{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T16:25:19Z","timestamp":1778171119868,"version":"3.51.4"},"reference-count":62,"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":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62102418"],"award-info":[{"award-number":["62102418"]}],"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":["62172415"],"award-info":[{"award-number":["62172415"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key R&D Program of China","award":["2019YFB2204104"],"award-info":[{"award-number":["2019YFB2204104"]}]},{"name":"Alibaba Group through Alibaba Innovative Research Program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2022.3150469","type":"journal-article","created":{"date-parts":[[2022,2,12]],"date-time":"2022-02-12T00:26:09Z","timestamp":1644625569000},"page":"2734-2748","source":"Crossref","is-referenced-by-count":29,"title":["Dense Modality Interaction Network for Audio-Visual Event Localization"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9707-5572","authenticated-orcid":false,"given":"Shuo","family":"Liu","sequence":"first","affiliation":[{"name":"NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0892-581X","authenticated-orcid":false,"given":"Weize","family":"Quan","sequence":"additional","affiliation":[{"name":"NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chaoqun","family":"Wang","sequence":"additional","affiliation":[{"name":"NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan","family":"Liu","sequence":"additional","affiliation":[{"name":"Speech Lab, Alibaba Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1529-1552","authenticated-orcid":false,"given":"Bin","family":"Liu","sequence":"additional","affiliation":[{"name":"NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2209-2404","authenticated-orcid":false,"given":"Dong-Ming","family":"Yan","sequence":"additional","affiliation":[{"name":"NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1162\/1064546053278973"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.conb.2006.06.008"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2987728"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-021-1293-0"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462527"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2853566"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00182"},{"key":"ref8","first-page":"711","article-title":"Cross-modal embeddings for video and audio retrieval","volume-title":"Proc. IEEE Eur. Conf. Comput. Vis.","author":"Surs","year":"2019"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2922128"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3050089"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/6046.865479"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2008.922789"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.389"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683733"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461326"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2975922"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.264"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00374"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_44"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3005033"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053895"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5361"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69544-6_17"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00833"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683226"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00639"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413581"},{"key":"ref29","first-page":"6000","article-title":"Attention is all you need","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2017.2784878"},{"key":"ref31","first-page":"604","volume-title":"Query by video: Cross-modal music retrieval","author":"Li","year":"2019"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11024-6_44"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/78"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01271"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.667"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093616"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"},{"key":"ref42","first-page":"6510","article-title":"Compact generalized non-local network","volume-title":"Neural Inf. Process. Syst.","author":"Yue","year":"2018"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.17000"},{"issue":"245","key":"ref44","first-page":"2725","article-title":"One-shot object detection with co-attention and co-excitation","volume-title":"Neural Inf. Process. Syst.","volume":"32","author":"Hsieh","year":"2019"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00713"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2993176"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2017.8019301"},{"key":"ref48","article-title":"Neural language modeling with visual features","author":"Anastasopoulos","year":"2019"},{"key":"ref49","article-title":"Simple baseline for visual question answering","author":"Zhou","year":"2015"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref51","article-title":"OMNINET: A unified architecture for multi-modal multi-task learning","author":"Pramanik","year":"2019","journal-title":"arXiv:1907.07804"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d16-1044"},{"key":"ref53","first-page":"247","article-title":"Hadamard product for low-rank bilinear pooling","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kim","year":"2017"},{"key":"ref54","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan","year":"2015"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref58","first-page":"570","article-title":"A framework for multiple-instance learning","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Maron","year":"1998"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298968"},{"key":"ref60","article-title":"ADAM: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref61","first-page":"1247","article-title":"Deep canonical correlation analysis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Andrew","year":"2013"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_26"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09712233.pdf?arnumber=9712233","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,17]],"date-time":"2024-01-17T22:53:24Z","timestamp":1705532004000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9712233\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/tmm.2022.3150469","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}