{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T07:17:34Z","timestamp":1761808654251,"version":"3.28.0"},"reference-count":27,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10446302","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"11581-11585","source":"Crossref","is-referenced-by-count":2,"title":["Multiscale Matching Driven by Cross-Modal Similarity Consistency for Audio-Text Retrieval"],"prefix":"10.1109","author":[{"given":"Qian","family":"Wang","sequence":"first","affiliation":[{"name":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P.R.China"}]},{"given":"Jia-Chen","family":"Gu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P.R.China"}]},{"given":"Zhen-Hua","family":"Ling","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P.R.China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref2","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc, ICML","author":"Radford"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"article-title":"Filip: Fine-grained interactive language-image pre-training","year":"2021","author":"Yao","key":"ref4"},{"article-title":"Universal vision-language dense retrieval: Learning a unified representation space for multi-modal retrieval","volume-title":"Proc, ICLRs","author":"Liu","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11115"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-1136"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746786"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.302"},{"article-title":"ONE-PEACE: Exploring one general representation model toward unlimited modalities","year":"2023","author":"Wang","key":"ref12"},{"key":"ref13","first-page":"28708","article-title":"Masked autoencoders that listen","volume-title":"Proc, NeurIPS","volume":"35","author":"Huang"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3592025"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096972"},{"key":"ref16","first-page":"119","article-title":"Audiocaps: Generating captions for audios in the wild","volume-title":"Proc, NAACL","author":"Kim"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3149712"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746312"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref22","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc, NAACL","author":"Ming-Wei Chang Kenton"},{"key":"ref23","first-page":"315","article-title":"Deep sparse rectifier neural networks","volume-title":"Proc, AISTATS. JMLR Workshop and Conference Proceedings","author":"Glorot"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401075"},{"key":"ref25","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"Proc, ICML","author":"Chen"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"Kingma","key":"ref27"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","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\/10446302.pdf?arnumber=10446302","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:09:42Z","timestamp":1722575382000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446302\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446302","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}