{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T10:08:31Z","timestamp":1769594911859,"version":"3.49.0"},"reference-count":22,"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\/100017413","name":"Innovation Fund","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100017413","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\/icassp43922.2022.9747641","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T15:50:34Z","timestamp":1651074634000},"page":"4538-4542","source":"Crossref","is-referenced-by-count":2,"title":["Mixed In Time And Modality: Curse Or Blessing\u0192 Cross-Instance Data Augmentation for Weakly Supervised Multimodal Temporal Fusion"],"prefix":"10.1109","author":[{"given":"Yonggang","family":"Zhu","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Communications"}]},{"given":"Chao","family":"Tian","sequence":"additional","affiliation":[{"name":"China Xi’an Satellite Control Center"}]},{"given":"Zhuqing","family":"Jiang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Communications"}]},{"given":"Aidong","family":"Men","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Communications"}]},{"given":"Haiying","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Communications"}]},{"given":"Qingchao","family":"Chen","sequence":"additional","affiliation":[{"name":"Peking University"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682475"},{"key":"ref12","article-title":"Cooperative learning of audio and video models from self-supervised synchronization","author":"korbar","year":"2018","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5361"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093616"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413581"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00833"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00639"},{"key":"ref18","article-title":"Unified multisensory perception: Weakly-supervised audio-visual video parsing","author":"tian","year":"2020","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682847"},{"key":"ref4","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":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.tins.2015.12.007"},{"key":"ref6","article-title":"Audiovisual slowfast networks for video recognition","author":"xiao","year":"2020","journal-title":"arXiv preprint arXiv 2001 04786"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683226"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_18"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053895"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00037"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1186\/s13634-020-00675-6"},{"key":"ref22","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 (ACCV)"},{"key":"ref21","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NIPS)"}],"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\/09747641.pdf?arnumber=9747641","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T05:38:15Z","timestamp":1769492295000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747641\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747641","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}