{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T02:02:42Z","timestamp":1782352962487,"version":"3.54.5"},"reference-count":31,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10446029","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"7890-7894","source":"Crossref","is-referenced-by-count":3,"title":["Unified Pretraining Target Based Video-Music Retrieval with Music Rhythm and Video Optical Flow Information"],"prefix":"10.1109","author":[{"given":"Tianjun","family":"Mao","sequence":"first","affiliation":[{"name":"Fudan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shansong","family":"Liu","sequence":"additional","affiliation":[{"name":"ARC Lab,Tencent PCG 3"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunxuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Fundamental Technology Center,Tencent PCG"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dian","family":"Li","sequence":"additional","affiliation":[{"name":"Fundamental Technology Center,Tencent PCG"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Shan","sequence":"additional","affiliation":[{"name":"ARC Lab,Tencent PCG 3"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"49","article-title":"The sound of an album cover: A probabilistic approach to multimedia","volume-title":"International Workshop on Artificial Intelligence and Statistics","author":"Brochu"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-21566-7_36"},{"key":"ref3","article-title":"Tunesensor: A semantic-driven music recommendation service for digital photo albums","volume-title":"Proceedings of the 10th International Semantic Web Conference. ISWC2011 (October 2011)","author":"Chao"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-04114-8_26"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2557722"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2018.07.001"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780195068276.001.0001"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3206025.3206046"},{"key":"ref9","first-page":"604","article-title":"Query by video: Cross-modal music retrieval","volume-title":"ISMIR","author":"Li"},{"key":"ref10","article-title":"Cross-modal variational auto-encoder for content-based micro-video background music recommendation","author":"Yi","year":"2021","journal-title":"IEEE Transactions on Multimedia"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3152598"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533662"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1147\/rd.14.0309"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1108\/eb026526"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01030"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462993"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref19","article-title":"musicnn: Pre-trained convolutional neural networks for music audio tagging","volume-title":"LBD-ISMIR","author":"Pons"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682475"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053135"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475195"},{"key":"ref25","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume-title":"Advances in neural information processing systems","volume":"32","author":"Paszke"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref27","article-title":"Pytorch implementation of conformer: Convolutionaugmented transformer for speech recognition","author":"Kim","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.25080\/majora-7b98e3ed-003"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref30","article-title":"Cross-modal retrieval between music and video","author":"Xu","year":"2022"},{"key":"ref31","article-title":"Youtube-8m: A large-scale video classification benchmark","author":"Abu-El-Haija","year":"2016"}],"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\/10446029.pdf?arnumber=10446029","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:37:49Z","timestamp":1722573469000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446029\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446029","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}