{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T05:18:06Z","timestamp":1768281486270,"version":"3.49.0"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Innovative Development Joint Fund Key Projects of Shandong NSF","award":["ZR2023LZH003"],"award-info":[{"award-number":["ZR2023LZH003"]}]},{"name":"Taishan Industrial Experts Program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1109\/tnnls.2025.3600878","type":"journal-article","created":{"date-parts":[[2025,9,4]],"date-time":"2025-09-04T18:22:40Z","timestamp":1757010160000},"page":"52-66","source":"Crossref","is-referenced-by-count":0,"title":["Fine-Grained Audio\u2013Visual Event Localization"],"prefix":"10.1109","volume":"37","author":[{"given":"Baoyu","family":"Fan","sequence":"first","affiliation":[{"name":"College of Computer Science, Nankai University, Tianjin, China"}]},{"given":"Lu","family":"Liu","sequence":"additional","affiliation":[{"name":"IEIT Systems Company Ltd., Jinan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6143-0854","authenticated-orcid":false,"given":"Xiaochuan","family":"Li","sequence":"additional","affiliation":[{"name":"IEIT Systems Company Ltd., Jinan, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6318-3342","authenticated-orcid":false,"given":"Runze","family":"Zhang","sequence":"additional","affiliation":[{"name":"IEIT Systems Company Ltd., Jinan, China"}]},{"given":"Liang","family":"Jin","sequence":"additional","affiliation":[{"name":"IEIT Systems Company Ltd., Jinan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9086-1178","authenticated-orcid":false,"given":"Jin","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Computer Science, Nankai University, Tianjin, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02197"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00639"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01936"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3290083"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pbio.1002075"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1250\/ast.28.61"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3672079"},{"key":"ref9","article-title":"Modality-independent teachers meet weakly-supervised audio-visual event parser","author":"Lai","year":"2023","journal-title":"arXiv:2305.17343"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00399"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01017"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_8"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_29"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01938"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01808"},{"key":"ref16","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":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.476"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3126648"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3217368"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00296"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01805"},{"key":"ref23","first-page":"11449","article-title":"Exploring cross-video and cross-modality signals for weakly-supervised audio-visual video parsing","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Lin"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_26"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.8"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.494"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01065"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3318289"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548417"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3261927"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3367940"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_1"},{"key":"ref33","article-title":"Temporal action localization with enhanced instant discriminability","author":"Shi","year":"2023","journal-title":"arXiv:2309.05590"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413581"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00833"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3270624"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681503"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3324498"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3127029"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3106814"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3226328"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3150469"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612506"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25093"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01011"},{"key":"ref49","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017","journal-title":"arXiv:1705.06950"},{"key":"ref50","first-page":"10078","article-title":"Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Tong"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01398"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00633"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3190367"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_12"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_35"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1017\/S026988890999035X"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-698"},{"key":"ref65","article-title":"BEATs: Audio pre-training with acoustic tokenizers","author":"Chen","year":"2022","journal-title":"arXiv:2212.09058"},{"key":"ref66","first-page":"64131","article-title":"SSLAM: Enhancing self-supervised models with audio mixtures for polyphonic soundscapes","volume-title":"Proc. 13th Int. Conf. Learn. Represent.","author":"Alex"},{"key":"ref67","article-title":"EquiAV: Leveraging equivariance for audio-visual contrastive learning","author":"Kim","year":"2024","journal-title":"arXiv:2403.09502"},{"key":"ref68","article-title":"PandaGPT: One model to instruction-follow them all","author":"Su","year":"2023","journal-title":"arXiv:2305.16355"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02531"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11339259\/11151200.pdf?arnumber=11151200","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:02:05Z","timestamp":1768255325000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11151200\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":70,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3600878","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}