{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T15:06:02Z","timestamp":1784041562824,"version":"3.55.0"},"reference-count":79,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"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":["62472208"],"award-info":[{"award-number":["62472208"]}],"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":["62332010"],"award-info":[{"award-number":["62332010"]}],"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":["62222207"],"award-info":[{"award-number":["62222207"]}],"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":["62427808"],"award-info":[{"award-number":["62427808"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/tcsvt.2025.3629609","type":"journal-article","created":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T18:54:58Z","timestamp":1762455298000},"page":"6838-6851","source":"Crossref","is-referenced-by-count":11,"title":["Locality-Aware Cross-Modal Correspondence Learning for Dense Audio-Visual Events Detection"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-6943-462X","authenticated-orcid":false,"given":"Ling","family":"Xing","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5064-4993","authenticated-orcid":false,"given":"Hongyu","family":"Qu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0694-9458","authenticated-orcid":false,"given":"Rui","family":"Yan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4902-4663","authenticated-orcid":false,"given":"Xiangbo","family":"Shu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9008-222X","authenticated-orcid":false,"given":"Jinhui","family":"Tang","sequence":"additional","affiliation":[{"name":"College of Information Science and Technology and Artificial Intelligence, Nanjing Forestry University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"16975","article-title":"Learning audio-visual dynamics using scene graphs for audio source separation","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","volume":"35","author":"Chatterjee"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_14"},{"key":"ref3","article-title":"Show-1: Marrying pixel and latent diffusion models for text-to-video generation","author":"Junhao Zhang","year":"2023","journal-title":"arXiv:2309.15818"},{"key":"ref4","article-title":"MVP-shot: Multi-velocity progressive-alignment framework for few-shot action recognition","author":"Qu","year":"2024","journal-title":"arXiv:2405.02077"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3384392"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3203421"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3225549"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3281462"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3290351"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3319140"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02197"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413581"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5361"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612506"},{"key":"ref16","article-title":"UniAV: Unified audio-visual perception for multi-task video event localization","author":"Geng","year":"2024","journal-title":"arXiv:2404.03179"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_29"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3223688"},{"key":"ref19","article-title":"ONE-PEACE: Exploring one general representation model toward unlimited modalities","author":"Wang","year":"2023","journal-title":"arXiv:2305.11172"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683226"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547869"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00833"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3150469"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00639"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01936"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428373"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3270624"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3127029"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3546312"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00783"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33185"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2025.3567020"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19806-9_27"},{"key":"ref38","first-page":"1","article-title":"Learning clustering-based prototypes for compositional zero-shot learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Qu"},{"key":"ref39","article-title":"Longformer: The long-document transformer","author":"Beltagy","year":"2020","journal-title":"arXiv:2004.05150"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3347693"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3309899"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3197420"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3337134"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.675"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.211"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_32"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00372"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00944"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01327"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_7"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3195321"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01808"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3311447"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2445"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3326694"},{"key":"ref57","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","volume":"34","author":"Li"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3287201"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01063"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01954"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20044-1_27"},{"key":"ref62","article-title":"Achieving cross modal generalization with multimodal unified representation","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","volume":"36","author":"Xia"},{"key":"ref63","first-page":"1","article-title":"EquiAV: Leveraging equivariance for audio-visual contrastive learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.25967"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01047"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01428"},{"key":"ref67","article-title":"Empirical evaluation of rectified activations in convolutional network","author":"Xu","year":"2015","journal-title":"arXiv:1505.00853"},{"key":"ref68","article-title":"Layer normalization","author":"Lei Ba","year":"2016","journal-title":"arXiv:1607.06450"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.593"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01340"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681503"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref76","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kingma"},{"key":"ref77","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2606"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00630"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11511351\/11230532.pdf?arnumber=11230532","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T05:17:46Z","timestamp":1778217466000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11230532\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":79,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3629609","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}