{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,26]],"date-time":"2026-04-26T05:00:29Z","timestamp":1777179629082,"version":"3.51.4"},"reference-count":66,"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":["62372003"],"award-info":[{"award-number":["62372003"]}],"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":["U21B2045"],"award-info":[{"award-number":["U21B2045"]}],"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":["U20A20223"],"award-info":[{"award-number":["U20A20223"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"University Synergy Innovation Program of Anhui Province","award":["GXXT-2022-036"],"award-info":[{"award-number":["GXXT-2022-036"]}]},{"DOI":"10.13039\/501100003995","name":"Natural Science Foundation of Anhui Province","doi-asserted-by":"publisher","award":["2308085Y40"],"award-info":[{"award-number":["2308085Y40"]}],"id":[{"id":"10.13039\/501100003995","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans.Inform.Forensic Secur."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tifs.2024.3388949","type":"journal-article","created":{"date-parts":[[2024,4,15]],"date-time":"2024-04-15T17:29:05Z","timestamp":1713202145000},"page":"4986-4998","source":"Crossref","is-referenced-by-count":10,"title":["Attribute-Guided Cross-Modal Interaction and Enhancement for Audio-Visual Matching"],"prefix":"10.1109","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3059-798X","authenticated-orcid":false,"given":"Jiaxiang","family":"Wang","sequence":"first","affiliation":[{"name":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9820-4743","authenticated-orcid":false,"given":"Aihua","family":"Zheng","sequence":"additional","affiliation":[{"name":"Information Materials and Intelligent Sensing Laboratory of Anhui Province and Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Artificial Intelligence, Anhui University, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Yan","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Illinois Institute of Technology, Chicago, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3807-991X","authenticated-orcid":false,"given":"Ran","family":"He","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8375-3590","authenticated-orcid":false,"given":"Jin","family":"Tang","sequence":"additional","affiliation":[{"name":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1111\/j.2044-8295.1986.tb02199.x"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1111\/j.2044-8295.2011.02041.x"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3758\/s13414-015-1045-8"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.cub.2003.09.005"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2020.02.001"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01524"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00805"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3217738"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2021.3059274"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2020.3039045"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2019.2941773"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3222963"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3127029"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2020.2994740"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00879"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401302"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/DICTA47822.2019.8945863"},{"key":"ref18","first-page":"1","article-title":"Disjoint mapping network for cross-modal matching of voices and faces","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wen"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413710"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3050089"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3222936"},{"key":"ref22","first-page":"1","article-title":"Generative adversarial nets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Goodfellow"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747704"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3071243"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01608"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01095"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.41"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01594"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01602"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-950"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.41"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_5"},{"key":"ref33","first-page":"1","article-title":"From inference to generation: End-to-end fully self-supervised generation of human face from speech","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Choi"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3083257"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475391"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123438"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240509"},{"key":"ref38","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"34","author":"Li"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548336"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01521"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5361"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3150469"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00278"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3096037"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2985716"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00359"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413869"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01030"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref50","first-page":"1","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Gu"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_29"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/94"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3284750"},{"key":"ref56","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM54844.2022.00075"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref59","article-title":"MobileViT: Light-weight, general-purpose, and mobile-friendly vision transformer","author":"Mehta","year":"2022","journal-title":"arXiv:2110.02178"},{"key":"ref60","first-page":"5785","article-title":"FastViT: A fast hybrid vision transformer using structural reparameterization","volume-title":"Proc. IEEE Int. Conf. Comput. Vis.","author":"Vasu"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02174"},{"key":"ref62","article-title":"RobustART: Benchmarking robustness on architecture design and training techniques","author":"Tang","year":"2021","journal-title":"arXiv:2109.05211"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/526"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097207"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00443"},{"key":"ref66","article-title":"Learning in audio-visual context: A review, analysis, and new perspective","author":"Wei","year":"2022","journal-title":"arXiv:2208.09579"}],"container-title":["IEEE Transactions on Information Forensics and Security"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10206\/10319981\/10499254.pdf?arnumber=10499254","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,8]],"date-time":"2024-05-08T04:47:51Z","timestamp":1715143671000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10499254\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/tifs.2024.3388949","relation":{},"ISSN":["1556-6013","1556-6021"],"issn-type":[{"value":"1556-6013","type":"print"},{"value":"1556-6021","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}