{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T10:14:23Z","timestamp":1740132863765,"version":"3.37.3"},"reference-count":28,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/lsp.2023.3313090","type":"journal-article","created":{"date-parts":[[2023,9,7]],"date-time":"2023-09-07T17:49:48Z","timestamp":1694108988000},"page":"1317-1321","source":"Crossref","is-referenced-by-count":3,"title":["Cooperative Game Modeling With Weighted Token-Level Alignment for Audio-Text Retrieval"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7792-6352","authenticated-orcid":false,"given":"Yifei","family":"Xin","sequence":"first","affiliation":[{"name":"School of Electronic and Computer Engineering, Peking University, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8623-6350","authenticated-orcid":false,"given":"Baojun","family":"Wang","sequence":"additional","affiliation":[{"name":"Noah's Ark Lab, Huawei, Shenzhen, China"}]},{"given":"Lifeng","family":"Shang","sequence":"additional","affiliation":[{"name":"Noah's Ark Lab, Huawei, Shenzhen, China"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401075"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01082"},{"key":"ref15","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"article-title":"Disentangled representation learning for text-video retrieval","year":"2022","author":"wang","key":"ref14"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1136"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097117"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747336"},{"key":"ref1","article-title":"Language-based audio retrieval with pre-trained models","author":"mei","year":"2022","journal-title":"Detection Classification Acoust Scenes Events Challenge"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2972956"},{"journal-title":"A Course in Game Theory","year":"1994","author":"ferguson","key":"ref16"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00244"},{"key":"ref18","first-page":"1196","article-title":"The Banzhaf interaction index in game with coalition structure","author":"li","year":"0","journal-title":"Proc Chin Control Decis Conf"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2016.02.001"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/116"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"ref25","first-page":"119","article-title":"Audiocaps: Generating captions for audios in the wild","author":"kim","year":"0","journal-title":"Proc Conf North Amer Chapter Assoc Comput Linguistics Hum Lang Technol"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevC.16.80"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00202-2_12"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1080\/03081079.2021.1924166"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref27","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"kenton","year":"0","journal-title":"Proc NAACL-HLT"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2010.11.027"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s001820050125"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11115"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3149712"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1478"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746786"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096972"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/97\/10036333\/10243086.pdf?arnumber=10243086","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,9]],"date-time":"2023-10-09T19:47:47Z","timestamp":1696880867000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10243086\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/lsp.2023.3313090","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"type":"print","value":"1070-9908"},{"type":"electronic","value":"1558-2361"}],"subject":[],"published":{"date-parts":[[2023]]}}}