embedding sharing","year":"2021","author":"He","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.585"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-023-02036-y"},{"article-title":"Tutorialvqa: Question answering dataset for tutorial videos","year":"2019","author":"Colas","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1736"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3060449"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.324"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.bionlp-1.43"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093328"},{"key":"ref23","article-title":"Fixing weight decay regularization in adam","volume":"5","author":"Loshchilov","year":"2017"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11209406.pdf?arnumber=11209406","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:56:56Z","timestamp":1761890216000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209406\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209406","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}