{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:36:35Z","timestamp":1740101795204,"version":"3.37.3"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095807","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Collaborative Audio-Visual Event Localization Based on Sequential Decision and Cross-Modal Consistency"],"prefix":"10.1109","author":[{"given":"Yuqian","family":"Kuang","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology,Harbin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaopeng","family":"Fan","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Harbin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746955"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00406"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2_4"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3517472"},{"key":"ref20","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref11","article-title":"Contrastive positive sample propagation along the audiovisual event line","author":"zhou","year":"2022","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00833"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2019.05.009"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683226"},{"key":"ref1","first-page":"247","article-title":"Audio-visual event localization in unconstrained videos","author":"tian","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"article-title":"Layer normalization","year":"2016","author":"ba","key":"ref17"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref19","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref18","first-page":"111","article-title":"A theoretical analysis of feature pooling in visual recognition","author":"boureau","year":"2010","journal-title":"Proceedings of the 27th International Conference on Machine Learning (ICML-10)"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413581"},{"key":"ref7","article-title":"Audiovisual transformer with instance attention for audio-visual event localization","author":"lin","year":"2020","journal-title":"Proceedings of the Asian Conference on Computer Vision"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428373"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093616"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5361"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428081"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053895"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10095807.pdf?arnumber=10095807","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T19:03:24Z","timestamp":1699902204000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095807\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095807","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}