{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T07:58:18Z","timestamp":1777103898645,"version":"3.51.4"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746786","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"4793-4797","source":"Crossref","is-referenced-by-count":24,"title":["Audio-Text Retrieval in Context"],"prefix":"10.1109","author":[{"given":"Siyu","family":"Lou","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China"}]},{"given":"Xuenan","family":"Xu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China"}]},{"given":"Mengyue","family":"Wu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China"}]},{"given":"Kai","family":"Yu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540039"},{"key":"ref11","article-title":"Efficient estimation of word representations in vector space","author":"mikolov","year":"2013"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.572"},{"key":"ref17","article-title":"Learnable pooling with context gating for video classification","author":"miech","year":"2017"},{"key":"ref18","article-title":"Deep fragment embeddings for bidirectional image sentence mapping","author":"karpathy","year":"2014"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682632"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1460096.1460115"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"ref5","first-page":"119","article-title":"Audiocaps: Generating captions for audios in the wild","author":"kim","year":"2019","journal-title":"Proceedings of Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)"},{"key":"ref8","article-title":"Learning a text-video embedding from incomplete and heterogeneous data","author":"miech","year":"2018"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2227"},{"key":"ref2","article-title":"Use what you have: Video retrieval using representations from collaborative experts","author":"liu","year":"2019"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746786.pdf?arnumber=9746786","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:06:47Z","timestamp":1660594007000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746786\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746786","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}