{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:36:48Z","timestamp":1753601808888,"version":"3.37.3"},"reference-count":13,"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\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002367","name":"Chinese Academy of Sciences","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012492","name":"Youth Innovation Promotion Association","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012492","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002367","name":"Chinese Academy of Sciences","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002367","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\/icassp49357.2023.10097072","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":5,"title":["CM-CS: Cross-Modal Common-Specific Feature Learning For Audio-Visual Video Parsing"],"prefix":"10.1109","author":[{"given":"Hongbo","family":"Chen","sequence":"first","affiliation":[{"name":"Chinese Academy of Sciences,Shanghai Institute of Microsystem and Information Technology,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongchen","family":"Zhu","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Shanghai Institute of Microsystem and Information Technology,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guanghui","family":"Zhang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Shanghai Institute of Microsystem and Information Technology,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenjun","family":"Shi","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Shanghai Institute of Microsystem and Information Technology,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaolin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Shanghai Institute of Microsystem and Information Technology,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiamao","family":"Li","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Shanghai Institute of Microsystem and Information Technology,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"247","article-title":"Audio-visual event localization in uneonstrained videos","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Tian"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00833"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_26"},{"key":"ref4","first-page":"11449","article-title":"Exploring cross-video and cross-modality signals for weakly-supervised audio-visual video parsing","volume":"34","author":"Lin","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00138"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413678"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01339"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20895"},{"journal-title":"Central moment diserepaney (cmd) for domain-invariant representation learning","year":"2017","author":"Zellinger","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.90"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00675"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683226"}],"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\/10097072.pdf?arnumber=10097072","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T08:34:51Z","timestamp":1710405291000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10097072\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":13,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10097072","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}