{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T17:01:59Z","timestamp":1777568519180,"version":"3.51.4"},"reference-count":15,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10446092","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"8421-8425","source":"Crossref","is-referenced-by-count":9,"title":["CM-PIE: Cross-Modal Perception for Interactive-Enhanced Audio-Visual Video Parsing"],"prefix":"10.1109","author":[{"given":"Yaru","family":"Chen","sequence":"first","affiliation":[{"name":"University of Surrey,Centre for Vision Speech and Signal Processing (CVSSP),United Kindom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruohao","family":"Guo","sequence":"additional","affiliation":[{"name":"Peking University,School of Intelligence Science and Technology,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xubo","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Surrey,Centre for Vision Speech and Signal Processing (CVSSP),United Kindom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peipei","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Surrey,Centre for Vision Speech and Signal Processing (CVSSP),United Kindom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangyao","family":"Li","sequence":"additional","affiliation":[{"name":"Renmin University of China,Gaoling School of Artificial Intelligence,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenbo","family":"Li","sequence":"additional","affiliation":[{"name":"China Agricultural University,College of Information and Electrical Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenwu","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Surrey,Centre for Vision Speech and Signal Processing (CVSSP),United Kindom"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-10073-7"},{"key":"ref2","author":"Wei","year":"2022","journal-title":"Learning in audiovisual context: A review, analysis, and new perspective"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00398"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01852"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00639"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_26"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547869"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097072"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1004649"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683226"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10446092.pdf?arnumber=10446092","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:02:17Z","timestamp":1722574937000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446092\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":15,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446092","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}