{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:17:29Z","timestamp":1740100649868,"version":"3.37.3"},"reference-count":23,"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\/icassp43922.2022.9747579","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"1975-1979","source":"Crossref","is-referenced-by-count":0,"title":["Navigating Audio-Visual Event Detection Across Mismatched Modalities"],"prefix":"10.1109","author":[{"given":"Guangwei","family":"Li","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,X-LANCE Lab,Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute,Shanghai,China"}]},{"given":"Xuenan","family":"Xu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,X-LANCE Lab,Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute,Shanghai,China"}]},{"given":"Mengyue","family":"Wu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,X-LANCE Lab,Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute,Shanghai,China"}]},{"given":"Kai","family":"Yu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,X-LANCE Lab,Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute,Shanghai,China"}]}],"member":"263","reference":[{"key":"ref10","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)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_26"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683226"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"article-title":"Ucf101: A dataset of 101 human actions classes from videos in the wild","year":"2012","author":"soomro","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414579"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3054313"},{"key":"ref18","first-page":"5100","article-title":"LXMert: Learning cross-modality encoder representations from transformers","author":"tan","year":"2020","journal-title":"EMNLP-IJCNLP 2019 - 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing Proceedings of the Conference"},{"journal-title":"EfficientNetV2 Smaller Models and Faster Training","year":"2021","author":"tan","key":"ref19"},{"key":"ref4","first-page":"558","article-title":"Large scale audio-visual learning of sounds with weakly labeled data","volume":"2021 janua","author":"fayek","year":"2020","journal-title":"IJCAI International Joint Conference on Artificial Intelligence"},{"article-title":"Perceiver: General Perception with Iterative Attention","year":"2021","author":"jaegle","key":"ref3"},{"key":"ref6","first-page":"631","article-title":"Audio-visual scene analysis with self-supervised multisensory features","author":"owens","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3120633"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3057230"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2028"},{"key":"ref2","first-page":"5612","article-title":"Multimodal transformer networks for end-to-end video-grounded dialogue systems","author":"le","year":"2020","journal-title":"ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics Proceedings of the Conference"},{"article-title":"OPT: Omni-Perception Pre-Trainer for Cross-Modal Understanding and Generation","year":"2021","author":"liu","key":"ref1"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2229"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref23","first-page":"5999","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2022,5,23]]},"location":"Singapore, Singapore","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\/09747579.pdf?arnumber=9747579","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:11:41Z","timestamp":1660594301000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747579\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747579","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}