{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:16:32Z","timestamp":1777889792655,"version":"3.51.4"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02069","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"22285-22293","source":"Crossref","is-referenced-by-count":0,"title":["Music Grounding by Short Video"],"prefix":"10.1109","author":[{"given":"Zijie","family":"Xin","sequence":"first","affiliation":[{"name":"Renmin University of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minquan","family":"Wang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingyu","family":"Liu","sequence":"additional","affiliation":[{"name":"Renmin University of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Quan","family":"Chen","sequence":"additional","affiliation":[{"name":"Kuaishou Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ye","family":"Ma","sequence":"additional","affiliation":[{"name":"Kuaishou Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Jiang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xirong","family":"Li","sequence":"additional","affiliation":[{"name":"Renmin University of China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"End-toend object detection with transformers","author":"Carion","year":"2020","journal-title":"ECCV"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1278"},{"key":"ref3","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020","journal-title":"ICML"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01214"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref6","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"Glorot","year":"2010","journal-title":"AISTATS"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-698"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00495"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3206025.3206046"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475281"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.5334\/tismir.14"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01273"},{"key":"ref15","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2015","journal-title":"ICLR"},{"key":"ref16","article-title":"Detecting moments and highlights in videos via natural language queries","author":"Lei","year":"2021","journal-title":"NeurIPS"},{"key":"ref17","article-title":"Query by video: Cross-modal music retrieval","author":"Li","year":"2019","journal-title":"ISMIR"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3042067"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i5.32585"},{"key":"ref20","author":"Loshchilov","year":"2016","journal-title":"SGDR: Stochastic gradient descent with warm restarts"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01420"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.01186"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02205"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3152598"},{"key":"ref25","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28304"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01031"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01622"},{"key":"ref29","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01770"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_11"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00134"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462874"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6984"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11443518.pdf?arnumber=11443518","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:19:51Z","timestamp":1777612791000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443518\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02069","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}