{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:49:51Z","timestamp":1773794991588,"version":"3.50.1"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746280","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"4868-4872","source":"Crossref","is-referenced-by-count":14,"title":["Bi-Directional Modality Fusion Network For Audio-Visual Event Localization"],"prefix":"10.1109","author":[{"given":"Shuo","family":"Liu","sequence":"first","affiliation":[{"name":"Chinese Academy of Sciences,Nlpr, Institute of Automation,Beijing,China"}]},{"given":"Weize","family":"Quan","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Nlpr, Institute of Automation,Beijing,China"}]},{"given":"Yuan","family":"Liu","sequence":"additional","affiliation":[{"name":"Alibaba Group,Speech Lab,China"}]},{"given":"Dong-Ming","family":"Yan","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Nlpr, Institute of Automation,Beijing,China"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00639"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00833"},{"key":"ref12","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"International Conference on Learning Representations"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref16","first-page":"1821","article-title":"Multi-modal factorized bilinear pooling with coattention learning for visual question answering","author":"yu","year":"2017","journal-title":"Proc of the IEEE International Conference on Computer Vision"},{"key":"ref17","article-title":"Refiner: Refining self-attention for vision transformers","author":"zhou","year":"2021","journal-title":"CoRR"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298968"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5361"},{"key":"ref4","first-page":"2002","article-title":"Dual-modality seq2seq network for audio-visual event localization","author":"frank","year":"2019","journal-title":"Proc of IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref3","first-page":"247","article-title":"Audio-visual event localization in unconstrained videos","author":"tian","year":"2018","journal-title":"Proc of the European Conference on Computer Vision"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413581"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053895"},{"key":"ref8","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proc of the North American Chapter of the Association for Computational Linguistics"},{"key":"ref7","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc of International Conference on Neural Information Processing"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.conb.2006.06.008"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1162\/1064546053278973"},{"key":"ref9","article-title":"Auditory-visual multisensory neurons and auditory-visual information integration in newborn rat cortex","author":"wang","year":"2006","journal-title":"Chinese Journal of Zoology"},{"key":"ref20","first-page":"2959","article-title":"See the sound, hear the pixels","author":"ramaswamy","year":"2020","journal-title":"IEEE Winter Conference on Applications of Computer Vision"},{"key":"ref21","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"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746280.pdf?arnumber=9746280","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:07:21Z","timestamp":1660594041000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746280\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746280","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}