{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,11]],"date-time":"2026-01-11T05:24:31Z","timestamp":1768109071171,"version":"3.49.0"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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","award":["62306029"],"award-info":[{"award-number":["62306029"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62206234"],"award-info":[{"award-number":["62206234"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CCF-Tencent Rhino-Bird Open Research Fund"},{"name":"ARC Discovery","award":["DP1900102479"],"award-info":[{"award-number":["DP1900102479"]}]},{"name":"Research Grant Council of Hong Kong","award":["ECS-HKUST22201322"],"award-info":[{"award-number":["ECS-HKUST22201322"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62271432"],"award-info":[{"award-number":["62271432"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100020785","name":"Shenzhen Research Institute of Big Data","doi-asserted-by":"publisher","award":["T00120220002"],"award-info":[{"award-number":["T00120220002"]}],"id":[{"id":"10.13039\/501100020785","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Provincial Key Laboratory of Big Data Computing"},{"DOI":"10.13039\/501100004853","name":"Chinese University of Hong Kong","doi-asserted-by":"publisher","award":["B10120210117-KP02"],"award-info":[{"award-number":["B10120210117-KP02"]}],"id":[{"id":"10.13039\/501100004853","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001348","name":"Agency for Science, Technology and Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001348","id-type":"DOI","asserted-by":"publisher"}]},{"name":"AME Programmatic Funding Scheme","award":["A18A2b0046"],"award-info":[{"award-number":["A18A2b0046"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2023.3323876","type":"journal-article","created":{"date-parts":[[2023,10,13]],"date-time":"2023-10-13T18:06:26Z","timestamp":1697220386000},"page":"4480-4489","source":"Crossref","is-referenced-by-count":7,"title":["Deep Cross-Modal Retrieval Between Spatial Image and Acoustic Speech"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9511-6713","authenticated-orcid":false,"given":"Xinyuan","family":"Qian","sequence":"first","affiliation":[{"name":"School of Computer and Communication Engineering, University of Science and Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4942-7748","authenticated-orcid":false,"given":"Wei","family":"Xue","sequence":"additional","affiliation":[{"name":"Division of Emerging Interdisciplinary Areas, Hong Kong University of Science and Technology, Hong Kong, SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5089-6317","authenticated-orcid":false,"given":"Qiquan","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Telecommunications, University of New South Wales, Sydney, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0021-5661","authenticated-orcid":false,"given":"Ruijie","family":"Tao","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9158-9401","authenticated-orcid":false,"given":"Haizhou","family":"Li","sequence":"additional","affiliation":[{"name":"Shenzhen Research Institute of Big Data, School of Data Science, The Chinese University of Hong Kong, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123326"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.232"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01275"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.01.078"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01939"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2877127"},{"key":"ref7","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref8","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jia","year":"2021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01101"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01759"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3181116"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.11.035"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747669"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01829"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1121\/1.4926438"},{"issue":"4","key":"ref16","first-page":"249","article-title":"Comparison of different impulse response measurement techniques","volume":"50","author":"Stan","year":"2002","journal-title":"J. Audio Eng. Soc."},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3390\/app11031150"},{"key":"ref18","first-page":"658","article-title":"Few-shot audio-visual learning of environment acoustics","volume-title":"Proc. Int. Conf. Neural Inf. Proc. Syst.","author":"Majumder","year":"2022"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01526"},{"key":"ref20","first-page":"9622","article-title":"Learning to set waypoints for audio-visual navigation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00817"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00122"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00035"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3152086"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3323873.3325029"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2705068"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-4380-9_14"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1873987"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/957013.957143"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2013.2276704"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502097"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2610969"},{"key":"ref33","first-page":"450","article-title":"A kernel method for canonical correlation analysis","volume-title":"Proc. Int. Meeting Psychometric Soc.","volume":"1","author":"Akaho","year":"2001"},{"key":"ref34","first-page":"689","article-title":"Multimodal deep learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ngiam","year":"2011"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298966"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210036"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806240"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107335"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01174"},{"key":"ref40","first-page":"233","article-title":"Multimodal learning with deep Boltzmann machines","volume-title":"Proc. Int. Conf. Neural Inf. Proc. Syst.","author":"Srivastava","year":"2012"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.17743\/jaes.2018.0069"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1250\/ast.41.675"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref44","first-page":"487","article-title":"Learning deep features for scene recognition using places database","volume-title":"Proc. Neural Inf. Process. Syst.","volume":"27","author":"Zhou","year":"2014"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1661100"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.26.041002.131047"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_2"},{"key":"ref52","article-title":"The replica dataset: A digital replica of indoor spaces","author":"Straub","year":"2019"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00374"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075614"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2017.7952261"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01064"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref61","article-title":"VoiceFixer: Toward general speech restoration with neural vocoder","author":"Liu","year":"2021"},{"key":"ref62","article-title":"Pytorch library for CAM methods","year":"2021"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10285477.pdf?arnumber=10285477","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T18:49:24Z","timestamp":1710269364000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10285477\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3323876","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}