{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:21:59Z","timestamp":1766067719158,"version":"3.37.3"},"reference-count":70,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["62101393"],"award-info":[{"award-number":["62101393"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018557","name":"Project of Sanya Yazhou Bay Science and Technology City","doi-asserted-by":"publisher","award":["SCKJ-JYRC-2022-17","SCKJ-JYRC-2022-76"],"award-info":[{"award-number":["SCKJ-JYRC-2022-17","SCKJ-JYRC-2022-76"]}],"id":[{"id":"10.13039\/501100018557","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022ZD0160604"],"award-info":[{"award-number":["2022ZD0160604"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["62176194"],"award-info":[{"award-number":["62176194"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Major Project of loV","award":["2020AAA001"],"award-info":[{"award-number":["2020AAA001"]}]},{"name":"Youth Fund Project of Hainan Natural Science Foundation","award":["6220N344"],"award-info":[{"award-number":["6220N344"]}]},{"name":"CAAI-Huawei MindSpore Open Fund","award":["CAAIXSJLJJ-2022-001A"],"award-info":[{"award-number":["CAAIXSJLJJ-2022-001A"]}]},{"name":"Knowledge Innovation Program of Wuhan-Basic Research"},{"DOI":"10.13039\/501100008860","name":"Sanya Science and Education Innovation Park of Wuhan University of Technology","doi-asserted-by":"publisher","award":["2022KF0020"],"award-info":[{"award-number":["2022KF0020"]}],"id":[{"id":"10.13039\/501100008860","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["WUT:223110001"],"award-info":[{"award-number":["WUT:223110001"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005230","name":"Natural Science Foundation of Chongqing","doi-asserted-by":"publisher","award":["cstc2021jcyj-msxmX1148"],"award-info":[{"award-number":["cstc2021jcyj-msxmX1148"]}],"id":[{"id":"10.13039\/501100005230","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Open Project of Wuhan University of Technology Chongqing Research Institute","award":["ZL2021-6"],"award-info":[{"award-number":["ZL2021-6"]}]},{"name":"Hainan Special Ph.D. Scientific Research Foundation of Sanya Yazhou Bay Science and Technology City","award":["HSPHDSRF-2023-03-002"],"award-info":[{"award-number":["HSPHDSRF-2023-03-002"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Geosci. Remote Sensing"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tgrs.2023.3264006","type":"journal-article","created":{"date-parts":[[2023,4,3]],"date-time":"2023-04-03T17:30:44Z","timestamp":1680543044000},"page":"1-14","source":"Crossref","is-referenced-by-count":8,"title":["Self-Supervision Interactive Alignment for Remote Sensing Image\u2013Audio Retrieval"],"prefix":"10.1109","volume":"61","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-3362-3023","authenticated-orcid":false,"given":"Jinghao","family":"Huang","sequence":"first","affiliation":[{"name":"Sanya Science and Education Innovation Park, Wuhan University of Technology, Sanya, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2903-6723","authenticated-orcid":false,"given":"Yaxiong","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Artificial Intelligence, Wuhan University of Technology, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4006-7029","authenticated-orcid":false,"given":"Shengwu","family":"Xiong","sequence":"additional","affiliation":[{"name":"Sanya Science and Education Innovation Park, Wuhan University of Technology, Sanya, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7037-5188","authenticated-orcid":false,"given":"Xiaoqiang","family":"Lu","sequence":"additional","affiliation":[{"name":"College of Physics and Information Engineering, Fuzhou University, Fuzhou, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2014.10.029"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.282"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/jproc.2016.2598228"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.10.053"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/jstars.2020.3027954"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2019.2946751"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2019.2931801"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2022.3177322"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2018.2836307"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2021.3055613"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2018.2885616"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2021.3101504"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2019.2916734"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2019.2951160"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/lgrs.2017.2651056"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2017.2756911"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2020.2991657"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2006.890579"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3390\/ijgi6110364"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2021.3060705"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2021.3070129"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3390\/rs12010084"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/jstars.2019.2949220"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2022.105090"},{"key":"ref25","first-page":"12","article-title":"VSE++: Improving visual-semantic embeddings with hard negatives","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Faghri"},{"key":"ref26","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2016.2606648"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2021.3078451"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462924"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/jstars.2021.3070872"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1162\/0899766042321814"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/11752790_2"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2011.5995350"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3390\/rs12030405"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2022.3163706"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2013.2276704"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/476"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2019.2954741"},{"key":"ref39","first-page":"99","article-title":"Semi-supervised multi-modal learning with balanced spectral decomposition","volume-title":"Proc. 34th AAAI Conf. Artif. Intell.","author":"Hu"},{"key":"ref40","first-page":"1858","article-title":"Unsupervised learning of spoken language with visual context","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Harwath"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.73"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.12.078"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/jstars.2022.3194076"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2018.2798607"},{"key":"ref45","article-title":"Class-aware sounding objects localization via audiovisual correspondence","author":"Hu","year":"2021","journal-title":"arXiv:2112.11749"},{"key":"ref46","first-page":"1801","article-title":"Visual sound localization in the wild by cross-modal interference erasing","volume-title":"Proc. 36th AAAI Conf. Artif. Intell.","author":"Liu"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_18"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2019.2952095"},{"key":"ref49","first-page":"1","article-title":"MultiModalQA: Complex question answering over text, tables and images","volume-title":"Proc. 9th Int. Conf. Learn. Represent.","author":"Talmor"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00037"},{"key":"ref51","article-title":"Multi-level attention fusion network for audio-visual event recognition","author":"Brousmiche","year":"2021","journal-title":"arXiv:2106.06736"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"ref53","first-page":"8436","article-title":"Positive sample propagation along the audio-visual event line","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Zhou"},{"key":"ref54","first-page":"10454","article-title":"Listen to look: Action recognition by previewing audio","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Gao"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_26"},{"key":"ref56","first-page":"1326","article-title":"Exploring heterogeneous clues for weakly-supervised audio-visual video parsing","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Wu"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_5"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2015.7298682"},{"key":"ref59","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/cits.2016.7546397"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3534117"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/j.infsof.2022.106922"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/tr.2019.2931559"},{"key":"ref64","first-page":"1979","article-title":"Polysemous visual-semantic embedding for cross-modal retrieval","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Song"},{"key":"ref65","first-page":"8415","article-title":"Probabilistic embeddings for cross-modal retrieval","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Chun"},{"key":"ref66","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.90"},{"key":"ref68","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00986"},{"key":"ref70","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","volume":"37","author":"Xu"}],"container-title":["IEEE Transactions on Geoscience and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/36\/10006360\/10091166.pdf?arnumber=10091166","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T20:53:41Z","timestamp":1709240021000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10091166\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1109\/tgrs.2023.3264006","relation":{},"ISSN":["0196-2892","1558-0644"],"issn-type":[{"type":"print","value":"0196-2892"},{"type":"electronic","value":"1558-0644"}],"subject":[],"published":{"date-parts":[[2023]]}}}